diff options
Diffstat (limited to 'tools/perf/arch/x86')
23 files changed, 2021 insertions, 152 deletions
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 44f5aba78210..7eb5621c021d 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -196,8 +196,10 @@ static int x86__annotate_init(struct arch *arch, char *cpuid) if (arch->initialized) return 0; - if (cpuid) - err = x86__cpuid_parse(arch, cpuid); + if (cpuid) { + if (x86__cpuid_parse(arch, cpuid)) + err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING; + } arch->initialized = true; return err; diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index c29976eca4a8..44d510bc9b78 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -357,6 +357,8 @@ 433 common fspick __x64_sys_fspick 434 common pidfd_open __x64_sys_pidfd_open 435 common clone3 __x64_sys_clone3/ptregs +437 common openat2 __x64_sys_openat2 +438 common pidfd_getfd __x64_sys_pidfd_getfd # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c index f53e4406709f..adcacf1b6609 100644 --- a/tools/perf/arch/x86/tests/bp-modify.c +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -7,6 +7,7 @@ #include <unistd.h> #include <stdio.h> #include <stdlib.h> +#include <string.h> #include <sys/ptrace.h> #include <asm/ptrace.h> #include <errno.h> diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c index 6ad0a1cedb13..ef43be9b6ec2 100644 --- a/tools/perf/arch/x86/tests/dwarf-unwind.c +++ b/tools/perf/arch/x86/tests/dwarf-unwind.c @@ -3,7 +3,7 @@ #include "perf_regs.h" #include "thread.h" #include "map.h" -#include "map_groups.h" +#include "maps.h" #include "event.h" #include "debug.h" #include "tests/tests.h" @@ -27,7 +27,7 @@ static int sample_ustack(struct perf_sample *sample, sp = (unsigned long) regs[PERF_REG_X86_SP]; - map = map_groups__find(thread->mg, (u64)sp); + map = maps__find(thread->maps, (u64)sp); if (!map) { pr_debug("failed to get stack map\n"); free(buf); diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-32.c b/tools/perf/arch/x86/tests/insn-x86-dat-32.c index fab3c6de73fa..e6461abc9e7b 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-32.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-32.c @@ -667,6 +667,86 @@ "62 f2 55 0f 4f f4 \tvrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}",}, {{0x62, 0xf2, 0xd5, 0x0f, 0x4f, 0xf4, }, 6, 0, "", "", "62 f2 d5 0f 4f f4 \tvrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 50 d9 \tvpdpbusd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 50 d9 \tvpdpbusd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 50 d9 \tvpdpbusd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 50 9c c8 78 56 34 12 \tvpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 51 d9 \tvpdpbusds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 51 d9 \tvpdpbusds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 51 d9 \tvpdpbusds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 51 9c c8 78 56 34 12 \tvpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 08 52 d9 \tvdpbf16ps %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6e, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 28 52 d9 \tvdpbf16ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 48 52 d9 \tvdpbf16ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6e 48 52 9c c8 78 56 34 12 \tvdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 52 d9 \tvpdpwssd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 52 d9 \tvpdpwssd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 52 d9 \tvpdpwssd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 52 9c c8 78 56 34 12 \tvpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 52 20 \tvp4dpwssd (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 52 a4 c8 78 56 34 12 \tvp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 53 d9 \tvpdpwssds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 53 d9 \tvpdpwssds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 53 d9 \tvpdpwssds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 53 9c c8 78 56 34 12 \tvpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 53 20 \tvp4dpwssds (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 53 a4 c8 78 56 34 12 \tvp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 54 d1 \tvpopcntb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 54 d1 \tvpopcntb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 54 d1 \tvpopcntb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 54 94 c8 78 56 34 12 \tvpopcntb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 54 d1 \tvpopcntw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 54 d1 \tvpopcntw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 54 d1 \tvpopcntw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 54 94 c8 78 56 34 12 \tvpopcntw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 55 d1 \tvpopcntd %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 55 d1 \tvpopcntd %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 55 d1 \tvpopcntd %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 55 94 c8 78 56 34 12 \tvpopcntd 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 55 d1 \tvpopcntq %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 55 d1 \tvpopcntq %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 55 d1 \tvpopcntq %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 55 94 c8 78 56 34 12 \tvpopcntq 0x12345678(%eax,%ecx,8),%zmm2",}, {{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "", "c4 e2 79 59 f4 \tvpbroadcastq %xmm4,%xmm6",}, {{0x62, 0xf2, 0x7d, 0x48, 0x59, 0xf7, }, 6, 0, "", "", @@ -681,6 +761,38 @@ "62 f2 7d 48 5b 31 \tvbroadcasti32x8 (%ecx),%zmm6",}, {{0x62, 0xf2, 0xfd, 0x48, 0x5b, 0x31, }, 6, 0, "", "", "62 f2 fd 48 5b 31 \tvbroadcasti64x4 (%ecx),%zmm6",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 62 d1 \tvpexpandb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 62 d1 \tvpexpandb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 62 d1 \tvpexpandb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 62 94 c8 78 56 34 12 \tvpexpandb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 62 d1 \tvpexpandw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 62 d1 \tvpexpandw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 62 d1 \tvpexpandw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 62 94 c8 78 56 34 12 \tvpexpandw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 08 63 ca \tvpcompressb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 28 63 ca \tvpcompressb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 48 63 ca \tvpcompressb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 63 94 c8 78 56 34 12 \tvpcompressb %zmm2,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 08 63 ca \tvpcompressw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 28 63 ca \tvpcompressw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 48 63 ca \tvpcompressw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 63 94 c8 78 56 34 12 \tvpcompressw %zmm2,0x12345678(%eax,%ecx,8)",}, {{0x62, 0xf2, 0x55, 0x48, 0x64, 0xf4, }, 6, 0, "", "", "62 f2 55 48 64 f4 \tvpblendmd %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x64, 0xf4, }, 6, 0, "", "", @@ -693,6 +805,86 @@ "62 f2 55 48 66 f4 \tvpblendmb %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x66, 0xf4, }, 6, 0, "", "", "62 f2 d5 48 66 f4 \tvpblendmw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 68 d9 \tvp2intersectd %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 68 d9 \tvp2intersectd %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 68 d9 \tvp2intersectd %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 68 9c c8 78 56 34 12 \tvp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 08 68 d9 \tvp2intersectq %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 28 68 d9 \tvp2intersectq %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 48 68 d9 \tvp2intersectq %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ef 48 68 9c c8 78 56 34 12 \tvp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 70 d9 \tvpshldvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 70 d9 \tvpshldvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 70 d9 \tvpshldvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 70 9c c8 78 56 34 12 \tvpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 71 d9 \tvpshldvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 71 d9 \tvpshldvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 71 d9 \tvpshldvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 71 9c c8 78 56 34 12 \tvpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 71 d9 \tvpshldvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 71 d9 \tvpshldvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 71 d9 \tvpshldvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 71 9c c8 78 56 34 12 \tvpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 72 d9 \tvcvtne2ps2bf16 %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 72 d9 \tvcvtne2ps2bf16 %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 72 d9 \tvcvtne2ps2bf16 %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 72 9c c8 78 56 34 12 \tvcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7e, 0x08, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 08 72 d1 \tvcvtneps2bf16 %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x28, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 28 72 d1 \tvcvtneps2bf16 %ymm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 48 72 d1 \tvcvtneps2bf16 %zmm1,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7e 48 72 94 c8 78 56 34 12 \tvcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2",}, +{{0x62, 0xf2, 0xed, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 72 d9 \tvpshrdvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 72 d9 \tvpshrdvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 72 d9 \tvpshrdvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 72 9c c8 78 56 34 12 \tvpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 73 d9 \tvpshrdvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 73 d9 \tvpshrdvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 73 d9 \tvpshrdvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 73 9c c8 78 56 34 12 \tvpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 73 d9 \tvpshrdvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 73 d9 \tvpshrdvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 73 d9 \tvpshrdvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 73 9c c8 78 56 34 12 \tvpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0xf2, 0x55, 0x48, 0x75, 0xf4, }, 6, 0, "", "", "62 f2 55 48 75 f4 \tvpermi2b %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x75, 0xf4, }, 6, 0, "", "", @@ -745,6 +937,14 @@ "62 f2 55 48 8d f4 \tvpermb %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0x8d, 0xf4, }, 6, 0, "", "", "62 f2 d5 48 8d f4 \tvpermw %zmm4,%zmm5,%zmm6",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 8f d9 \tvpshufbitqmb %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 8f d9 \tvpshufbitqmb %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 8f d9 \tvpshufbitqmb %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 8f 9c c8 78 56 34 12 \tvpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, {{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", "c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%ebp,%xmm7,2),%xmm1",}, {{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "", @@ -761,6 +961,38 @@ "62 f2 7d 49 91 b4 fd 7b 00 00 00 \tvpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}",}, {{0x62, 0xf2, 0xfd, 0x49, 0x91, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 f2 fd 49 91 b4 fd 7b 00 00 00 \tvpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}",}, +{{0xc4, 0xe2, 0x69, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9a d9 \tvfmsub132ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 6d 9a d9 \tvfmsub132ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 9a d9 \tvfmsub132ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 9a 9c c8 78 56 34 12 \tvfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9a d9 \tvfmsub132pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 ed 9a d9 \tvfmsub132pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 9a d9 \tvfmsub132pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 9a 9c c8 78 56 34 12 \tvfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 9a 20 \tv4fmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 9a a4 c8 78 56 34 12 \tv4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9b d9 \tvfmsub132ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 9b 9c c8 78 56 34 12 \tvfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9b d9 \tvfmsub132sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 9b 9c c8 78 56 34 12 \tvfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 9b 20 \tv4fmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 9b a4 c8 78 56 34 12 \tv4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0xf2, 0x7d, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 f2 7d 49 a0 b4 fd 7b 00 00 00 \tvpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, {{0x62, 0xf2, 0xfd, 0x49, 0xa0, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", @@ -777,6 +1009,38 @@ "62 f2 7d 49 a3 b4 fd 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}",}, {{0x62, 0xf2, 0xfd, 0x49, 0xa3, 0xb4, 0xfd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 f2 fd 49 a3 b4 fd 7b 00 00 00 \tvscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}",}, +{{0xc4, 0xe2, 0x69, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 69 aa d9 \tvfmsub213ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 6d aa d9 \tvfmsub213ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 aa d9 \tvfmsub213ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 aa 9c c8 78 56 34 12 \tvfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 aa d9 \tvfmsub213pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 ed aa d9 \tvfmsub213pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 aa d9 \tvfmsub213pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 aa 9c c8 78 56 34 12 \tvfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 aa 20 \tv4fnmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 aa a4 c8 78 56 34 12 \tv4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 69 ab d9 \tvfmsub213ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 ab 9c c8 78 56 34 12 \tvfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 ab d9 \tvfmsub213sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 ab 9c c8 78 56 34 12 \tvfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 ab 20 \tv4fnmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 ab a4 c8 78 56 34 12 \tv4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0xf2, 0xd5, 0x48, 0xb4, 0xf4, }, 6, 0, "", "", "62 f2 d5 48 b4 f4 \tvpmadd52luq %zmm4,%zmm5,%zmm6",}, {{0x62, 0xf2, 0xd5, 0x48, 0xb5, 0xf4, }, 6, 0, "", "", @@ -805,6 +1069,50 @@ "62 f2 4d 0f cd fd \tvrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}",}, {{0x62, 0xf2, 0xcd, 0x0f, 0xcd, 0xfd, }, 6, 0, "", "", "62 f2 cd 0f cd fd \tvrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}",}, +{{0x66, 0x0f, 0x38, 0xcf, 0xd9, }, 5, 0, "", "", +"66 0f 38 cf d9 \tgf2p8mulb %xmm1,%xmm3",}, +{{0x66, 0x0f, 0x38, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"66 0f 38 cf 9c c8 78 56 34 12 \tgf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 cf d9 \tvgf2p8mulb %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d cf d9 \tvgf2p8mulb %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 cf d9 \tvgf2p8mulb %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 cf 9c c8 78 56 34 12 \tvgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dc d9 \tvaesenc %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dc d9 \tvaesenc %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dc d9 \tvaesenc %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dc 9c c8 78 56 34 12 \tvaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dd d9 \tvaesenclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dd d9 \tvaesenclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dd d9 \tvaesenclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dd 9c c8 78 56 34 12 \tvaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 69 de d9 \tvaesdec %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 6d de d9 \tvaesdec %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 de d9 \tvaesdec %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 de 9c c8 78 56 34 12 \tvaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 df d9 \tvaesdeclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d df d9 \tvaesdeclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 df d9 \tvaesdeclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 df 9c c8 78 56 34 12 \tvaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0xf3, 0x4d, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "", "62 f3 4d 48 03 fd 12 \tvalignd $0x12,%zmm5,%zmm6,%zmm7",}, {{0x62, 0xf3, 0xcd, 0x48, 0x03, 0xfd, 0x12, }, 7, 0, "", "", @@ -905,6 +1213,12 @@ "62 f3 4d 48 43 fd 12 \tvshufi32x4 $0x12,%zmm5,%zmm6,%zmm7",}, {{0x62, 0xf3, 0xcd, 0x48, 0x43, 0xfd, 0x12, }, 7, 0, "", "", "62 f3 cd 48 43 fd 12 \tvshufi64x2 $0x12,%zmm5,%zmm6,%zmm7",}, +{{0xc4, 0xe3, 0x69, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 69 44 d9 12 \tvpclmulqdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0x6d, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 6d 44 d9 12 \tvpclmulqdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x44, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 44 d9 12 \tvpclmulqdq $0x12,%zmm1,%zmm2,%zmm3",}, {{0x62, 0xf3, 0x4d, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "", "62 f3 4d 48 50 fd 12 \tvrangeps $0x12,%zmm5,%zmm6,%zmm7",}, {{0x62, 0xf3, 0xcd, 0x48, 0x50, 0xfd, 0x12, }, 7, 0, "", "", @@ -937,6 +1251,58 @@ "62 f3 7d 08 67 ef 12 \tvfpclassss $0x12,%xmm7,%k5",}, {{0x62, 0xf3, 0xfd, 0x08, 0x67, 0xef, 0x12, }, 7, 0, "", "", "62 f3 fd 08 67 ef 12 \tvfpclasssd $0x12,%xmm7,%k5",}, +{{0x62, 0xf3, 0xed, 0x08, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 70 d9 12 \tvpshldw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 70 d9 12 \tvpshldw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 70 d9 12 \tvpshldw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 71 d9 12 \tvpshldd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 71 d9 12 \tvpshldd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 71 d9 12 \tvpshldd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0xed, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 71 d9 12 \tvpshldq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 71 d9 12 \tvpshldq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 71 d9 12 \tvpshldq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0xed, 0x08, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 72 d9 12 \tvpshrdw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 72 d9 12 \tvpshrdw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 72 d9 12 \tvpshrdw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 73 d9 12 \tvpshrdd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 73 d9 12 \tvpshrdd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 73 d9 12 \tvpshrdd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf3, 0xed, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 73 d9 12 \tvpshrdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 73 d9 12 \tvpshrdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 73 d9 12 \tvpshrdq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x66, 0x0f, 0x3a, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a ce d9 12 \tgf2p8affineqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 ce d9 12 \tvgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed ce d9 12 \tvgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xce, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 ce d9 12 \tvgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x66, 0x0f, 0x3a, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a cf d9 12 \tgf2p8affineinvqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 cf d9 12 \tvgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed cf d9 12 \tvgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xcf, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 cf d9 12 \tvgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3",}, {{0x62, 0xf1, 0x4d, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "", "62 f1 4d 48 72 c5 12 \tvprord $0x12,%zmm5,%zmm6",}, {{0x62, 0xf1, 0xcd, 0x48, 0x72, 0xc5, 0x12, }, 7, 0, "", "", @@ -1647,6 +2013,12 @@ "0f ae 30 \txsaveopt (%eax)",}, {{0x0f, 0xae, 0xf0, }, 3, 0, "", "", "0f ae f0 \tmfence ",}, +{{0x0f, 0x1c, 0x00, }, 3, 0, "", "", +"0f 1c 00 \tcldemote (%eax)",}, +{{0x0f, 0x1c, 0x05, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", +"0f 1c 05 78 56 34 12 \tcldemote 0x12345678",}, +{{0x0f, 0x1c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"0f 1c 84 c8 78 56 34 12 \tcldemote 0x12345678(%eax,%ecx,8)",}, {{0x0f, 0xc7, 0x20, }, 3, 0, "", "", "0f c7 20 \txsavec (%eax)",}, {{0x0f, 0xc7, 0x25, 0x78, 0x56, 0x34, 0x12, }, 7, 0, "", "", @@ -1677,3 +2049,49 @@ "f3 0f ae 25 78 56 34 12 \tptwritel 0x12345678",}, {{0xf3, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", "f3 0f ae a4 c8 78 56 34 12 \tptwritel 0x12345678(%eax,%ecx,8)",}, +{{0x66, 0x0f, 0xae, 0xf3, }, 4, 0, "", "", +"66 0f ae f3 \ttpause %ebx",}, +{{0x67, 0xf3, 0x0f, 0xae, 0xf0, }, 5, 0, "", "", +"67 f3 0f ae f0 \tumonitor %ax",}, +{{0xf3, 0x0f, 0xae, 0xf0, }, 4, 0, "", "", +"f3 0f ae f0 \tumonitor %eax",}, +{{0xf2, 0x0f, 0xae, 0xf0, }, 4, 0, "", "", +"f2 0f ae f0 \tumwait %eax",}, +{{0x0f, 0x38, 0xf9, 0x03, }, 4, 0, "", "", +"0f 38 f9 03 \tmovdiri %eax,(%ebx)",}, +{{0x0f, 0x38, 0xf9, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"0f 38 f9 88 78 56 34 12 \tmovdiri %ecx,0x12345678(%eax)",}, +{{0x66, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "", +"66 0f 38 f8 18 \tmovdir64b (%eax),%ebx",}, +{{0x66, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"66 0f 38 f8 88 78 56 34 12 \tmovdir64b 0x12345678(%eax),%ecx",}, +{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x1c, }, 6, 0, "", "", +"67 66 0f 38 f8 1c \tmovdir64b (%si),%bx",}, +{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "", +"67 66 0f 38 f8 8c 34 12 \tmovdir64b 0x1234(%si),%cx",}, +{{0xf2, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "", +"f2 0f 38 f8 18 \tenqcmd (%eax),%ebx",}, +{{0xf2, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f2 0f 38 f8 88 78 56 34 12 \tenqcmd 0x12345678(%eax),%ecx",}, +{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x1c, }, 6, 0, "", "", +"67 f2 0f 38 f8 1c \tenqcmd (%si),%bx",}, +{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "", +"67 f2 0f 38 f8 8c 34 12 \tenqcmd 0x1234(%si),%cx",}, +{{0xf3, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "", +"f3 0f 38 f8 18 \tenqcmds (%eax),%ebx",}, +{{0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%eax),%ecx",}, +{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x1c, }, 6, 0, "", "", +"67 f3 0f 38 f8 1c \tenqcmds (%si),%bx",}, +{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x8c, 0x34, 0x12, }, 8, 0, "", "", +"67 f3 0f 38 f8 8c 34 12 \tenqcmds 0x1234(%si),%cx",}, +{{0x0f, 0x01, 0xcf, }, 3, 0, "", "", +"0f 01 cf \tencls ",}, +{{0x0f, 0x01, 0xd7, }, 3, 0, "", "", +"0f 01 d7 \tenclu ",}, +{{0x0f, 0x01, 0xc0, }, 3, 0, "", "", +"0f 01 c0 \tenclv ",}, +{{0x0f, 0x01, 0xc5, }, 3, 0, "", "", +"0f 01 c5 \tpconfig ",}, +{{0xf3, 0x0f, 0x09, }, 3, 0, "", "", +"f3 0f 09 \twbnoinvd ",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-64.c b/tools/perf/arch/x86/tests/insn-x86-dat-64.c index c57f34603b9b..567ecccfad7c 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-64.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-64.c @@ -587,6 +587,112 @@ "62 02 35 07 4f d0 \tvrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}",}, {{0x62, 0x02, 0xb5, 0x07, 0x4f, 0xd0, }, 6, 0, "", "", "62 02 b5 07 4f d0 \tvrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 50 d9 \tvpdpbusd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 50 d9 \tvpdpbusd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 50 d9 \tvpdpbusd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x50, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 50 9c c8 78 56 34 12 \tvpdpbusd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x50, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 50 9c c8 78 56 34 12 \tvpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 51 d9 \tvpdpbusds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 51 d9 \tvpdpbusds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 51 d9 \tvpdpbusds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x51, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 51 9c c8 78 56 34 12 \tvpdpbusds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x51, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 51 9c c8 78 56 34 12 \tvpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 08 52 d9 \tvdpbf16ps %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6e, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 28 52 d9 \tvdpbf16ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6e 48 52 d9 \tvdpbf16ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6e, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6e 48 52 9c c8 78 56 34 12 \tvdpbf16ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6e, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6e 48 52 9c c8 78 56 34 12 \tvdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 52 d9 \tvpdpwssd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 52 d9 \tvpdpwssd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 52 d9 \tvpdpwssd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 52 9c c8 78 56 34 12 \tvpdpwssd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x52, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 52 9c c8 78 56 34 12 \tvpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 52 20 \tvp4dpwssd (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x52, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 52 20 \tvp4dpwssd (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x52, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 52 a4 c8 78 56 34 12 \tvp4dpwssd 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x52, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 52 a4 c8 78 56 34 12 \tvp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 53 d9 \tvpdpwssds %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 53 d9 \tvpdpwssds %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 53 d9 \tvpdpwssds %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x53, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 53 9c c8 78 56 34 12 \tvpdpwssds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x53, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 53 9c c8 78 56 34 12 \tvpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 53 20 \tvp4dpwssds (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x53, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 53 20 \tvp4dpwssds (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x53, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 53 a4 c8 78 56 34 12 \tvp4dpwssds 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x53, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 53 a4 c8 78 56 34 12 \tvp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 54 d1 \tvpopcntb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 54 d1 \tvpopcntb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 54 d1 \tvpopcntb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 54 94 c8 78 56 34 12 \tvpopcntb 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 54 94 c8 78 56 34 12 \tvpopcntb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 54 d1 \tvpopcntw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 54 d1 \tvpopcntw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 54 d1 \tvpopcntw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 54 94 c8 78 56 34 12 \tvpopcntw 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x54, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 54 94 c8 78 56 34 12 \tvpopcntw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 55 d1 \tvpopcntd %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 55 d1 \tvpopcntd %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 55 d1 \tvpopcntd %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 55 94 c8 78 56 34 12 \tvpopcntd 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 55 94 c8 78 56 34 12 \tvpopcntd 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 55 d1 \tvpopcntq %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 55 d1 \tvpopcntq %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 55 d1 \tvpopcntq %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 55 94 c8 78 56 34 12 \tvpopcntq 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x55, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 55 94 c8 78 56 34 12 \tvpopcntq 0x12345678(%eax,%ecx,8),%zmm2",}, {{0xc4, 0xe2, 0x79, 0x59, 0xf4, }, 5, 0, "", "", "c4 e2 79 59 f4 \tvpbroadcastq %xmm4,%xmm6",}, {{0x62, 0x02, 0x7d, 0x48, 0x59, 0xd3, }, 6, 0, "", "", @@ -601,6 +707,46 @@ "62 62 7d 48 5b 21 \tvbroadcasti32x8 (%rcx),%zmm28",}, {{0x62, 0x62, 0xfd, 0x48, 0x5b, 0x11, }, 6, 0, "", "", "62 62 fd 48 5b 11 \tvbroadcasti64x4 (%rcx),%zmm26",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 08 62 d1 \tvpexpandb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 28 62 d1 \tvpexpandb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 7d 48 62 d1 \tvpexpandb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 62 94 c8 78 56 34 12 \tvpexpandb 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 62 94 c8 78 56 34 12 \tvpexpandb 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 08 62 d1 \tvpexpandw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 28 62 d1 \tvpexpandw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0xd1, }, 6, 0, "", "", +"62 f2 fd 48 62 d1 \tvpexpandw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 62 94 c8 78 56 34 12 \tvpexpandw 0x12345678(%rax,%rcx,8),%zmm2",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x62, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 62 94 c8 78 56 34 12 \tvpexpandw 0x12345678(%eax,%ecx,8),%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 08 63 ca \tvpcompressb %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7d, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 28 63 ca \tvpcompressb %ymm1,%ymm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 7d 48 63 ca \tvpcompressb %zmm1,%zmm2",}, +{{0x62, 0xf2, 0x7d, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7d 48 63 94 c8 78 56 34 12 \tvpcompressb %zmm2,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf2, 0x7d, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7d 48 63 94 c8 78 56 34 12 \tvpcompressb %zmm2,0x12345678(%eax,%ecx,8)",}, +{{0x62, 0xf2, 0xfd, 0x08, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 08 63 ca \tvpcompressw %xmm1,%xmm2",}, +{{0x62, 0xf2, 0xfd, 0x28, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 28 63 ca \tvpcompressw %ymm1,%ymm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0xca, }, 6, 0, "", "", +"62 f2 fd 48 63 ca \tvpcompressw %zmm1,%zmm2",}, +{{0x62, 0xf2, 0xfd, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 fd 48 63 94 c8 78 56 34 12 \tvpcompressw %zmm2,0x12345678(%rax,%rcx,8)",}, +{{0x67, 0x62, 0xf2, 0xfd, 0x48, 0x63, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 fd 48 63 94 c8 78 56 34 12 \tvpcompressw %zmm2,0x12345678(%eax,%ecx,8)",}, {{0x62, 0x02, 0x25, 0x40, 0x64, 0xe2, }, 6, 0, "", "", "62 02 25 40 64 e2 \tvpblendmd %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0x64, 0xe2, }, 6, 0, "", "", @@ -613,6 +759,106 @@ "62 02 25 40 66 e2 \tvpblendmb %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0x66, 0xe2, }, 6, 0, "", "", "62 02 a5 40 66 e2 \tvpblendmw %zmm26,%zmm27,%zmm28",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 68 d9 \tvp2intersectd %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 68 d9 \tvp2intersectd %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 68 d9 \tvp2intersectd %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 68 9c c8 78 56 34 12 \tvp2intersectd 0x12345678(%rax,%rcx,8),%zmm2,%k3",}, +{{0x67, 0x62, 0xf2, 0x6f, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6f 48 68 9c c8 78 56 34 12 \tvp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x08, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 08 68 d9 \tvp2intersectq %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x28, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 28 68 d9 \tvp2intersectq %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0xd9, }, 6, 0, "", "", +"62 f2 ef 48 68 d9 \tvp2intersectq %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0xef, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ef 48 68 9c c8 78 56 34 12 \tvp2intersectq 0x12345678(%rax,%rcx,8),%zmm2,%k3",}, +{{0x67, 0x62, 0xf2, 0xef, 0x48, 0x68, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ef 48 68 9c c8 78 56 34 12 \tvp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 70 d9 \tvpshldvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 70 d9 \tvpshldvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 70 d9 \tvpshldvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x70, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 70 9c c8 78 56 34 12 \tvpshldvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x70, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 70 9c c8 78 56 34 12 \tvpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 71 d9 \tvpshldvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 71 d9 \tvpshldvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 71 d9 \tvpshldvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 71 9c c8 78 56 34 12 \tvpshldvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 71 9c c8 78 56 34 12 \tvpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 71 d9 \tvpshldvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 71 d9 \tvpshldvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 71 d9 \tvpshldvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 71 9c c8 78 56 34 12 \tvpshldvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x71, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 71 9c c8 78 56 34 12 \tvpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 08 72 d9 \tvcvtne2ps2bf16 %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6f, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 28 72 d9 \tvcvtne2ps2bf16 %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 6f 48 72 d9 \tvcvtne2ps2bf16 %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6f, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6f 48 72 9c c8 78 56 34 12 \tvcvtne2ps2bf16 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6f, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6f 48 72 9c c8 78 56 34 12 \tvcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7e, 0x08, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 08 72 d1 \tvcvtneps2bf16 %xmm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x28, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 28 72 d1 \tvcvtneps2bf16 %ymm1,%xmm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0xd1, }, 6, 0, "", "", +"62 f2 7e 48 72 d1 \tvcvtneps2bf16 %zmm1,%ymm2",}, +{{0x62, 0xf2, 0x7e, 0x48, 0x72, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7e 48 72 94 c8 78 56 34 12 \tvcvtneps2bf16 0x12345678(%rax,%rcx,8),%ymm2",}, +{{0x67, 0x62, 0xf2, 0x7e, 0x48, 0x72, 0x94, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7e 48 72 94 c8 78 56 34 12 \tvcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2",}, +{{0x62, 0xf2, 0xed, 0x08, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 72 d9 \tvpshrdvw %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 72 d9 \tvpshrdvw %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 72 d9 \tvpshrdvw %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 72 9c c8 78 56 34 12 \tvpshrdvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x72, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 72 9c c8 78 56 34 12 \tvpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 73 d9 \tvpshrdvd %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 73 d9 \tvpshrdvd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 73 d9 \tvpshrdvd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 73 9c c8 78 56 34 12 \tvpshrdvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 73 9c c8 78 56 34 12 \tvpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x08, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 08 73 d9 \tvpshrdvq %xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf2, 0xed, 0x28, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 28 73 d9 \tvpshrdvq %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 73 d9 \tvpshrdvq %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 73 9c c8 78 56 34 12 \tvpshrdvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x73, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 73 9c c8 78 56 34 12 \tvpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0x02, 0x35, 0x40, 0x75, 0xd0, }, 6, 0, "", "", "62 02 35 40 75 d0 \tvpermi2b %zmm24,%zmm25,%zmm26",}, {{0x62, 0x02, 0xa5, 0x40, 0x75, 0xe2, }, 6, 0, "", "", @@ -667,6 +913,16 @@ "62 02 25 40 8d e2 \tvpermb %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0x8d, 0xe2, }, 6, 0, "", "", "62 02 a5 40 8d e2 \tvpermw %zmm26,%zmm27,%zmm28",}, +{{0x62, 0xf2, 0x6d, 0x08, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 08 8f d9 \tvpshufbitqmb %xmm1,%xmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x28, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 28 8f d9 \tvpshufbitqmb %ymm1,%ymm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 8f d9 \tvpshufbitqmb %zmm1,%zmm2,%k3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x8f, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 8f 9c c8 78 56 34 12 \tvpshufbitqmb 0x12345678(%rax,%rcx,8),%zmm2,%k3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x8f, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 8f 9c c8 78 56 34 12 \tvpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3",}, {{0xc4, 0xe2, 0x69, 0x90, 0x4c, 0x7d, 0x02, }, 7, 0, "", "", "c4 e2 69 90 4c 7d 02 \tvpgatherdd %xmm2,0x2(%rbp,%xmm7,2),%xmm1",}, {{0xc4, 0xe2, 0xe9, 0x90, 0x4c, 0x7d, 0x04, }, 7, 0, "", "", @@ -683,6 +939,54 @@ "62 22 7d 41 91 94 dd 7b 00 00 00 \tvpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}",}, {{0x62, 0x22, 0xfd, 0x41, 0x91, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 22 fd 41 91 94 dd 7b 00 00 00 \tvpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}",}, +{{0xc4, 0xe2, 0x69, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9a d9 \tvfmsub132ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 6d 9a d9 \tvfmsub132ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 9a d9 \tvfmsub132ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 9a 9c c8 78 56 34 12 \tvfmsub132ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 9a 9c c8 78 56 34 12 \tvfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9a d9 \tvfmsub132pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0x9a, 0xd9, }, 5, 0, "", "", +"c4 e2 ed 9a d9 \tvfmsub132pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 9a d9 \tvfmsub132pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 9a 9c c8 78 56 34 12 \tvfmsub132pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0x9a, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 9a 9c c8 78 56 34 12 \tvfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 9a 20 \tv4fmaddps (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x9a, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 9a 20 \tv4fmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0x9a, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 9a a4 c8 78 56 34 12 \tv4fmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0x9a, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 9a a4 c8 78 56 34 12 \tv4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 69 9b d9 \tvfmsub132ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 9b 9c c8 78 56 34 12 \tvfmsub132ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0x69, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 69 9b 9c c8 78 56 34 12 \tvfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 9b d9 \tvfmsub132sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 9b 9c c8 78 56 34 12 \tvfmsub132sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0xe9, 0x9b, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 e9 9b 9c c8 78 56 34 12 \tvfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 9b 20 \tv4fmaddss (%rax),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0x9b, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 08 9b 20 \tv4fmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0x9b, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 9b a4 c8 78 56 34 12 \tv4fmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0x9b, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 08 9b a4 c8 78 56 34 12 \tv4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0x22, 0x7d, 0x41, 0xa0, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 22 7d 41 a0 a4 ed 7b 00 00 00 \tvpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, {{0x62, 0x22, 0xfd, 0x41, 0xa0, 0x94, 0xdd, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", @@ -699,6 +1003,54 @@ "62 b2 7d 41 a3 b4 ed 7b 00 00 00 \tvscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}",}, {{0x62, 0x22, 0xfd, 0x41, 0xa3, 0xa4, 0xed, 0x7b, 0x00, 0x00, 0x00, }, 11, 0, "", "", "62 22 fd 41 a3 a4 ed 7b 00 00 00 \tvscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}",}, +{{0xc4, 0xe2, 0x69, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 69 aa d9 \tvfmsub213ps %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 6d aa d9 \tvfmsub213ps %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 aa d9 \tvfmsub213ps %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 aa 9c c8 78 56 34 12 \tvfmsub213ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 aa 9c c8 78 56 34 12 \tvfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0xe9, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 aa d9 \tvfmsub213pd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xed, 0xaa, 0xd9, }, 5, 0, "", "", +"c4 e2 ed aa d9 \tvfmsub213pd %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0xd9, }, 6, 0, "", "", +"62 f2 ed 48 aa d9 \tvfmsub213pd %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0xed, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 ed 48 aa 9c c8 78 56 34 12 \tvfmsub213pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0xed, 0x48, 0xaa, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 ed 48 aa 9c c8 78 56 34 12 \tvfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0x20, }, 6, 0, "", "", +"62 f2 7f 48 aa 20 \tv4fnmaddps (%rax),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0xaa, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 48 aa 20 \tv4fnmaddps (%eax),%zmm0,%zmm4",}, +{{0x62, 0xf2, 0x7f, 0x48, 0xaa, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 48 aa a4 c8 78 56 34 12 \tv4fnmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x48, 0xaa, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 48 aa a4 c8 78 56 34 12 \tv4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4",}, +{{0xc4, 0xe2, 0x69, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 69 ab d9 \tvfmsub213ss %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 69 ab 9c c8 78 56 34 12 \tvfmsub213ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0x69, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 69 ab 9c c8 78 56 34 12 \tvfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0xd9, }, 5, 