diff options
Diffstat (limited to 'llvm/test/CodeGen/X86/avg.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/avg.ll | 455 |
1 files changed, 232 insertions, 223 deletions
diff --git a/llvm/test/CodeGen/X86/avg.ll b/llvm/test/CodeGen/X86/avg.ll index c4b15070bad..84f1296d51c 100644 --- a/llvm/test/CodeGen/X86/avg.ll +++ b/llvm/test/CodeGen/X86/avg.ll @@ -2141,7 +2141,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: pushq %r13 ; AVX1-NEXT: pushq %r12 ; AVX1-NEXT: pushq %rbx -; AVX1-NEXT: subq $16, %rsp +; AVX1-NEXT: subq $24, %rsp ; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero ; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero ; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero @@ -2152,12 +2152,12 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: vmovq %xmm5, %rbp ; AVX1-NEXT: vpshufd {{.*#+}} xmm4 = xmm4[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero -; AVX1-NEXT: vpextrq $1, %xmm4, %rcx -; AVX1-NEXT: vmovq %xmm4, %rsi +; AVX1-NEXT: vpextrq $1, %xmm4, %rsi +; AVX1-NEXT: vmovq %xmm4, %rcx ; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[2,3,0,1] ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm4 = xmm3[0],zero,xmm3[1],zero -; AVX1-NEXT: vpextrq $1, %xmm4, %r10 +; AVX1-NEXT: vpextrq $1, %xmm4, %r8 ; AVX1-NEXT: vmovq %xmm4, %r11 ; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero @@ -2166,7 +2166,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm3 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm4 = xmm3[0],zero,xmm3[1],zero ; AVX1-NEXT: vpextrq $1, %xmm4, %r15 -; AVX1-NEXT: vmovq %xmm4, %rdx +; AVX1-NEXT: vmovq %xmm4, %rdi ; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero ; AVX1-NEXT: vpextrq $1, %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill @@ -2175,28 +2175,27 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm1[0],zero,xmm1[1],zero ; AVX1-NEXT: vpextrq $1, %xmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX1-NEXT: vmovq %xmm3, %r9 +; AVX1-NEXT: vmovq %xmm3, %r10 ; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm3 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm4 = xmm3[0],zero,xmm3[1],zero -; AVX1-NEXT: vpextrq $1, %xmm4, %r14 -; AVX1-NEXT: addq %rbx, %r14 -; AVX1-NEXT: vmovq %xmm4, %r8 -; AVX1-NEXT: addq %rbp, %r8 +; AVX1-NEXT: vpextrq $1, %xmm4, %rdx +; AVX1-NEXT: addq %rbx, %rdx +; AVX1-NEXT: vmovq %xmm4, %r9 +; AVX1-NEXT: addq %rbp, %r9 ; AVX1-NEXT: vpshufd {{.*#+}} xmm3 = xmm3[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm3[0],zero,xmm3[1],zero -; AVX1-NEXT: vpextrq $1, %xmm3, %rdi -; AVX1-NEXT: addq %rcx, %rdi -; AVX1-NEXT: vmovq %xmm3, %rax +; AVX1-NEXT: vpextrq $1, %xmm3, %rax ; AVX1-NEXT: addq %rsi, %rax -; AVX1-NEXT: movq %rax, %rsi +; AVX1-NEXT: movq %rax, %r14 +; AVX1-NEXT: vmovq %xmm3, %rbp +; AVX1-NEXT: addq %rcx, %rbp ; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1] ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm2[0],zero,xmm2[1],zero -; AVX1-NEXT: vpextrq $1, %xmm3, %rax -; AVX1-NEXT: addq %r10, %rax -; AVX1-NEXT: movq %rax, %r10 +; AVX1-NEXT: vpextrq $1, %xmm3, %rsi +; AVX1-NEXT: addq %r8, %rsi ; AVX1-NEXT: vmovq %xmm3, %rax ; AVX1-NEXT: addq %r11, %rax ; AVX1-NEXT: movq %rax, %r11 @@ -2204,17 +2203,17 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero ; AVX1-NEXT: vpextrq $1, %xmm2, %rax ; AVX1-NEXT: addq %r13, %rax -; AVX1-NEXT: movq %rax, %rbx +; AVX1-NEXT: movq %rax, %rcx ; AVX1-NEXT: vmovq %xmm2, %rax ; AVX1-NEXT: addq %r12, %rax -; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: movq %rax, %r8 ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm3 = xmm2[0],zero,xmm2[1],zero ; AVX1-NEXT: vpextrq $1, %xmm3, %rax ; AVX1-NEXT: addq %r15, %rax -; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: movq %rax, %rbx ; AVX1-NEXT: vmovq %xmm3, %rax -; AVX1-NEXT: addq %rdx, %rax +; AVX1-NEXT: addq %rdi, %rax ; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm2[0],zero,xmm2[1],zero @@ -2227,40 +2226,41 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1] ; AVX1-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero -; AVX1-NEXT: vpextrq $1, %xmm2, %rbp -; AVX1-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Folded Reload -; AVX1-NEXT: vmovq %xmm2, %r15 -; AVX1-NEXT: addq %r9, %r15 +; AVX1-NEXT: vpextrq $1, %xmm2, %rax +; AVX1-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload +; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: vmovq %xmm2, %r12 +; AVX1-NEXT: addq %r10, %r12 ; AVX1-NEXT: vpextrq $1, %xmm1, %rax ; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1] ; AVX1-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero -; AVX1-NEXT: vpextrq $1, %xmm0, %r9 -; AVX1-NEXT: addq %rax, %r9 -; AVX1-NEXT: vmovq %xmm1, %rcx -; AVX1-NEXT: vmovq %xmm0, %rdx -; AVX1-NEXT: addq %rcx, %rdx -; AVX1-NEXT: addq $-1, %r14 -; AVX1-NEXT: movq %r14, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: vpextrq $1, %xmm0, %r10 +; AVX1-NEXT: addq %rax, %r10 +; AVX1-NEXT: vmovq %xmm1, %rax +; AVX1-NEXT: vmovq %xmm0, %rdi +; AVX1-NEXT: addq %rax, %rdi +; AVX1-NEXT: addq $-1, %rdx +; AVX1-NEXT: movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax ; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX1-NEXT: addq $-1, %r8 -; AVX1-NEXT: movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: addq $-1, %r9 +; AVX1-NEXT: movq %r9, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax -; AVX1-NEXT: movq %rax, (%rsp) # 8-byte Spill -; AVX1-NEXT: addq $-1, %rdi -; AVX1-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: addq $-1, %r14 +; AVX1-NEXT: movq %r14, (%rsp) # 8-byte Spill ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax ; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX1-NEXT: addq $-1, %rsi -; AVX1-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: addq $-1, %rbp +; AVX1-NEXT: movq %rbp, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax ; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX1-NEXT: addq $-1, %r10 -; AVX1-NEXT: movq %r10, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: addq $-1, %rsi +; AVX1-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax ; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill @@ -2269,90 +2269,93 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax ; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: addq $-1, %rcx +; AVX1-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: movl $0, %ebp +; AVX1-NEXT: adcq $-1, %rbp +; AVX1-NEXT: addq $-1, %r8 +; AVX1-NEXT: movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: movl $0, %r15d +; AVX1-NEXT: adcq $-1, %r15 ; AVX1-NEXT: addq $-1, %rbx ; AVX1-NEXT: movq %rbx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX1-NEXT: movl $0, %eax ; AVX1-NEXT: adcq $-1, %rax ; AVX1-NEXT: movq %rax, %rsi ; AVX1-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX1-NEXT: movl $0, %r12d -; AVX1-NEXT: adcq $-1, %r12 -; AVX1-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill ; AVX1-NEXT: movl $0, %r13d ; AVX1-NEXT: adcq $-1, %r13 ; AVX1-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill ; AVX1-NEXT: movl $0, %r14d ; AVX1-NEXT: adcq $-1, %r14 -; AVX1-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX1-NEXT: movl $0, %ebx -; AVX1-NEXT: adcq $-1, %rbx -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload -; AVX1-NEXT: addq $-1, %rcx +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload +; AVX1-NEXT: addq $-1, %rdx ; AVX1-NEXT: movl $0, %r11d ; AVX1-NEXT: adcq $-1, %r11 -; AVX1-NEXT: addq $-1, %rbp -; AVX1-NEXT: movl $0, %r10d -; AVX1-NEXT: adcq $-1, %r10 -; AVX1-NEXT: addq $-1, %r15 +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload +; AVX1-NEXT: addq $-1, %rax +; AVX1-NEXT: movl $0, %ebx +; AVX1-NEXT: adcq $-1, %rbx +; AVX1-NEXT: addq $-1, %r12 +; AVX1-NEXT: movl $0, %r9d +; AVX1-NEXT: adcq $-1, %r9 +; AVX1-NEXT: addq $-1, %r10 ; AVX1-NEXT: movl $0, %r8d ; AVX1-NEXT: adcq $-1, %r8 -; AVX1-NEXT: addq $-1, %r9 -; AVX1-NEXT: movl $0, %edi -; AVX1-NEXT: adcq $-1, %rdi -; AVX1-NEXT: addq $-1, %rdx -; AVX1-NEXT: movl $0, %eax -; AVX1-NEXT: adcq $-1, %rax -; AVX1-NEXT: shldq $63, %rdx, %rax -; AVX1-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX1-NEXT: shldq $63, %r9, %rdi -; AVX1-NEXT: shldq $63, %r15, %r8 -; AVX1-NEXT: shldq $63, %rbp, %r10 -; AVX1-NEXT: shldq $63, %rcx, %r11 -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX1-NEXT: shldq $63, %rdx, %rbx +; AVX1-NEXT: addq $-1, %rdi +; AVX1-NEXT: movl $0, %ecx +; AVX1-NEXT: adcq $-1, %rcx +; AVX1-NEXT: shldq $63, %rdi, %rcx +; AVX1-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: shldq $63, %r10, %r8 +; AVX1-NEXT: shldq $63, %r12, %r9 +; AVX1-NEXT: shldq $63, %rax, %rbx +; AVX1-NEXT: shldq $63, %rdx, %r11 ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload ; AVX1-NEXT: shldq $63, %rdx, %r14 ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload ; AVX1-NEXT: shldq $63, %rdx, %r13 -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX1-NEXT: shldq $63, %rdx, %r12 ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload ; AVX1-NEXT: shldq $63, %rax, %rsi ; AVX1-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload +; AVX1-NEXT: shldq $63, %rax, %r15 +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload +; AVX1-NEXT: shldq $63, %rax, %rbp ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rsi # 8-byte Reload ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload ; AVX1-NEXT: shldq $63, %rax, %rsi -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r15 # 8-byte Reload +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload -; AVX1-NEXT: shldq $63, %rax, %r15 +; AVX1-NEXT: shldq $63, %rax, %rcx +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdi # 8-byte Reload ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload -; AVX1-NEXT: shldq $63, %rcx, %rax -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r9 # 8-byte Reload -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload -; AVX1-NEXT: shldq $63, %rcx, %r9 -; AVX1-NEXT: movq (%rsp), %rcx # 8-byte Reload -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX1-NEXT: shldq $63, %rdx, %rcx +; AVX1-NEXT: shldq $63, %rax, %rdi +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r12 # 8-byte Reload +; AVX1-NEXT: movq (%rsp), %rax # 8-byte Reload +; AVX1-NEXT: shldq $63, %rax, %r12 +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r10 # 8-byte Reload +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload +; AVX1-NEXT: shldq $63, %rax, %r10 ; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Reload -; AVX1-NEXT: shldq $63, %rbp, %rdx -; AVX1-NEXT: vmovq %rdx, %xmm8 -; AVX1-NEXT: vmovq %rcx, %xmm0 -; AVX1-NEXT: vmovq %r9, %xmm1 -; AVX1-NEXT: vmovq %rax, %xmm11 -; AVX1-NEXT: vmovq %r15, %xmm2 +; AVX1-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload +; AVX1-NEXT: shldq $63, %rdx, %rax +; AVX1-NEXT: vmovq %rax, %xmm8 +; AVX1-NEXT: vmovq %r10, %xmm0 +; AVX1-NEXT: vmovq %r12, %xmm1 +; AVX1-NEXT: vmovq %rdi, %xmm11 +; AVX1-NEXT: vmovq %rcx, %xmm2 ; AVX1-NEXT: vmovq %rsi, %xmm13 -; AVX1-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm14 # 8-byte Folded Reload -; AVX1-NEXT: # xmm14 = mem[0],zero -; AVX1-NEXT: vmovq %r12, %xmm15 -; AVX1-NEXT: vmovq %r13, %xmm9 -; AVX1-NEXT: vmovq %r14, %xmm10 -; AVX1-NEXT: vmovq %rbx, %xmm12 +; AVX1-NEXT: vmovq %rbp, %xmm14 +; AVX1-NEXT: vmovq %r15, %xmm15 +; AVX1-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm9 # 8-byte Folded Reload +; AVX1-NEXT: # xmm9 = mem[0],zero +; AVX1-NEXT: vmovq %r13, %xmm10 +; AVX1-NEXT: vmovq %r14, %xmm12 ; AVX1-NEXT: vmovq %r11, %xmm3 -; AVX1-NEXT: vmovq %r10, %xmm4 -; AVX1-NEXT: vmovq %r8, %xmm5 -; AVX1-NEXT: vmovq %rdi, %xmm6 +; AVX1-NEXT: vmovq %rbx, %xmm4 +; AVX1-NEXT: vmovq %r9, %xmm5 +; AVX1-NEXT: vmovq %r8, %xmm6 ; AVX1-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 8-byte Folded Reload ; AVX1-NEXT: # xmm7 = mem[0],zero ; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm8 = xmm0[0],xmm8[0] @@ -2379,7 +2382,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX1-NEXT: vpshufb %xmm4, %xmm1, %xmm1 ; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0] ; AVX1-NEXT: vmovdqu %xmm0, (%rax) -; AVX1-NEXT: addq $16, %rsp +; AVX1-NEXT: addq $24, %rsp ; AVX1-NEXT: popq %rbx ; AVX1-NEXT: popq %r12 ; AVX1-NEXT: popq %r13 @@ -2404,15 +2407,15 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm3 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4 ; AVX2-NEXT: vpextrq $1, %xmm4, %rbx -; AVX2-NEXT: vmovq %xmm4, %rdx +; AVX2-NEXT: vmovq %xmm4, %rbp ; AVX2-NEXT: vpextrq $1, %xmm3, %rdi ; AVX2-NEXT: vmovq %xmm3, %rcx ; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm2 ; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3 -; AVX2-NEXT: vpextrq $1, %xmm3, %r9 -; AVX2-NEXT: vmovq %xmm3, %r10 -; AVX2-NEXT: vpextrq $1, %xmm2, %r13 +; AVX2-NEXT: vpextrq $1, %xmm3, %rdx +; AVX2-NEXT: vmovq %xmm3, %r9 +; AVX2-NEXT: vpextrq $1, %xmm2, %r11 ; AVX2-NEXT: vmovq %xmm2, %r12 ; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero ; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero @@ -2430,26 +2433,26 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero,xmm2[4],zero,xmm2[5],zero,xmm2[6],zero,xmm2[7],zero ; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm3 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm4 -; AVX2-NEXT: vpextrq $1, %xmm4, %rbp -; AVX2-NEXT: addq %rbx, %rbp -; AVX2-NEXT: vmovq %xmm4, %rax -; AVX2-NEXT: addq %rdx, %rax -; AVX2-NEXT: movq %rax, %r11 -; AVX2-NEXT: vpextrq $1, %xmm3, %r8 -; AVX2-NEXT: addq %rdi, %r8 +; AVX2-NEXT: vpextrq $1, %xmm4, %rax +; AVX2-NEXT: addq %rbx, %rax +; AVX2-NEXT: movq %rax, %rbx +; AVX2-NEXT: vmovq %xmm4, %r13 +; AVX2-NEXT: addq %rbp, %r13 +; AVX2-NEXT: vpextrq $1, %xmm3, %r10 +; AVX2-NEXT: addq %rdi, %r10 ; AVX2-NEXT: vmovq %xmm3, %r14 ; AVX2-NEXT: addq %rcx, %r14 ; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm2 ; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm3 ; AVX2-NEXT: vpextrq $1, %xmm3, %rax -; AVX2-NEXT: addq %r9, %rax -; AVX2-NEXT: movq %rax, %rbx -; AVX2-NEXT: vmovq %xmm3, %rax -; AVX2-NEXT: addq %r10, %rax -; AVX2-NEXT: movq %rax, %r10 -; AVX2-NEXT: vpextrq $1, %xmm2, %rcx -; AVX2-NEXT: addq %r13, %rcx +; AVX2-NEXT: addq %rdx, %rax +; AVX2-NEXT: movq %rax, %rcx +; AVX2-NEXT: vmovq %xmm3, %r8 +; AVX2-NEXT: addq %r9, %r8 +; AVX2-NEXT: vpextrq $1, %xmm2, %rax +; AVX2-NEXT: addq %r11, %rax +; AVX2-NEXT: movq %rax, %r11 ; AVX2-NEXT: vmovq %xmm2, %rax ; AVX2-NEXT: addq %r12, %rax ; AVX2-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill @@ -2471,8 +2474,8 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0 ; AVX2-NEXT: vpmovzxdq {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero ; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm2 -; AVX2-NEXT: vpextrq $1, %xmm2, %r12 -; AVX2-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %r12 # 8-byte Folded Reload +; AVX2-NEXT: vpextrq $1, %xmm2, %rbp +; AVX2-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Folded Reload ; AVX2-NEXT: vmovq %xmm2, %r9 ; AVX2-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %r9 # 8-byte Folded Reload ; AVX2-NEXT: vpextrq $1, %xmm1, %rax @@ -2481,36 +2484,36 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: vmovq %xmm1, %rdx ; AVX2-NEXT: vmovq %xmm0, %rsi ; AVX2-NEXT: addq %rdx, %rsi -; AVX2-NEXT: addq $-1, %rbp -; AVX2-NEXT: movq %rbp, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX2-NEXT: addq $-1, %rbx +; AVX2-NEXT: movq %rbx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: movl $0, %eax ; AVX2-NEXT: adcq $-1, %rax ; AVX2-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX2-NEXT: addq $-1, %r11 -; AVX2-NEXT: movq %r11, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX2-NEXT: addq $-1, %r13 +; AVX2-NEXT: movq %r13, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: movl $0, %eax ; AVX2-NEXT: adcq $-1, %rax ; AVX2-NEXT: movq %rax, (%rsp) # 8-byte Spill -; AVX2-NEXT: addq $-1, %r8 -; AVX2-NEXT: movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX2-NEXT: addq $-1, %r10 +; AVX2-NEXT: movq %r10, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: movl $0, %eax ; AVX2-NEXT: adcq $-1, %rax ; AVX2-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: addq $-1, %r14 ; AVX2-NEXT: movq %r14, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX2-NEXT: movl $0, %ebp -; AVX2-NEXT: adcq $-1, %rbp -; AVX2-NEXT: addq $-1, %rbx -; AVX2-NEXT: movq %rbx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX2-NEXT: movl $0, %r13d +; AVX2-NEXT: adcq $-1, %r13 +; AVX2-NEXT: addq $-1, %rcx +; AVX2-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: movl $0, %eax ; AVX2-NEXT: adcq $-1, %rax ; AVX2-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX2-NEXT: addq $-1, %r10 -; AVX2-NEXT: movq %r10, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX2-NEXT: addq $-1, %r8 +; AVX2-NEXT: movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: movl $0, %r15d ; AVX2-NEXT: adcq $-1, %r15 -; AVX2-NEXT: addq $-1, %rcx -; AVX2-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX2-NEXT: addq $-1, %r11 +; AVX2-NEXT: movq %r11, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: movl $0, %ebx ; AVX2-NEXT: adcq $-1, %rbx ; AVX2-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill @@ -2525,13 +2528,13 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: adcq $-1, %rax ; AVX2-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX2-NEXT: movl $0, %r13d -; AVX2-NEXT: adcq $-1, %r13 +; AVX2-NEXT: movl $0, %r12d +; AVX2-NEXT: adcq $-1, %r12 ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload ; AVX2-NEXT: addq $-1, %rcx ; AVX2-NEXT: movl $0, %r11d ; AVX2-NEXT: adcq $-1, %r11 -; AVX2-NEXT: addq $-1, %r12 +; AVX2-NEXT: addq $-1, %rbp ; AVX2-NEXT: movl $0, %r14d ; AVX2-NEXT: adcq $-1, %r14 ; AVX2-NEXT: addq $-1, %r9 @@ -2547,10 +2550,10 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX2-NEXT: shldq $63, %rdi, %rdx ; AVX2-NEXT: shldq $63, %r9, %r10 -; AVX2-NEXT: shldq $63, %r12, %r14 +; AVX2-NEXT: shldq $63, %rbp, %r14 ; AVX2-NEXT: shldq $63, %rcx, %r11 ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload -; AVX2-NEXT: shldq $63, %rcx, %r13 +; AVX2-NEXT: shldq $63, %rcx, %r12 ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload ; AVX2-NEXT: shldq $63, %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload @@ -2566,10 +2569,10 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload ; AVX2-NEXT: shldq $63, %rcx, %rax ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload -; AVX2-NEXT: shldq $63, %rcx, %rbp -; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r12 # 8-byte Reload +; AVX2-NEXT: shldq $63, %rcx, %r13 +; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Reload ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload -; AVX2-NEXT: shldq $63, %rcx, %r12 +; AVX2-NEXT: shldq $63, %rcx, %rbp ; AVX2-NEXT: movq (%rsp), %rdi # 8-byte Reload ; AVX2-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload ; AVX2-NEXT: shldq $63, %rcx, %rdi @@ -2578,8 +2581,8 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: shldq $63, %rcx, %rsi ; AVX2-NEXT: vmovq %rsi, %xmm8 ; AVX2-NEXT: vmovq %rdi, %xmm9 -; AVX2-NEXT: vmovq %r12, %xmm10 -; AVX2-NEXT: vmovq %rbp, %xmm11 +; AVX2-NEXT: vmovq %rbp, %xmm10 +; AVX2-NEXT: vmovq %r13, %xmm11 ; AVX2-NEXT: vmovq %rax, %xmm12 ; AVX2-NEXT: vmovq %r15, %xmm13 ; AVX2-NEXT: vmovq %rbx, %xmm14 @@ -2587,7 +2590,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX2-NEXT: vmovq %r9, %xmm0 ; AVX2-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 8-byte Folded Reload ; AVX2-NEXT: # xmm1 = mem[0],zero -; AVX2-NEXT: vmovq %r13, %xmm2 +; AVX2-NEXT: vmovq %r12, %xmm2 ; AVX2-NEXT: vmovq %r11, %xmm3 ; AVX2-NEXT: vmovq %r14, %xmm4 ; AVX2-NEXT: vmovq %r10, %xmm5 @@ -2644,7 +2647,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: pushq %r13 ; AVX512-NEXT: pushq %r12 ; AVX512-NEXT: pushq %rbx -; AVX512-NEXT: subq $16, %rsp +; AVX512-NEXT: subq $24, %rsp ; AVX512-NEXT: vpmovzxbw {{.*#+}} ymm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero ; AVX512-NEXT: vpmovzxbw {{.*#+}} ymm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero ; AVX512-NEXT: vpmovzxwd {{.*#+}} ymm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero @@ -2657,8 +2660,8 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: vmovq %xmm3, %rsi ; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3 -; AVX512-NEXT: vpextrq $1, %xmm3, %rcx -; AVX512-NEXT: vmovq %xmm3, %r10 +; AVX512-NEXT: vpextrq $1, %xmm3, %rdx +; AVX512-NEXT: vmovq %xmm3, %r8 ; AVX512-NEXT: vpextrq $1, %xmm2, %r13 ; AVX512-NEXT: vmovq %xmm2, %r12 ; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm0 @@ -2666,7 +2669,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm2 ; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3 -; AVX512-NEXT: vpextrq $1, %xmm3, %rdx +; AVX512-NEXT: vpextrq $1, %xmm3, %r15 ; AVX512-NEXT: vmovq %xmm3, %r14 ; AVX512-NEXT: vpextrq $1, %xmm2, %r9 ; AVX512-NEXT: vmovq %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill @@ -2678,34 +2681,35 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3 ; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm3 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero ; AVX512-NEXT: vextracti128 $1, %ymm3, %xmm4 -; AVX512-NEXT: vpextrq $1, %xmm4, %r11 -; AVX512-NEXT: addq %rbx, %r11 +; AVX512-NEXT: vpextrq $1, %xmm4, %rax +; AVX512-NEXT: addq %rbx, %rax +; AVX512-NEXT: movq %rax, %rbx ; AVX512-NEXT: vmovq %xmm4, %rax ; AVX512-NEXT: addq %rbp, %rax -; AVX512-NEXT: movq %rax, %rbx -; AVX512-NEXT: vpextrq $1, %xmm3, %r8 -; AVX512-NEXT: addq %rdi, %r8 -; AVX512-NEXT: vmovq %xmm3, %r15 -; AVX512-NEXT: addq %rsi, %r15 +; AVX512-NEXT: movq %rax, %rbp +; AVX512-NEXT: vpextrq $1, %xmm3, %rax +; AVX512-NEXT: addq %rdi, %rax +; AVX512-NEXT: movq %rax, %rdi +; AVX512-NEXT: vmovq %xmm3, %r10 +; AVX512-NEXT: addq %rsi, %r10 ; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3 -; AVX512-NEXT: vpextrq $1, %xmm3, %rdi -; AVX512-NEXT: addq %rcx, %rdi +; AVX512-NEXT: vpextrq $1, %xmm3, %rcx +; AVX512-NEXT: addq %rdx, %rcx ; AVX512-NEXT: vmovq %xmm3, %rax -; AVX512-NEXT: addq %r10, %rax -; AVX512-NEXT: movq %rax, %r10 +; AVX512-NEXT: addq %r8, %rax +; AVX512-NEXT: movq %rax, %r8 ; AVX512-NEXT: vpextrq $1, %xmm2, %rsi ; AVX512-NEXT: addq %r13, %rsi -; AVX512-NEXT: vmovq %xmm2, %rax -; AVX512-NEXT: addq %r12, %rax -; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: vmovq %xmm2, %r11 +; AVX512-NEXT: addq %r12, %r11 ; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm1 ; AVX512-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero ; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2 ; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm2 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero ; AVX512-NEXT: vextracti128 $1, %ymm2, %xmm3 ; AVX512-NEXT: vpextrq $1, %xmm3, %rax -; AVX512-NEXT: addq %rdx, %rax +; AVX512-NEXT: addq %r15, %rax ; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: vmovq %xmm3, %rax ; AVX512-NEXT: addq %r14, %rax @@ -2718,33 +2722,24 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: vpmovzxdq {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero ; AVX512-NEXT: vextracti128 $1, %ymm1, %xmm2 -; AVX512-NEXT: vpextrq $1, %xmm2, %rbp -; AVX512-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Folded