0, "", "", +"c4 e2 e9 ab d9 \tvfmsub213sd %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0xe9, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"c4 e2 e9 ab 9c c8 78 56 34 12 \tvfmsub213sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3",}, +{{0x67, 0xc4, 0xe2, 0xe9, 0xab, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 c4 e2 e9 ab 9c c8 78 56 34 12 \tvfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0x20, }, 6, 0, "", "", +"62 f2 7f 08 ab 20 \tv4fnmaddss (%rax),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0xab, 0x20, }, 7, 0, "", "", +"67 62 f2 7f 08 ab 20 \tv4fnmaddss (%eax),%xmm0,%xmm4",}, +{{0x62, 0xf2, 0x7f, 0x08, 0xab, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 7f 08 ab a4 c8 78 56 34 12 \tv4fnmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4",}, +{{0x67, 0x62, 0xf2, 0x7f, 0x08, 0xab, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 7f 08 ab a4 c8 78 56 34 12 \tv4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4",}, {{0x62, 0x02, 0xa5, 0x40, 0xb4, 0xe2, }, 6, 0, "", "", "62 02 a5 40 b4 e2 \tvpmadd52luq %zmm26,%zmm27,%zmm28",}, {{0x62, 0x02, 0xa5, 0x40, 0xb5, 0xe2, }, 6, 0, "", "", @@ -727,6 +1079,62 @@ "62 02 15 07 cd f4 \tvrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}",}, {{0x62, 0x02, 0xad, 0x07, 0xcd, 0xd9, }, 6, 0, "", "", "62 02 ad 07 cd d9 \tvrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}",}, +{{0x66, 0x0f, 0x38, 0xcf, 0xd9, }, 5, 0, "", "", +"66 0f 38 cf d9 \tgf2p8mulb %xmm1,%xmm3",}, +{{0x66, 0x0f, 0x38, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"66 0f 38 cf 9c c8 78 56 34 12 \tgf2p8mulb 0x12345678(%rax,%rcx,8),%xmm3",}, +{{0x67, 0x66, 0x0f, 0x38, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"67 66 0f 38 cf 9c c8 78 56 34 12 \tgf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3",}, +{{0xc4, 0xe2, 0x69, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 cf d9 \tvgf2p8mulb %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xcf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d cf d9 \tvgf2p8mulb %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 cf d9 \tvgf2p8mulb %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 cf 9c c8 78 56 34 12 \tvgf2p8mulb 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xcf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 cf 9c c8 78 56 34 12 \tvgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dc d9 \tvaesenc %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdc, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dc d9 \tvaesenc %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dc d9 \tvaesenc %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdc, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dc 9c c8 78 56 34 12 \tvaesenc 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xdc, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 dc 9c c8 78 56 34 12 \tvaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 69 dd d9 \tvaesenclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdd, 0xd9, }, 5, 0, "", "", +"c4 e2 6d dd d9 \tvaesenclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 dd d9 \tvaesenclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdd, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 dd 9c c8 78 56 34 12 \tvaesenclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xdd, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 dd 9c c8 78 56 34 12 \tvaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 69 de d9 \tvaesdec %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xde, 0xd9, }, 5, 0, "", "", +"c4 e2 6d de d9 \tvaesdec %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 de d9 \tvaesdec %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xde, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 de 9c c8 78 56 34 12 \tvaesdec 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xde, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 de 9c c8 78 56 34 12 \tvaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, +{{0xc4, 0xe2, 0x69, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 69 df d9 \tvaesdeclast %xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe2, 0x6d, 0xdf, 0xd9, }, 5, 0, "", "", +"c4 e2 6d df d9 \tvaesdeclast %ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0xd9, }, 6, 0, "", "", +"62 f2 6d 48 df d9 \tvaesdeclast %zmm1,%zmm2,%zmm3",}, +{{0x62, 0xf2, 0x6d, 0x48, 0xdf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 11, 0, "", "", +"62 f2 6d 48 df 9c c8 78 56 34 12 \tvaesdeclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3",}, +{{0x67, 0x62, 0xf2, 0x6d, 0x48, 0xdf, 0x9c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 12, 0, "", "", +"67 62 f2 6d 48 df 9c c8 78 56 34 12 \tvaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3",}, {{0x62, 0x03, 0x15, 0x40, 0x03, 0xf4, 0x12, }, 7, 0, "", "", "62 03 15 40 03 f4 12 \tvalignd $0x12,%zmm28,%zmm29,%zmm30",}, {{0x62, 0x03, 0xad, 0x40, 0x03, 0xd9, 0x12, }, 7, 0, "", "", @@ -827,6 +1235,14 @@ "62 03 2d 40 43 d9 12 \tvshufi32x4 $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x03, 0x95, 0x40, 0x43, 0xf4, 0x12, }, 7, 0, "", "", "62 03 95 40 43 f4 12 \tvshufi64x2 $0x12,%zmm28,%zmm29,%zmm30",}, +{{0xc4, 0xe3, 0x69, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 69 44 d9 12 \tvpclmulqdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0x6d, 0x44, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 6d 44 d9 12 \tvpclmulqdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x44, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 44 d9 12 \tvpclmulqdq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0x2d, 0x40, 0x44, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 44 d9 12 \tvpclmulqdq $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x03, 0x2d, 0x40, 0x50, 0xd9, 0x12, }, 7, 0, "", "", "62 03 2d 40 50 d9 12 \tvrangeps $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x03, 0x95, 0x40, 0x50, 0xf4, 0x12, }, 7, 0, "", "", @@ -859,6 +1275,74 @@ "62 93 7d 08 67 eb 12 \tvfpclassss $0x12,%xmm27,%k5",}, {{0x62, 0x93, 0xfd, 0x08, 0x67, 0xee, 0x12, }, 7, 0, "", "", "62 93 fd 08 67 ee 12 \tvfpclasssd $0x12,%xmm30,%k5",}, +{{0x62, 0xf3, 0xed, 0x08, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 70 d9 12 \tvpshldw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 70 d9 12 \tvpshldw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 70 d9 12 \tvpshldw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x70, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 70 d9 12 \tvpshldw $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 71 d9 12 \tvpshldd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 71 d9 12 \tvpshldd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 71 d9 12 \tvpshldd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0x2d, 0x40, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 71 d9 12 \tvpshldd $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0xed, 0x08, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 71 d9 12 \tvpshldq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 71 d9 12 \tvpshldq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 71 d9 12 \tvpshldq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x71, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 71 d9 12 \tvpshldq $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0xed, 0x08, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 72 d9 12 \tvpshrdw $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 72 d9 12 \tvpshrdw $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 72 d9 12 \tvpshrdw $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x72, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 72 d9 12 \tvpshrdw $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0x6d, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 08 73 d9 12 \tvpshrdd $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0x6d, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 28 73 d9 12 \tvpshrdd $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0x6d, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 6d 48 73 d9 12 \tvpshrdd $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0x2d, 0x40, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 2d 40 73 d9 12 \tvpshrdd $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x62, 0xf3, 0xed, 0x08, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 08 73 d9 12 \tvpshrdq $0x12,%xmm1,%xmm2,%xmm3",}, +{{0x62, 0xf3, 0xed, 0x28, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 28 73 d9 12 \tvpshrdq $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 73 d9 12 \tvpshrdq $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0x73, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 73 d9 12 \tvpshrdq $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x66, 0x0f, 0x3a, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a ce d9 12 \tgf2p8affineqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 ce d9 12 \tvgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xce, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed ce d9 12 \tvgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xce, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 ce d9 12 \tvgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0xce, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 ce d9 12 \tvgf2p8affineqb $0x12,%zmm25,%zmm26,%zmm27",}, +{{0x66, 0x0f, 0x3a, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"66 0f 3a cf d9 12 \tgf2p8affineinvqb $0x12,%xmm1,%xmm3",}, +{{0xc4, 0xe3, 0xe9, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 e9 cf d9 12 \tvgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3",}, +{{0xc4, 0xe3, 0xed, 0xcf, 0xd9, 0x12, }, 6, 0, "", "", +"c4 e3 ed cf d9 12 \tvgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3",}, +{{0x62, 0xf3, 0xed, 0x48, 0xcf, 0xd9, 0x12, }, 7, 0, "", "", +"62 f3 ed 48 cf d9 12 \tvgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3",}, +{{0x62, 0x03, 0xad, 0x40, 0xcf, 0xd9, 0x12, }, 7, 0, "", "", +"62 03 ad 40 cf d9 12 \tvgf2p8affineinvqb $0x12,%zmm25,%zmm26,%zmm27",}, {{0x62, 0x91, 0x2d, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "", "62 91 2d 40 72 c1 12 \tvprord $0x12,%zmm25,%zmm26",}, {{0x62, 0x91, 0xad, 0x40, 0x72, 0xc1, 0x12, }, 7, 0, "", "", @@ -1667,6 +2151,16 @@ "41 0f ae 30 \txsaveopt (%r8)",}, {{0x0f, 0xae, 0xf0, }, 3, 0, "", "", "0f ae f0 \tmfence ",}, +{{0x0f, 0x1c, 0x00, }, 3, 0, "", "", +"0f 1c 00 \tcldemote (%rax)",}, +{{0x41, 0x0f, 0x1c, 0x00, }, 4, 0, "", "", +"41 0f 1c 00 \tcldemote (%r8)",}, +{{0x0f, 0x1c, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"0f 1c 04 25 78 56 34 12 \tcldemote 0x12345678",}, +{{0x0f, 0x1c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "", +"0f 1c 84 c8 78 56 34 12 \tcldemote 0x12345678(%rax,%rcx,8)",}, +{{0x41, 0x0f, 0x1c, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"41 0f 1c 84 c8 78 56 34 12 \tcldemote 0x12345678(%r8,%rcx,8)",}, {{0x0f, 0xc7, 0x20, }, 3, 0, "", "", "0f c7 20 \txsavec (%rax)",}, {{0x41, 0x0f, 0xc7, 0x20, }, 4, 0, "", "", @@ -1727,3 +2221,55 @@ "f3 48 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%rax,%rcx,8)",}, {{0xf3, 0x49, 0x0f, 0xae, 0xa4, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", "f3 49 0f ae a4 c8 78 56 34 12 \tptwriteq 0x12345678(%r8,%rcx,8)",}, +{{0x66, 0x0f, 0xae, 0xf3, }, 4, 0, "", "", +"66 0f ae f3 \ttpause %ebx",}, +{{0x66, 0x41, 0x0f, 0xae, 0xf0, }, 5, 0, "", "", +"66 41 0f ae f0 \ttpause %r8d",}, +{{0x67, 0xf3, 0x0f, 0xae, 0xf0, }, 5, 0, "", "", +"67 f3 0f ae f0 \tumonitor %eax",}, +{{0xf3, 0x0f, 0xae, 0xf0, }, 4, 0, "", "", +"f3 0f ae f0 \tumonitor %rax",}, +{{0x67, 0xf3, 0x41, 0x0f, 0xae, 0xf0, }, 6, 0, "", "", +"67 f3 41 0f ae f0 \tumonitor %r8d",}, +{{0xf2, 0x0f, 0xae, 0xf0, }, 4, 0, "", "", +"f2 0f ae f0 \tumwait %eax",}, +{{0xf2, 0x41, 0x0f, 0xae, 0xf0, }, 5, 0, "", "", +"f2 41 0f ae f0 \tumwait %r8d",}, +{{0x48, 0x0f, 0x38, 0xf9, 0x03, }, 5, 0, "", "", +"48 0f 38 f9 03 \tmovdiri %rax,(%rbx)",}, +{{0x48, 0x0f, 0x38, 0xf9, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"48 0f 38 f9 88 78 56 34 12 \tmovdiri %rcx,0x12345678(%rax)",}, +{{0x66, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "", +"66 0f 38 f8 18 \tmovdir64b (%rax),%rbx",}, +{{0x66, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"66 0f 38 f8 88 78 56 34 12 \tmovdir64b 0x12345678(%rax),%rcx",}, +{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x18, }, 6, 0, "", "", +"67 66 0f 38 f8 18 \tmovdir64b (%eax),%ebx",}, +{{0x67, 0x66, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"67 66 0f 38 f8 88 78 56 34 12 \tmovdir64b 0x12345678(%eax),%ecx",}, +{{0xf2, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "", +"f2 0f 38 f8 18 \tenqcmd (%rax),%rbx",}, +{{0xf2, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f2 0f 38 f8 88 78 56 34 12 \tenqcmd 0x12345678(%rax),%rcx",}, +{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x18, }, 6, 0, "", "", +"67 f2 0f 38 f8 18 \tenqcmd (%eax),%ebx",}, +{{0x67, 0xf2, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"67 f2 0f 38 f8 88 78 56 34 12 \tenqcmd 0x12345678(%eax),%ecx",}, +{{0xf3, 0x0f, 0x38, 0xf8, 0x18, }, 5, 0, "", "", +"f3 0f 38 f8 18 \tenqcmds (%rax),%rbx",}, +{{0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "", +"f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%rax),%rcx",}, +{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x18, }, 6, 0, "", "", +"67 f3 0f 38 f8 18 \tenqcmds (%eax),%ebx",}, +{{0x67, 0xf3, 0x0f, 0x38, 0xf8, 0x88, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "", +"67 f3 0f 38 f8 88 78 56 34 12 \tenqcmds 0x12345678(%eax),%ecx",}, +{{0x0f, 0x01, 0xcf, }, 3, 0, "", "", +"0f 01 cf \tencls ",}, +{{0x0f, 0x01, 0xd7, }, 3, 0, "", "", +"0f 01 d7 \tenclu ",}, +{{0x0f, 0x01, 0xc0, }, 3, 0, "", "", +"0f 01 c0 \tenclv ",}, +{{0x0f, 0x01, 0xc5, }, 3, 0, "", "", +"0f 01 c5 \tpconfig ",}, +{{0xf3, 0x0f, 0x09, }, 3, 0, "", "", +"f3 0f 09 \twbnoinvd ",}, diff --git a/tools/perf/arch/x86/tests/insn-x86-dat-src.c b/tools/perf/arch/x86/tests/insn-x86-dat-src.c index 891415b10984..ddbf07c50bb8 100644 --- a/tools/perf/arch/x86/tests/insn-x86-dat-src.c +++ b/tools/perf/arch/x86/tests/insn-x86-dat-src.c @@ -510,6 +510,82 @@ int main(void) asm volatile("vrsqrt14ss %xmm24,%xmm25,%xmm26{%k7}"); asm volatile("vrsqrt14sd %xmm24,%xmm25,%xmm26{%k7}"); + /* AVX-512: Op code 0f 38 50 */ + + asm volatile("vpdpbusd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 51 */ + + asm volatile("vpdpbusds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 52 */ + + asm volatile("vdpbf16ps %xmm1, %xmm2, %xmm3"); + asm volatile("vdpbf16ps %ymm1, %ymm2, %ymm3"); + asm volatile("vdpbf16ps %zmm1, %zmm2, %zmm3"); + asm volatile("vdpbf16ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpdpwssd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssd (%rax), %zmm0, %zmm4"); + asm volatile("vp4dpwssd (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssd 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("vp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 53 */ + + asm volatile("vpdpwssds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssds 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssds (%rax), %zmm0, %zmm4"); + asm volatile("vp4dpwssds (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssds 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("vp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 54 */ + + asm volatile("vpopcntb %xmm1, %xmm2"); + asm volatile("vpopcntb %ymm1, %ymm2"); + asm volatile("vpopcntb %zmm1, %zmm2"); + asm volatile("vpopcntb 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntw %xmm1, %xmm2"); + asm volatile("vpopcntw %ymm1, %ymm2"); + asm volatile("vpopcntw %zmm1, %zmm2"); + asm volatile("vpopcntw 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 55 */ + + asm volatile("vpopcntd %xmm1, %xmm2"); + asm volatile("vpopcntd %ymm1, %ymm2"); + asm volatile("vpopcntd %zmm1, %zmm2"); + asm volatile("vpopcntd 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntd 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntq %xmm1, %xmm2"); + asm volatile("vpopcntq %ymm1, %ymm2"); + asm volatile("vpopcntq %zmm1, %zmm2"); + asm volatile("vpopcntq 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpopcntq 0x12345678(%eax,%ecx,8),%zmm2"); + /* AVX-512: Op code 0f 38 59 */ asm volatile("vpbroadcastq %xmm4,%xmm6"); @@ -526,6 +602,34 @@ int main(void) asm volatile("vbroadcasti32x8 (%rcx),%zmm28"); asm volatile("vbroadcasti64x4 (%rcx),%zmm26"); + /* AVX-512: Op code 0f 38 62 */ + + asm volatile("vpexpandb %xmm1, %xmm2"); + asm volatile("vpexpandb %ymm1, %ymm2"); + asm volatile("vpexpandb %zmm1, %zmm2"); + asm volatile("vpexpandb 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpexpandb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpexpandw %xmm1, %xmm2"); + asm volatile("vpexpandw %ymm1, %ymm2"); + asm volatile("vpexpandw %zmm1, %zmm2"); + asm volatile("vpexpandw 0x12345678(%rax,%rcx,8),%zmm2"); + asm volatile("vpexpandw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 63 */ + + asm volatile("vpcompressb %xmm1, %xmm2"); + asm volatile("vpcompressb %ymm1, %ymm2"); + asm volatile("vpcompressb %zmm1, %zmm2"); + asm volatile("vpcompressb %zmm2,0x12345678(%rax,%rcx,8)"); + asm volatile("vpcompressb %zmm2,0x12345678(%eax,%ecx,8)"); + + asm volatile("vpcompressw %xmm1, %xmm2"); + asm volatile("vpcompressw %ymm1, %ymm2"); + asm volatile("vpcompressw %zmm1, %zmm2"); + asm volatile("vpcompressw %zmm2,0x12345678(%rax,%rcx,8)"); + asm volatile("vpcompressw %zmm2,0x12345678(%eax,%ecx,8)"); + /* AVX-512: Op code 0f 38 64 */ asm volatile("vpblendmd %zmm26,%zmm27,%zmm28"); @@ -541,6 +645,76 @@ int main(void) asm volatile("vpblendmb %zmm26,%zmm27,%zmm28"); asm volatile("vpblendmw %zmm26,%zmm27,%zmm28"); + /* AVX-512: Op code 0f 38 68 */ + + asm volatile("vp2intersectd %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectd %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectd %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectd 0x12345678(%rax,%rcx,8),%zmm2,%k3"); + asm volatile("vp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + asm volatile("vp2intersectq %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectq %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectq %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectq 0x12345678(%rax,%rcx,8),%zmm2,%k3"); + asm volatile("vp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + /* AVX-512: Op code 0f 38 70 */ + + asm volatile("vpshldvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 71 */ + + asm volatile("vpshldvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshldvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 72 */ + + asm volatile("vcvtne2ps2bf16 %xmm1, %xmm2, %xmm3"); + asm volatile("vcvtne2ps2bf16 %ymm1, %ymm2, %ymm3"); + asm volatile("vcvtne2ps2bf16 %zmm1, %zmm2, %zmm3"); + asm volatile("vcvtne2ps2bf16 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vcvtneps2bf16 %xmm1, %xmm2"); + asm volatile("vcvtneps2bf16 %ymm1, %xmm2"); + asm volatile("vcvtneps2bf16 %zmm1, %ymm2"); + asm volatile("vcvtneps2bf16 0x12345678(%rax,%rcx,8),%ymm2"); + asm volatile("vcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2"); + + asm volatile("vpshrdvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvw 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 73 */ + + asm volatile("vpshrdvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshrdvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvq 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 38 75 */ asm volatile("vpermi2b %zmm24,%zmm25,%zmm26"); @@ -613,6 +787,14 @@ int main(void) asm volatile("vpermb %zmm26,%zmm27,%zmm28"); asm volatile("vpermw %zmm26,%zmm27,%zmm28"); + /* AVX-512: Op code 0f 38 8f */ + + asm volatile("vpshufbitqmb %xmm1, %xmm2, %k3"); + asm volatile("vpshufbitqmb %ymm1, %ymm2, %k3"); + asm volatile("vpshufbitqmb %zmm1, %zmm2, %k3"); + asm volatile("vpshufbitqmb 0x12345678(%rax,%rcx,8),%zmm2,%k3"); + asm volatile("vpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + /* AVX-512: Op code 0f 38 90 */ asm volatile("vpgatherdd %xmm2,0x02(%rbp,%xmm7,2),%xmm1"); @@ -627,6 +809,40 @@ int main(void) asm volatile("vpgatherqd 0x7b(%rbp,%zmm27,8),%ymm26{%k1}"); asm volatile("vpgatherqq 0x7b(%rbp,%zmm27,8),%zmm26{%k1}"); + /* AVX-512: Op code 0f 38 9a */ + + asm volatile("vfmsub132ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub132pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fmaddps (%rax), %zmm0, %zmm4"); + asm volatile("v4fmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("v4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 9b */ + + asm volatile("vfmsub132ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub132sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fmaddss (%rax), %xmm0, %xmm4"); + asm volatile("v4fmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4"); + asm volatile("v4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 a0 */ asm volatile("vpscatterdd %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); @@ -647,6 +863,40 @@ int main(void) asm volatile("vscatterqps %ymm6,0x7b(%rbp,%zmm29,8){%k1}"); asm volatile("vscatterqpd %zmm28,0x7b(%rbp,%zmm29,8){%k1}"); + /* AVX-512: Op code 0f 38 aa */ + + asm volatile("vfmsub213ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213ps 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub213pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213pd 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fnmaddps (%rax), %zmm0, %zmm4"); + asm volatile("v4fnmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fnmaddps 0x12345678(%rax,%rcx,8),%zmm0,%zmm4"); + asm volatile("v4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 ab */ + + asm volatile("vfmsub213ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ss 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub213sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213sd 0x12345678(%rax,%rcx,8),%xmm2,%xmm3"); + asm volatile("vfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fnmaddss (%rax), %xmm0, %xmm4"); + asm volatile("v4fnmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fnmaddss 0x12345678(%rax,%rcx,8),%xmm0,%xmm4"); + asm volatile("v4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 b4 */ asm volatile("vpmadd52luq %zmm26,%zmm27,%zmm28"); @@ -685,6 +935,50 @@ int main(void) asm volatile("vrsqrt28ss %xmm28,%xmm29,%xmm30{%k7}"); asm volatile("vrsqrt28sd %xmm25,%xmm26,%xmm27{%k7}"); + /* AVX-512: Op code 0f 38 cf */ + + asm volatile("gf2p8mulb %xmm1, %xmm3"); + asm volatile("gf2p8mulb 0x12345678(%rax,%rcx,8),%xmm3"); + asm volatile("gf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3"); + + asm volatile("vgf2p8mulb %xmm1, %xmm2, %xmm3"); + asm volatile("vgf2p8mulb %ymm1, %ymm2, %ymm3"); + asm volatile("vgf2p8mulb %zmm1, %zmm2, %zmm3"); + asm volatile("vgf2p8mulb 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dc */ + + asm volatile("vaesenc %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenc %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenc %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenc 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dd */ + + asm volatile("vaesenclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 de */ + + asm volatile("vaesdec %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdec %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdec %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdec 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 df */ + + asm volatile("vaesdeclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdeclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdeclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdeclast 0x12345678(%rax,%rcx,8),%zmm2,%zmm3"); + asm volatile("vaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 3a 03 */ asm volatile("valignd $0x12,%zmm28,%zmm29,%zmm30"); @@ -804,6 +1098,13 @@ int main(void) asm volatile("vshufi32x4 $0x12,%zmm25,%zmm26,%zmm27"); asm volatile("vshufi64x2 $0x12,%zmm28,%zmm29,%zmm30"); + /* AVX-512: Op code 0f 3a 44 */ + + asm volatile("vpclmulqdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpclmulqdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpclmulqdq $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpclmulqdq $0x12,%zmm25,%zmm26,%zmm27"); + /* AVX-512: Op code 0f 3a 50 */ asm volatile("vrangeps $0x12,%zmm25,%zmm26,%zmm27"); @@ -844,6 +1145,62 @@ int main(void) asm volatile("vfpclassss $0x12,%xmm27,%k5"); asm volatile("vfpclasssd $0x12,%xmm30,%k5"); + /* AVX-512: Op code 0f 3a 70 */ + + asm volatile("vpshldw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldw $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshldw $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 71 */ + + asm volatile("vpshldd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldd $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshldd $0x12,%zmm25,%zmm26,%zmm27"); + + asm volatile("vpshldq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldq $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshldq $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 72 */ + + asm volatile("vpshrdw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdw $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshrdw $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a 73 */ + + asm volatile("vpshrdd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdd $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshrdd $0x12,%zmm25,%zmm26,%zmm27"); + + asm volatile("vpshrdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdq $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vpshrdq $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a ce */ + + asm volatile("gf2p8affineqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vgf2p8affineqb $0x12,%zmm25,%zmm26,%zmm27"); + + /* AVX-512: Op code 0f 3a cf */ + + asm volatile("gf2p8affineinvqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3"); + asm volatile("vgf2p8affineinvqb $0x12,%zmm25,%zmm26,%zmm27"); + /* AVX-512: Op code 0f 72 (Grp13) */ asm volatile("vprord $0x12,%zmm25,%zmm26"); @@ -1320,6 +1677,14 @@ int main(void) asm volatile("xsaveopt (%r8)"); asm volatile("mfence"); + /* cldemote m8 */ + + asm volatile("cldemote (%rax)"); + asm volatile("cldemote (%r8)"); + asm volatile("cldemote (0x12345678)"); + asm volatile("cldemote 0x12345678(%rax,%rcx,8)"); + asm volatile("cldemote 0x12345678(%r8,%rcx,8)"); + /* xsavec mem */ asm volatile("xsavec (%rax)"); @@ -1364,6 +1729,48 @@ int main(void) asm volatile("ptwriteq 0x12345678(%rax,%rcx,8)"); asm volatile("ptwriteq 0x12345678(%r8,%rcx,8)"); + /* tpause */ + + asm volatile("tpause %ebx"); + asm volatile("tpause %r8d"); + + /* umonitor */ + + asm volatile("umonitor %eax"); + asm volatile("umonitor %rax"); + asm volatile("umonitor %r8d"); + + /* umwait */ + + asm volatile("umwait %eax"); + asm volatile("umwait %r8d"); + + /* movdiri */ + + asm volatile("movdiri %rax,(%rbx)"); + asm volatile("movdiri %rcx,0x12345678(%rax)"); + + /* movdir64b */ + + asm volatile("movdir64b (%rax),%rbx"); + asm volatile("movdir64b 0x12345678(%rax),%rcx"); + asm volatile("movdir64b (%eax),%ebx"); + asm volatile("movdir64b 0x12345678(%eax),%ecx"); + + /* enqcmd */ + + asm volatile("enqcmd (%rax),%rbx"); + asm volatile("enqcmd 0x12345678(%rax),%rcx"); + asm volatile("enqcmd (%eax),%ebx"); + asm volatile("enqcmd 0x12345678(%eax),%ecx"); + + /* enqcmds */ + + asm volatile("enqcmds (%rax),%rbx"); + asm volatile("enqcmds 0x12345678(%rax),%rcx"); + asm volatile("enqcmds (%eax),%ebx"); + asm volatile("enqcmds 0x12345678(%eax),%ecx"); + #else /* #ifdef __x86_64__ */ /* bound r32, mem (same op code as EVEX prefix) */ @@ -1896,6 +2303,69 @@ int main(void) asm volatile("vrsqrt14ss %xmm4,%xmm5,%xmm6{%k7}"); asm volatile("vrsqrt14sd %xmm4,%xmm5,%xmm6{%k7}"); + /* AVX-512: Op code 0f 38 50 */ + + asm volatile("vpdpbusd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 51 */ + + asm volatile("vpdpbusds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpbusds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpbusds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpbusds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 52 */ + + asm volatile("vdpbf16ps %xmm1, %xmm2, %xmm3"); + asm volatile("vdpbf16ps %ymm1, %ymm2, %ymm3"); + asm volatile("vdpbf16ps %zmm1, %zmm2, %zmm3"); + asm volatile("vdpbf16ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpdpwssd %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssd %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssd %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssd (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssd 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 53 */ + + asm volatile("vpdpwssds %xmm1, %xmm2, %xmm3"); + asm volatile("vpdpwssds %ymm1, %ymm2, %ymm3"); + asm volatile("vpdpwssds %zmm1, %zmm2, %zmm3"); + asm volatile("vpdpwssds 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vp4dpwssds (%eax), %zmm0, %zmm4"); + asm volatile("vp4dpwssds 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 54 */ + + asm volatile("vpopcntb %xmm1, %xmm2"); + asm volatile("vpopcntb %ymm1, %ymm2"); + asm volatile("vpopcntb %zmm1, %zmm2"); + asm volatile("vpopcntb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntw %xmm1, %xmm2"); + asm volatile("vpopcntw %ymm1, %ymm2"); + asm volatile("vpopcntw %zmm1, %zmm2"); + asm volatile("vpopcntw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 55 */ + + asm volatile("vpopcntd %xmm1, %xmm2"); + asm volatile("vpopcntd %ymm1, %ymm2"); + asm volatile("vpopcntd %zmm1, %zmm2"); + asm volatile("vpopcntd 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpopcntq %xmm1, %xmm2"); + asm volatile("vpopcntq %ymm1, %ymm2"); + asm volatile("vpopcntq %zmm1, %zmm2"); + asm volatile("vpopcntq 0x12345678(%eax,%ecx,8),%zmm2"); + /* AVX-512: Op code 0f 38 59 */ asm volatile("vpbroadcastq %xmm4,%xmm6"); @@ -1912,6 +2382,30 @@ int main(void) asm volatile("vbroadcasti32x8 (%ecx),%zmm6"); asm volatile("vbroadcasti64x4 (%ecx),%zmm6"); + /* AVX-512: Op code 0f 38 62 */ + + asm volatile("vpexpandb %xmm1, %xmm2"); + asm volatile("vpexpandb %ymm1, %ymm2"); + asm volatile("vpexpandb %zmm1, %zmm2"); + asm volatile("vpexpandb 0x12345678(%eax,%ecx,8),%zmm2"); + + asm volatile("vpexpandw %xmm1, %xmm2"); + asm volatile("vpexpandw %ymm1, %ymm2"); + asm volatile("vpexpandw %zmm1, %zmm2"); + asm volatile("vpexpandw 0x12345678(%eax,%ecx,8),%zmm2"); + + /* AVX-512: Op code 0f 38 63 */ + + asm volatile("vpcompressb %xmm1, %xmm2"); + asm volatile("vpcompressb %ymm1, %ymm2"); + asm volatile("vpcompressb %zmm1, %zmm2"); + asm volatile("vpcompressb %zmm2,0x12345678(%eax,%ecx,8)"); + + asm volatile("vpcompressw %xmm1, %xmm2"); + asm volatile("vpcompressw %ymm1, %ymm2"); + asm volatile("vpcompressw %zmm1, %zmm2"); + asm volatile("vpcompressw %zmm2,0x12345678(%eax,%ecx,8)"); + /* AVX-512: Op code 0f 38 64 */ asm volatile("vpblendmd %zmm4,%zmm5,%zmm6"); @@ -1927,6 +2421,66 @@ int main(void) asm volatile("vpblendmb %zmm4,%zmm5,%zmm6"); asm volatile("vpblendmw %zmm4,%zmm5,%zmm6"); + /* AVX-512: Op code 0f 38 68 */ + + asm volatile("vp2intersectd %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectd %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectd %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectd 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + asm volatile("vp2intersectq %xmm1, %xmm2, %k3"); + asm volatile("vp2intersectq %ymm1, %ymm2, %k3"); + asm volatile("vp2intersectq %zmm1, %zmm2, %k3"); + asm volatile("vp2intersectq 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + + /* AVX-512: Op code 0f 38 70 */ + + asm volatile("vpshldvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 71 */ + + asm volatile("vpshldvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshldvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshldvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshldvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshldvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 72 */ + + asm volatile("vcvtne2ps2bf16 %xmm1, %xmm2, %xmm3"); + asm volatile("vcvtne2ps2bf16 %ymm1, %ymm2, %ymm3"); + asm volatile("vcvtne2ps2bf16 %zmm1, %zmm2, %zmm3"); + asm volatile("vcvtne2ps2bf16 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vcvtneps2bf16 %xmm1, %xmm2"); + asm volatile("vcvtneps2bf16 %ymm1, %xmm2"); + asm volatile("vcvtneps2bf16 %zmm1, %ymm2"); + asm volatile("vcvtneps2bf16 0x12345678(%eax,%ecx,8),%ymm2"); + + asm volatile("vpshrdvw %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvw %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvw %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvw 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 73 */ + + asm volatile("vpshrdvd %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvd %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvd %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vpshrdvq %xmm1, %xmm2, %xmm3"); + asm volatile("vpshrdvq %ymm1, %ymm2, %ymm3"); + asm volatile("vpshrdvq %zmm1, %zmm2, %zmm3"); + asm volatile("vpshrdvq 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 38 75 */ asm volatile("vpermi2b %zmm4,%zmm5,%zmm6"); @@ -1998,6 +2552,13 @@ int main(void) asm volatile("vpermb %zmm4,%zmm5,%zmm6"); asm volatile("vpermw %zmm4,%zmm5,%zmm6"); + /* AVX-512: Op code 0f 38 8f */ + + asm volatile("vpshufbitqmb %xmm1, %xmm2, %k3"); + asm volatile("vpshufbitqmb %ymm1, %ymm2, %k3"); + asm volatile("vpshufbitqmb %zmm1, %zmm2, %k3"); + asm volatile("vpshufbitqmb 0x12345678(%eax,%ecx,8),%zmm2,%k3"); + /* AVX-512: Op code 0f 38 90 */ asm volatile("vpgatherdd %xmm2,0x02(%ebp,%xmm7,2),%xmm1"); @@ -2012,6 +2573,32 @@ int main(void) asm volatile("vpgatherqd 0x7b(%ebp,%zmm7,8),%ymm6{%k1}"); asm volatile("vpgatherqq 0x7b(%ebp,%zmm7,8),%zmm6{%k1}"); + /* AVX-512: Op code 0f 38 9a */ + + asm volatile("vfmsub132ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub132pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub132pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub132pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 9b */ + + asm volatile("vfmsub132ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub132sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub132sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 a0 */ asm volatile("vpscatterdd %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); @@ -2032,6 +2619,32 @@ int main(void) asm volatile("vscatterqps %ymm6,0x7b(%ebp,%zmm7,8){%k1}"); asm volatile("vscatterqpd %zmm6,0x7b(%ebp,%zmm7,8){%k1}"); + /* AVX-512: Op code 0f 38 aa */ + + asm volatile("vfmsub213ps %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ps %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213ps %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213ps 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("vfmsub213pd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213pd %ymm1, %ymm2, %ymm3"); + asm volatile("vfmsub213pd %zmm1, %zmm2, %zmm3"); + asm volatile("vfmsub213pd 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + asm volatile("v4fnmaddps (%eax), %zmm0, %zmm4"); + asm volatile("v4fnmaddps 0x12345678(%eax,%ecx,8),%zmm0,%zmm4"); + + /* AVX-512: Op code 0f 38 ab */ + + asm volatile("vfmsub213ss %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213ss 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("vfmsub213sd %xmm1, %xmm2, %xmm3"); + asm volatile("vfmsub213sd 0x12345678(%eax,%ecx,8),%xmm2,%xmm3"); + + asm volatile("v4fnmaddss (%eax), %xmm0, %xmm4"); + asm volatile("v4fnmaddss 0x12345678(%eax,%ecx,8),%xmm0,%xmm4"); + /* AVX-512: Op code 0f 38 b4 */ asm volatile("vpmadd52luq %zmm4,%zmm5,%zmm6"); @@ -2070,6 +2683,44 @@ int main(void) asm volatile("vrsqrt28ss %xmm5,%xmm6,%xmm7{%k7}"); asm volatile("vrsqrt28sd %xmm5,%xmm6,%xmm7{%k7}"); + /* AVX-512: Op code 0f 38 cf */ + + asm volatile("gf2p8mulb %xmm1, %xmm3"); + asm volatile("gf2p8mulb 0x12345678(%eax,%ecx,8),%xmm3"); + + asm volatile("vgf2p8mulb %xmm1, %xmm2, %xmm3"); + asm volatile("vgf2p8mulb %ymm1, %ymm2, %ymm3"); + asm volatile("vgf2p8mulb %zmm1, %zmm2, %zmm3"); + asm volatile("vgf2p8mulb 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dc */ + + asm volatile("vaesenc %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenc %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenc %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenc 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 dd */ + + asm volatile("vaesenclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesenclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesenclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesenclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 de */ + + asm volatile("vaesdec %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdec %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdec %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdec 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 38 df */ + + asm volatile("vaesdeclast %xmm1, %xmm2, %xmm3"); + asm volatile("vaesdeclast %ymm1, %ymm2, %ymm3"); + asm volatile("vaesdeclast %zmm1, %zmm2, %zmm3"); + asm volatile("vaesdeclast 0x12345678(%eax,%ecx,8),%zmm2,%zmm3"); + /* AVX-512: Op code 0f 3a 03 */ asm volatile("valignd $0x12,%zmm5,%zmm6,%zmm7"); @@ -2189,6 +2840,12 @@ int main(void) asm volatile("vshufi32x4 $0x12,%zmm5,%zmm6,%zmm7"); asm volatile("vshufi64x2 $0x12,%zmm5,%zmm6,%zmm7"); + /* AVX-512: Op code 0f 3a 44 */ + + asm volatile("vpclmulqdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpclmulqdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpclmulqdq $0x12,%zmm1,%zmm2,%zmm3"); + /* AVX-512: Op code 0f 3a 50 */ asm volatile("vrangeps $0x12,%zmm5,%zmm6,%zmm7"); @@ -2229,6 +2886,54 @@ int main(void) asm volatile("vfpclassss $0x12,%xmm7,%k5"); asm volatile("vfpclasssd $0x12,%xmm7,%k5"); + /* AVX-512: Op code 0f 3a 70 */ + + asm volatile("vpshldw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldw $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a 71 */ + + asm volatile("vpshldd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldd $0x12,%zmm1,%zmm2,%zmm3"); + + asm volatile("vpshldq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshldq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshldq $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a 72 */ + + asm volatile("vpshrdw $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdw $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdw $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a 73 */ + + asm volatile("vpshrdd $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdd $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdd $0x12,%zmm1,%zmm2,%zmm3"); + + asm volatile("vpshrdq $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vpshrdq $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vpshrdq $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a ce */ + + asm volatile("gf2p8affineqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineqb $0x12,%zmm1,%zmm2,%zmm3"); + + /* AVX-512: Op code 0f 3a cf */ + + asm volatile("gf2p8affineinvqb $0x12,%xmm1,%xmm3"); + + asm volatile("vgf2p8affineinvqb $0x12,%xmm1,%xmm2,%xmm3"); + asm volatile("vgf2p8affineinvqb $0x12,%ymm1,%ymm2,%ymm3"); + asm volatile("vgf2p8affineinvqb $0x12,%zmm1,%zmm2,%zmm3"); + /* AVX-512: Op code 0f 72 (Grp13) */ asm volatile("vprord $0x12,%zmm5,%zmm6"); @@ -2656,6 +3361,12 @@ int main(void) asm volatile("xsaveopt (%eax)"); asm volatile("mfence"); + /* cldemote m8 */ + + asm volatile("cldemote (%eax)"); + asm volatile("cldemote (0x12345678)"); + asm volatile("cldemote 0x12345678(%eax,%ecx,8)"); + /* xsavec mem */ asm volatile("xsavec (%eax)"); @@ -2684,8 +3395,61 @@ int main(void) asm volatile("ptwritel (0x12345678)"); asm volatile("ptwritel 0x12345678(%eax,%ecx,8)"); + /* tpause */ + + asm volatile("tpause %ebx"); + + /* umonitor */ + + asm volatile("umonitor %ax"); + asm volatile("umonitor %eax"); + + /* umwait */ + + asm volatile("umwait %eax"); + + /* movdiri */ + + asm volatile("movdiri %eax,(%ebx)"); + asm volatile("movdiri %ecx,0x12345678(%eax)"); + + /* movdir64b */ + + asm volatile("movdir64b (%eax),%ebx"); + asm volatile("movdir64b 0x12345678(%eax),%ecx"); + asm volatile("movdir64b (%si),%bx"); + asm volatile("movdir64b 0x1234(%si),%cx"); + + /* enqcmd */ + + asm volatile("enqcmd (%eax),%ebx"); + asm volatile("enqcmd 0x12345678(%eax),%ecx"); + asm volatile("enqcmd (%si),%bx"); + asm volatile("enqcmd 0x1234(%si),%cx"); + + /* enqcmds */ + + asm volatile("enqcmds (%eax),%ebx"); + asm volatile("enqcmds 0x12345678(%eax),%ecx"); + asm volatile("enqcmds (%si),%bx"); + asm volatile("enqcmds 0x1234(%si),%cx"); + #endif /* #ifndef __x86_64__ */ + /* SGX */ + + asm volatile("encls"); + asm volatile("enclu"); + asm volatile("enclv"); + + /* pconfig */ + + asm volatile("pconfig"); + + /* wbnoinvd */ + + asm volatile("wbnoinvd"); + /* Following line is a marker for the awk script - do not change */ asm volatile("rdtsc"); /* Stop here */ diff --git a/tools/perf/arch/x86/tests/insn-x86.c b/tools/perf/arch/x86/tests/insn-x86.c index c3e5f4ab0d3e..745f29adb14b 100644 --- a/tools/perf/arch/x86/tests/insn-x86.c +++ b/tools/perf/arch/x86/tests/insn-x86.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> +#include "../../../../arch/x86/include/asm/insn.h" +#include <string.h> #include "debug.h" #include "tests/tests.h" #include "arch-tests.h" -#include "intel-pt-decoder/insn.h" #include "intel-pt-decoder/intel-pt-insn-decoder.h" struct test_data { diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 94aa0b673b7f..3ec562a2aaba 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -1,12 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include "tests/tests.h" -#include "perf.h" #include "cloexec.h" #include "debug.h" #include "evlist.h" #include "evsel.h" #include "arch-tests.h" -#include "util.h" +#include <internal/lib.h> // page_size #include <signal.h> #include <sys/mman.h> @@ -40,8 +39,8 @@ static pid_t spawn(void) */ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subtest __maybe_unused) { - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel = NULL; struct perf_event_attr pe; int i, fd[2], flag, ret; size_t mmap_len; @@ -51,7 +50,7 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt flag = perf_event_open_cloexec_flag(); - evlist = perf_evlist__new(); + evlist = evlist__new(); if (!evlist) { pr_debug("perf_evlist__new failed\n"); return TEST_FAIL; @@ -64,9 +63,9 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt goto out; } - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); if (!evsel) { - pr_debug("perf_evlist__first failed\n"); + pr_debug("evlist__first failed\n"); goto out; } @@ -124,6 +123,6 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt kill(pid, SIGKILL); wait(NULL); out: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index 7a7721604b86..909ead08a6f6 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -1,17 +1,24 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> #include <inttypes.h> +#include <limits.h> +#include <stdbool.h> #include <stdio.h> #include <unistd.h> #include <linux/types.h> #include <sys/prctl.h> +#include <perf/cpumap.h> +#include <perf/evlist.h> +#include <perf/mmap.h> +#include "debug.h" #include "parse-events.h" #include "evlist.h" #include "evsel.h" #include "thread_map.h" -#include "cpumap.h" +#include "record.h" #include "tsc.h" +#include "util/mmap.h" #include "tests/tests.h" #include "arch-tests.h" @@ -49,10 +56,10 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe }, .sample_time = true, }; - struct thread_map *threads = NULL; - struct cpu_map *cpus = NULL; - struct perf_evlist *evlist = NULL; - struct perf_evsel *evsel = NULL; + struct perf_thread_map *threads = NULL; + struct perf_cpu_map *cpus = NULL; + struct evlist *evlist = NULL; + struct evsel *evsel = NULL; int err = -1, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; @@ -60,34 +67,34 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe union perf_event *event; u64 test_tsc, comm1_tsc, comm2_tsc; u64 test_time, comm1_time = 0, comm2_time = 0; - struct perf_mmap *md; + struct mmap *md; threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); - cpus = cpu_map__new(NULL); + cpus = perf_cpu_map__new(NULL); CHECK_NOT_NULL__(cpus); - evlist = perf_evlist__new(); + evlist = evlist__new(); CHECK_NOT_NULL__(evlist); - perf_evlist__set_maps(evlist, cpus, threads); + perf_evlist__set_maps(&evlist->core, cpus, threads); CHECK__(parse_events(evlist, "cycles:u", NULL)); perf_evlist__config(evlist, &opts, NULL); - evsel = perf_evlist__first(evlist); + evsel = evlist__first(evlist); - evsel->attr.comm = 1; - evsel->attr.disabled = 1; - evsel->attr.enable_on_exec = 0; + evsel->core.attr.comm = 1; + evsel->core.attr.disabled = 1; + evsel->core.attr.enable_on_exec = 0; - CHECK__(perf_evlist__open(evlist)); + CHECK__(evlist__open(evlist)); - CHECK__(perf_evlist__mmap(evlist, UINT_MAX)); + CHECK__(evlist__mmap(evlist, UINT_MAX)); - pc = evlist->mmap[0].base; + pc = evlist->mmap[0].core.base; ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { @@ -97,7 +104,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe goto out_err; } - perf_evlist__enable(evlist); + evlist__enable(evlist); comm1 = "Test COMM 1"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm1, 0, 0, 0)); @@ -107,14 +114,14 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe comm2 = "Test COMM 2"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm2, 0, 0, 0)); - perf_evlist__disable(evlist); + evlist__disable(evlist); - for (i = 0; i < evlist->nr_mmaps; i++) { + for (i = 0; i < evlist->core.nr_mmaps; i++) { md = &evlist->mmap[i]; - if (perf_mmap__read_init(md) < 0) + if (perf_mmap__read_init(&md->core) < 0) continue; - while ((event = perf_mmap__read_event(md)) != NULL) { + while ((event = perf_mmap__read_event(&md->core)) != NULL) { struct perf_sample sample; if (event->header.type != PERF_RECORD_COMM || @@ -133,9 +140,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe comm2_time = sample.time; } next_event: - perf_mmap__consume(md); + perf_mmap__consume(&md->core); } - perf_mmap__read_done(md); + perf_mmap__read_done(&md->core); } if (!comm1_time || !comm2_time) @@ -163,6 +170,6 @@ next_event: err = 0; out_err: - perf_evlist__delete(evlist); + evlist__delete(evlist); return err; } diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c index 7a11f02d6c6c..1ea916656a2d 100644 --- a/tools/perf/arch/x86/tests/rdpmc.c +++ b/tools/perf/arch/x86/tests/rdpmc.c @@ -6,12 +6,14 @@ #include <sys/mman.h> #include <sys/types.h> #include <sys/wait.h> +#include <linux/string.h> #include <linux/types.h> -#include "perf.h" +#include "perf-sys.h" #include "debug.h" #include "tests/tests.h" #include "cloexec.h" -#include "util.h" +#include "event.h" +#include <internal/lib.h> // page_size #include "arch-tests.h" static u64 rdpmc(unsigned int counter) diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S index bbe5a0d16e51..80f14f52e3f6 100644 --- a/tools/perf/arch/x86/tests/regs_load.S +++ b/tools/perf/arch/x86/tests/regs_load.S @@ -28,7 +28,7 @@ .text #ifdef HAVE_ARCH_X86_64_SUPPORT -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) movq %rax, AX(%rdi) movq %rbx, BX(%rdi) movq %rcx, CX(%rdi) @@ -60,9 +60,9 @@ ENTRY(perf_regs_load) movq %r14, R14(%rdi) movq %r15, R15(%rdi) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) #else -ENTRY(perf_regs_load) +SYM_FUNC_START(perf_regs_load) push %edi movl 8(%esp), %edi movl %eax, AX(%edi) @@ -88,7 +88,7 @@ ENTRY(perf_regs_load) movl $0, FS(%edi) movl $0, GS(%edi) ret -ENDPROC(perf_regs_load) +SYM_FUNC_END(perf_regs_load) #endif /* diff --git a/tools/perf/arch/x86/util/archinsn.c b/tools/perf/arch/x86/util/archinsn.c index 4237bb2e7fa2..3e6791531ca5 100644 --- a/tools/perf/arch/x86/util/archinsn.c +++ b/tools/perf/arch/x86/util/archinsn.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include "perf.h" +#include "../../../../arch/x86/include/asm/insn.h" #include "archinsn.h" -#include "util/intel-pt-decoder/insn.h" +#include "event.h" #include "machine.h" #include "thread.h" #include "symbol.h" diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c index d711268af330..7abc9fd4cbec 100644 --- a/tools/perf/arch/x86/util/auxtrace.c +++ b/tools/perf/arch/x86/util/auxtrace.c @@ -16,22 +16,26 @@ #include "../../util/evlist.h" static -struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init_intel(struct evlist *evlist, int *err) { struct perf_pmu *intel_pt_pmu; struct perf_pmu *intel_bts_pmu; - struct perf_evsel *evsel; + struct evsel *evsel; bool found_pt = false; bool found_bts = false; intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME); + if (intel_pt_pmu) + intel_pt_pmu->auxtrace = true; intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME); + if (intel_bts_pmu) + intel_bts_pmu->auxtrace = true; evlist__for_each_entry(evlist, evsel) { - if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type) + if (intel_pt_pmu && evsel->core.attr.type == intel_pt_pmu->type) found_pt = true; - if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type) + if (intel_bts_pmu && evsel->core.attr.type == intel_bts_pmu->type) found_bts = true; } @@ -50,7 +54,7 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist, return NULL; } -struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, +struct auxtrace_record *auxtrace_record__init(struct evlist *evlist, int *err) { char buffer[64]; diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c index a3a0b6884779..ac45015cc6ba 100644 --- a/tools/perf/arch/x86/util/event.c +++ b/tools/perf/arch/x86/util/event.c @@ -3,6 +3,8 @@ #include <linux/string.h> #include <linux/zalloc.h> +#include "../../util/event.h" +#include "../../util/synthetic-events.h" #include "../../util/machine.h" #include "../../util/tool.h" #include "../../util/map.h" @@ -16,8 +18,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, { int rc = 0; struct map *pos; - struct map_groups *kmaps = &machine->kmaps; - struct maps *maps = &kmaps->maps; + struct maps *kmaps = &machine->kmaps; union perf_event *event = zalloc(sizeof(event->mmap) + machine->id_hdr_size); @@ -27,7 +28,7 @@ int perf_event__synthesize_extra_kmaps(struct perf_tool *tool, return -1; } - for (pos = maps__first(maps); pos; pos = map__next(pos)) { + maps__for_each_entry(kmaps, pos) { struct kmap *kmap; size_t size; diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c index af9a9f2600be..aa6deb463bf3 100644 --- a/tools/perf/arch/x86/util/header.c +++ b/tools/perf/arch/x86/util/header.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 #include <sys/types.h> +#include <errno.h> #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <regex.h> +#include "../../util/debug.h" #include "../../util/header.h" static inline void @@ -57,7 +59,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt) buffer[nb-1] = '\0'; return 0; } - return -1; + return ENOBUFS; } int diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index ec5c1bb84095..27d9e214d068 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -12,14 +12,18 @@ #include <linux/zalloc.h> #include "../../util/cpumap.h" +#include "../../util/event.h" #include "../../util/evsel.h" #include "../../util/evlist.h" +#include "../../util/mmap.h" #include "../../util/session.h" #include "../../util/pmu.h" #include "../../util/debug.h" +#include "../../util/record.h" #include "../../util/tsc.h" #include "../../util/auxtrace.h" #include "../../util/intel-bts.h" +#include <internal/lib.h> // page_size #define KiB(x) ((x) * 1024) #define MiB(x) ((x) * 1024 * 1024) @@ -35,7 +39,7 @@ struct intel_bts_snapshot_ref { struct intel_bts_recording { struct auxtrace_record itr; struct perf_pmu *intel_bts_pmu; - struct perf_evlist *evlist; + struct evlist *evlist; bool snapshot_mode; size_t snapshot_size; int snapshot_ref_cnt; @@ -50,14 +54,14 @@ struct branch { static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused, - struct perf_evlist *evlist __maybe_unused) + struct evlist *evlist __maybe_unused) { return INTEL_BTS_AUXTRACE_PRIV_SIZE; } static int intel_bts_info_fill(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size) { struct intel_bts_recording *btsr = @@ -71,10 +75,10 @@ static int intel_bts_info_fill(struct auxtrace_record *itr, if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE) return -EINVAL; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; - pc = session->evlist->mmap[0].base; + pc = session->evlist->mmap[0].core.base; if (pc) { err = perf_read_tsc_conversion(pc, &tc); if (err) { @@ -99,27 +103,32 @@ static int intel_bts_info_fill(struct auxtrace_record *itr, } static int intel_bts_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); struct perf_pmu *intel_bts_pmu = btsr->intel_bts_pmu; - struct perf_evsel *evsel, *intel_bts_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; - bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; + struct evsel *evsel, *intel_bts_evsel = NULL; + const struct perf_cpu_map *cpus = evlist->core.cpus; + bool privileged = perf_event_paranoid_check(-1); + + if (opts->auxtrace_sample_mode) { + pr_err("Intel BTS does not support AUX area sampling\n"); + return -EINVAL; + } btsr->evlist = evlist; btsr->snapshot_mode = opts->auxtrace_snapshot_mode; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_bts_pmu->type) { + if (evsel->core.attr.type == intel_bts_pmu->type) { if (intel_bts_evsel) { pr_err("There may be only one " INTEL_BTS_PMU_NAME " event\n"); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; intel_bts_evsel = evsel; opts->full_auxtrace = true; } @@ -133,7 +142,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, if (!opts->full_auxtrace) return 0; - if (opts->full_auxtrace && !cpu_map__empty(cpus)) { + if (opts->full_auxtrace && !perf_cpu_map__empty(cpus)) { pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n"); return -EINVAL; } @@ -214,25 +223,25 @@ static int intel_bts_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) perf_evsel__set_sample_bit(intel_bts_evsel, CPU); } /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; int err; err = parse_events(evlist, "dummy:u", NULL); if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; } return 0; @@ -313,11 +322,11 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -326,11 +335,11 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -408,10 +417,10 @@ static int intel_bts_read_finish(struct auxtrace_record *itr, int idx) { struct intel_bts_recording *btsr = container_of(itr, struct intel_bts_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(btsr->evlist, evsel) { - if (evsel->attr.type == btsr->intel_bts_pmu->type) + if (evsel->core.attr.type == btsr->intel_bts_pmu->type) return perf_evlist__enable_event_idx(btsr->evlist, evsel, idx); } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 609088c01e3a..20df442fdf36 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -13,18 +13,22 @@ #include <linux/zalloc.h> #include <cpuid.h> -#include "../../perf.h" #include "../../util/session.h" #include "../../util/event.h" #include "../../util/evlist.h" #include "../../util/evsel.h" +#include "../../util/evsel_config.h" #include "../../util/cpumap.h" +#include "../../util/mmap.h" #include <subcmd/parse-options.h> #include "../../util/parse-events.h" #include "../../util/pmu.h" #include "../../util/debug.h" #include "../../util/auxtrace.h" +#include "../../util/record.h" +#include "../../util/target.h" #include "../../util/tsc.h" +#include <internal/lib.h> // page_size #include "../../util/intel-pt.h" #define KiB(x) ((x) * 1024) @@ -44,7 +48,7 @@ struct intel_pt_recording { struct auxtrace_record itr; struct perf_pmu *intel_pt_pmu; int have_sched_switch; - struct perf_evlist *evlist; + struct evlist *evlist; bool snapshot_mode; bool snapshot_init_done; size_t snapshot_size; @@ -110,9 +114,9 @@ static u64 intel_pt_masked_bits(u64 mask, u64 bits) } static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, - struct perf_evlist *evlist, u64 *res) + struct evlist *evlist, u64 *res) { - struct perf_evsel *evsel; + struct evsel *evsel; u64 mask; *res = 0; @@ -122,8 +126,8 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, return -EINVAL; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) { - *res = intel_pt_masked_bits(mask, evsel->attr.config); + if (evsel->core.attr.type == intel_pt_pmu->type) { + *res = intel_pt_masked_bits(mask, evsel->core.attr.config); return 0; } } @@ -132,7 +136,7 @@ static int intel_pt_read_config(struct perf_pmu *intel_pt_pmu, const char *str, } static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu, - struct perf_evlist *evlist) + struct evlist *evlist) { u64 val; int err, topa_multiple_entries; @@ -268,13 +272,13 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) return attr; } -static const char *intel_pt_find_filter(struct perf_evlist *evlist, +static const char *intel_pt_find_filter(struct evlist *evlist, struct perf_pmu *intel_pt_pmu) { - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) + if (evsel->core.attr.type == intel_pt_pmu->type) return evsel->filter; } @@ -289,7 +293,7 @@ static size_t intel_pt_filter_bytes(const char *filter) } static size_t -intel_pt_info_priv_size(struct auxtrace_record *itr, struct perf_evlist *evlist) +intel_pt_info_priv_size(struct auxtrace_record *itr, struct evlist *evlist) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); @@ -312,7 +316,7 @@ static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d) static int intel_pt_info_fill(struct auxtrace_record *itr, struct perf_session *session, - struct auxtrace_info_event *auxtrace_info, + struct perf_record_auxtrace_info *auxtrace_info, size_t priv_size) { struct intel_pt_recording *ptr = @@ -326,7 +330,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, unsigned long max_non_turbo_ratio; size_t filter_str_len; const char *filter; - u64 *info; + __u64 *info; int err; if (priv_size != ptr->priv_size) @@ -349,10 +353,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu); filter_str_len = filter ? strlen(filter) : 0; - if (!session->evlist->nr_mmaps) + if (!session->evlist->core.nr_mmaps) return -EINVAL; - pc = session->evlist->mmap[0].base; + pc = session->evlist->mmap[0].core.base; if (pc) { err = perf_read_tsc_conversion(pc, &tc); if (err) { @@ -365,7 +369,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, ui__warning("Intel Processor Trace: TSC not available\n"); } - per_cpu_mmaps = !cpu_map__empty(session->evlist->cpus); + per_cpu_mmaps = !perf_cpu_map__empty(session->evlist->core.cpus); auxtrace_info->type = PERF_AUXTRACE_INTEL_PT; auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type; @@ -398,10 +402,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr, return 0; } -static int intel_pt_track_switches(struct perf_evlist *evlist) +static int intel_pt_track_switches(struct evlist *evlist) { const char *sched_switch = "sched:sched_switch"; - struct perf_evsel *evsel; + struct evsel *evsel; int err; if (!perf_evlist__can_select_event(evlist, sched_switch)) @@ -414,12 +418,12 @@ static int intel_pt_track_switches(struct perf_evlist *evlist) return err; } - evsel = perf_evlist__last(evlist); + evsel = evlist__last(evlist); perf_evsel__set_sample_bit(evsel, CPU); perf_evsel__set_sample_bit(evsel, TIME); - evsel->system_wide = true; + evsel->core.system_wide = true; evsel->no_aux_samples = true; evsel->immediate = true; @@ -513,7 +517,7 @@ out_err: } static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, - struct perf_evsel *evsel) + struct evsel *evsel) { int err; char c; @@ -526,39 +530,96 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu, * sets pt=0, which avoids senseless kernel errors. */ if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 && - !(evsel->attr.config & 1)) { + !(evsel->core.attr.config & 1)) { pr_warning("pt=0 doesn't make sense, forcing pt=1\n"); - evsel->attr.config |= 1; + evsel->core.attr.config |= 1; } err = intel_pt_val_config_term(intel_pt_pmu, "caps/cycle_thresholds", "cyc_thresh", "caps/psb_cyc", - evsel->attr.config); + evsel->core.attr.config); if (err) return err; err = intel_pt_val_config_term(intel_pt_pmu, "caps/mtc_periods", "mtc_period", "caps/mtc", - evsel->attr.config); + evsel->core.attr.config); if (err) return err; return intel_pt_val_config_term(intel_pt_pmu, "caps/psb_periods", "psb_period", "caps/psb_cyc", - evsel->attr.config); + evsel->core.attr.config); +} + +static void intel_pt_config_sample_mode(struct perf_pmu *intel_pt_pmu, + struct evsel *evsel) +{ + struct perf_evsel_config_term *term; + u64 user_bits = 0, bits; + + term = perf_evsel__get_config_term(evsel, CFG_CHG); + if (term) + user_bits = term->val.cfg_chg; + + bits = perf_pmu__format_bits(&intel_pt_pmu->format, "psb_period"); + + /* Did user change psb_period */ + if (bits & user_bits) + return; + + /* Set psb_period to 0 */ + evsel->core.attr.config &= ~bits; +} + +static void intel_pt_min_max_sample_sz(struct evlist *evlist, + size_t *min_sz, size_t *max_sz) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + size_t sz = evsel->core.attr.aux_sample_size; + + if (!sz) + continue; + if (min_sz && (sz < *min_sz || !*min_sz)) + *min_sz = sz; + if (max_sz && sz > *max_sz) + *max_sz = sz; + } +} + +/* + * Currently, there is not enough information to disambiguate different PEBS + * events, so only allow one. + */ +static bool intel_pt_too_many_aux_output(struct evlist *evlist) +{ + struct evsel *evsel; + int aux_output_cnt = 0; + + evlist__for_each_entry(evlist, evsel) + aux_output_cnt += !!evsel->core.attr.aux_output; + + if (aux_output_cnt > 1) { + pr_err(INTEL_PT_PMU_NAME " supports at most one event with aux-output\n"); + return true; + } + + return false; } static int intel_pt_recording_options(struct auxtrace_record *itr, - struct perf_evlist *evlist, + struct evlist *evlist, struct record_opts *opts) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; bool have_timing_info, need_immediate = false; - struct perf_evsel *evsel, *intel_pt_evsel = NULL; - const struct cpu_map *cpus = evlist->cpus; - bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; + struct evsel *evsel, *intel_pt_evsel = NULL; + const struct perf_cpu_map *cpus = evlist->core.cpus; + bool privileged = perf_event_paranoid_check(-1); u64 tsc_bit; int err; @@ -566,13 +627,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, ptr->snapshot_mode = opts->auxtrace_snapshot_mode; evlist__for_each_entry(evlist, evsel) { - if (evsel->attr.type == intel_pt_pmu->type) { + if (evsel->core.attr.type == intel_pt_pmu->type) { if (intel_pt_evsel) { pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n"); return -EINVAL; } - evsel->attr.freq = 0; - evsel->attr.sample_period = 1; + evsel->core.attr.freq = 0; + evsel->core.attr.sample_period = 1; intel_pt_evsel = evsel; opts->full_auxtrace = true; } @@ -583,14 +644,25 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, return -EINVAL; } + if (opts->auxtrace_snapshot_mode && opts->auxtrace_sample_mode) { + pr_err("Snapshot mode (" INTEL_PT_PMU_NAME " PMU) and sample trace cannot be used together\n"); + return -EINVAL; + } + if (opts->use_clockid) { pr_err("Cannot use clockid (-k option) with " INTEL_PT_PMU_NAME "\n"); return -EINVAL; } + if (intel_pt_too_many_aux_output(evlist)) + return -EINVAL; + if (!opts->full_auxtrace) return 0; + if (opts->auxtrace_sample_mode) + intel_pt_config_sample_mode(intel_pt_pmu, intel_pt_evsel); + err = intel_pt_validate_config(intel_pt_pmu, intel_pt_evsel); if (err) return err; @@ -640,6 +712,34 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, opts->auxtrace_snapshot_size, psb_period); } + /* Set default sizes for sample mode */ + if (opts->auxtrace_sample_mode) { + size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist); + size_t min_sz = 0, max_sz = 0; + + intel_pt_min_max_sample_sz(evlist, &min_sz, &max_sz); + if (!opts->auxtrace_mmap_pages && !privileged && + opts->mmap_pages == UINT_MAX) + opts->mmap_pages = KiB(256) / page_size; + if (!opts->auxtrace_mmap_pages) { + size_t sz = round_up(max_sz, page_size) / page_size; + + opts->auxtrace_mmap_pages = roundup_pow_of_two(sz); + } + if (max_sz > opts->auxtrace_mmap_pages * (size_t)page_size) { + pr_err("Sample size %zu must not be greater than AUX area tracing mmap size %zu\n", + max_sz, + opts->auxtrace_mmap_pages * (size_t)page_size); + return -EINVAL; + } + pr_debug2("Intel PT min. sample size: %zu max. sample size: %zu\n", + min_sz, max_sz); + if (psb_period && + min_sz <= psb_period + INTEL_PT_PSB_PERIOD_NEAR) + ui__warning("Intel PT sample size (%zu) may be too small for PSB period (%zu)\n", + min_sz, psb_period); + } + /* Set default sizes for full trace mode */ if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) { if (privileged) { @@ -656,7 +756,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size; size_t min_sz; - if (opts->auxtrace_snapshot_mode) + if (opts->auxtrace_snapshot_mode || opts->auxtrace_sample_mode) min_sz = KiB(4); else min_sz = KiB(8); @@ -670,7 +770,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit); - if (opts->full_auxtrace && (intel_pt_evsel->attr.config & tsc_bit)) + if (opts->full_auxtrace && (intel_pt_evsel->core.attr.config & tsc_bit)) have_timing_info = true; else have_timing_info = false; @@ -679,25 +779,25 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Per-cpu recording needs sched_switch events to distinguish different * threads. */ - if (have_timing_info && !cpu_map__empty(cpus)) { + if (have_timing_info && !perf_cpu_map__empty(cpus)) { if (perf_can_record_switch_events()) { bool cpu_wide = !target__none(&opts->target) && !target__has_task(&opts->target); if (!cpu_wide && perf_can_record_cpu_wide()) { - struct perf_evsel *switch_evsel; + struct evsel *switch_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) return err; - switch_evsel = perf_evlist__last(evlist); + switch_evsel = evlist__last(evlist); - switch_evsel->attr.freq = 0; - switch_evsel->attr.sample_period = 1; - switch_evsel->attr.context_switch = 1; + switch_evsel->core.attr.freq = 0; + switch_evsel->core.attr.sample_period = 1; + switch_evsel->core.attr.context_switch = 1; - switch_evsel->system_wide = true; + switch_evsel->core.system_wide = true; switch_evsel->no_aux_samples = true; switch_evsel->immediate = true; @@ -737,31 +837,31 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * In the case of per-cpu mmaps, we need the CPU on the * AUX event. */ - if (!cpu_map__empty(cpus)) + if (!perf_cpu_map__empty(cpus)) perf_evsel__set_sample_bit(intel_pt_evsel, CPU); } /* Add dummy event to keep tracking */ if (opts->full_auxtrace) { - struct perf_evsel *tracking_evsel; + struct evsel *tracking_evsel; err = parse_events(evlist, "dummy:u", NULL); if (err) return err; - tracking_evsel = perf_evlist__last(evlist); + tracking_evsel = evlist__last(evlist); perf_evlist__set_tracking_event(evlist, tracking_evsel); - tracking_evsel->attr.freq = 0; - tracking_evsel->attr.sample_period = 1; + tracking_evsel->core.attr.freq = 0; + tracking_evsel->core.attr.sample_period = 1; tracking_evsel->no_aux_samples = true; if (need_immediate) tracking_evsel->immediate = true; /* In per-cpu case, always need the time of mmap events etc */ - if (!cpu_map__empty(cpus)) { + if (!perf_cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(tracking_evsel, TIME); /* And the CPU for switch events */ perf_evsel__set_sample_bit(tracking_evsel, CPU); @@ -773,7 +873,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, * Warn the user when we do not have enough information to decode i.e. * per-cpu with no sched_switch (except workload-only). */ - if (!ptr->have_sched_switch && !cpu_map__empty(cpus) && + if (!ptr->have_sched_switch && !perf_cpu_map__empty(cpus) && !target__none(&opts->target)) ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n"); @@ -784,11 +884,11 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evsel__disable(evsel); + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) + return evsel__disable(evsel); } return -EINVAL; } @@ -797,11 +897,11 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evsel__enable(evsel); + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) + return evsel__enable(evsel); } return -EINVAL; } @@ -1070,10 +1170,10 @@ static int intel_pt_read_finish(struct auxtrace_record *itr, int idx) { struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); - struct perf_evsel *evsel; + struct evsel *evsel; evlist__for_each_entry(ptr->evlist, evsel) { - if (evsel->attr.type == ptr->intel_pt_pmu->type) + if (evsel->core.attr.type == ptr->intel_pt_pmu->type) return perf_evlist__enable_event_idx(ptr->evlist, evsel, idx); } @@ -1110,5 +1210,10 @@ struct auxtrace_record *intel_pt_recording_init(int *err) ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options; ptr->itr.reference = intel_pt_reference; ptr->itr.read_finish = intel_pt_read_finish; + /* + * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K + * should give at least 1 PSB per sample. + */ + ptr->itr.default_aux_sample_size = 4096; return &ptr->itr; } diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c index 865a9762f22e..c0775c39227f 100644 --- a/tools/perf/arch/x86/util/kvm-stat.c +++ b/tools/perf/arch/x86/util/kvm-stat.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> -#include "../../util/kvm-stat.h" -#include "../../util/evsel.h" +#include <string.h> +#include "../../../util/kvm-stat.h" +#include "../../../util/evsel.h" #include <asm/svm.h> #include <asm/vmx.h> #include <asm/kvm.h> @@ -27,7 +28,7 @@ const char *kvm_exit_trace = "kvm:kvm_exit"; * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry * the time of MMIO read: kvm_exit -> kvm_mmio(KVM_TRACE_MMIO_READ...). */ -static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sample, +static void mmio_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { key->key = perf_evsel__intval(evsel, sample, "gpa"); @@ -38,7 +39,7 @@ static void mmio_event_get_key(struct perf_evsel *evsel, struct perf_sample *sam #define KVM_TRACE_MMIO_READ 1 #define KVM_TRACE_MMIO_WRITE 2 -static bool mmio_event_begin(struct perf_evsel *evsel, +static bool mmio_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO read begin event in kernel. */ @@ -55,7 +56,7 @@ static bool mmio_event_begin(struct perf_evsel *evsel, return false; } -static bool mmio_event_end(struct perf_evsel *evsel, struct perf_sample *sample, +static bool mmio_event_end(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { /* MMIO write end event in kernel. */ @@ -89,7 +90,7 @@ static struct kvm_events_ops mmio_events = { }; /* The time of emulation pio access is from kvm_pio to kvm_entry. */ -static void ioport_event_get_key(struct perf_evsel *evsel, +static void ioport_event_get_key(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -97,7 +98,7 @@ static void ioport_event_get_key(struct perf_evsel *evsel, key->info = perf_evsel__intval(evsel, sample, "rw"); } -static bool ioport_event_begin(struct perf_evsel *evsel, +static bool ioport_event_begin(struct evsel *evsel, struct perf_sample *sample, struct event_key *key) { @@ -109,7 +110,7 @@ static bool ioport_event_begin(struct perf_evsel *evsel, return false; } -static bool ioport_event_end(struct perf_evsel *evsel, +static bool ioport_event_end(struct evsel *evsel, struct perf_sample *sample __maybe_unused, struct event_key *key __maybe_unused) { diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c index 1e9ec783b9a1..e17e080e76f4 100644 --- a/tools/perf/arch/x86/util/machine.c +++ b/tools/perf/arch/x86/util/machine.c @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/string.h> +#include <limits.h> #include <stdlib.h> -#include "../../util/util.h" +#include <internal/lib.h> // page_size #include "../../util/machine.h" #include "../../util/map.h" #include "../../util/symbol.h" diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 0d7b77ff0ae6..c218b83e063b 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -2,11 +2,13 @@ #include <errno.h> #include <string.h> #include <regex.h> +#include <linux/kernel.h> #include <linux/zalloc.h> -#include "../../perf.h" +#include "../../perf-sys.h" #include "../../util/perf_regs.h" #include "../../util/debug.h" +#include "../../util/event.h" const struct sample_reg sample_reg_masks[] = { SMPL_REG(AX, PERF_REG_X86_AX), diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 950539f9a4f7..2f55afb14e1f 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -5,10 +5,12 @@ #include <linux/stddef.h> #include <linux/perf_event.h> -#include "../../perf.h" #include <linux/types.h> -#include "../../util/debug.h" -#include "../../util/tsc.h" +#include <asm/barrier.h> +#include "../../../util/debug.h" +#include "../../../util/event.h" +#include "../../../util/synthetic-events.h" +#include "../../../util/tsc.h" int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc, struct perf_tsc_conversion *tc) @@ -57,7 +59,7 @@ int perf_event__synth_time_conv(const struct perf_event_mmap_page *pc, .time_conv = { .header = { .type = PERF_RECORD_TIME_CONV, - .size = sizeof(struct time_conv_event), + .size = sizeof(struct perf_record_time_conv), }, }, }; diff --git a/tools/perf/arch/x86/util/unwind-libunwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c index 05920e3edf7a..47357973b55b 100644 --- a/tools/perf/arch/x86/util/unwind-libunwind.c +++ b/tools/perf/arch/x86/util/unwind-libunwind.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include "../../util/debug.h" #ifndef REMOTE_UNWIND_LIBUNWIND #include <libunwind.h> #include "perf_regs.h" #include "../../util/unwind.h" -#include "../../util/debug.h" #endif #ifdef HAVE_ARCH_X86_64_SUPPORT |