Reload +; AVX512-NEXT: vpextrq $1, %xmm2, %rax +; AVX512-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Folded Reload +; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: vmovq %xmm2, %r14 ; AVX512-NEXT: addq {{[-0-9]+}}(%r{{[sb]}}p), %r14 # 8-byte Folded Reload ; AVX512-NEXT: vpextrq $1, %xmm0, %rax ; AVX512-NEXT: vpextrq $1, %xmm1, %r9 ; AVX512-NEXT: addq %rax, %r9 -; AVX512-NEXT: vmovq %xmm0, %rcx +; AVX512-NEXT: vmovq %xmm0, %rax ; AVX512-NEXT: vmovq %xmm1, %rdx -; AVX512-NEXT: addq %rcx, %rdx -; AVX512-NEXT: addq $-1, %r11 -; AVX512-NEXT: movq %r11, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX512-NEXT: movl $0, %eax -; AVX512-NEXT: adcq $-1, %rax -; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: addq %rax, %rdx ; AVX512-NEXT: addq $-1, %rbx ; AVX512-NEXT: movq %rbx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: movl $0, %eax ; AVX512-NEXT: adcq $-1, %rax -; AVX512-NEXT: movq %rax, (%rsp) # 8-byte Spill -; AVX512-NEXT: addq $-1, %r8 -; AVX512-NEXT: movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX512-NEXT: movl $0, %eax -; AVX512-NEXT: adcq $-1, %rax ; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX512-NEXT: addq $-1, %r15 -; AVX512-NEXT: movq %r15, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: addq $-1, %rbp +; AVX512-NEXT: movq %rbp, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: movl $0, %eax ; AVX512-NEXT: adcq $-1, %rax ; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill @@ -2752,94 +2747,108 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: movl $0, %eax ; AVX512-NEXT: adcq $-1, %rax -; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: movq %rax, (%rsp) # 8-byte Spill ; AVX512-NEXT: addq $-1, %r10 ; AVX512-NEXT: movq %r10, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: movl $0, %eax ; AVX512-NEXT: adcq $-1, %rax -; AVX512-NEXT: movq %rax, %rcx +; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: addq $-1, %rcx +; AVX512-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: movl $0, %eax +; AVX512-NEXT: adcq $-1, %rax +; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: addq $-1, %r8 +; AVX512-NEXT: movq %r8, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: movl $0, %eax +; AVX512-NEXT: adcq $-1, %rax +; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: addq $-1, %rsi ; AVX512-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX512-NEXT: movl $0, %r12d -; AVX512-NEXT: adcq $-1, %r12 -; AVX512-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX512-NEXT: movl $0, %ebx -; AVX512-NEXT: adcq $-1, %rbx -; AVX512-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill ; AVX512-NEXT: movl $0, %r13d ; AVX512-NEXT: adcq $-1, %r13 -; AVX512-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill +; AVX512-NEXT: addq $-1, %r11 +; AVX512-NEXT: movq %r11, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: movl $0, %r15d ; AVX512-NEXT: adcq $-1, %r15 ; AVX512-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX512-NEXT: movl $0, %r11d -; AVX512-NEXT: adcq $-1, %r11 +; AVX512-NEXT: movl $0, %eax +; AVX512-NEXT: adcq $-1, %rax +; AVX512-NEXT: movq %rax, %rsi ; AVX512-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill -; AVX512-NEXT: movl $0, %r8d -; AVX512-NEXT: adcq $-1, %r8 +; AVX512-NEXT: movl $0, %r12d +; AVX512-NEXT: adcq $-1, %r12 +; AVX512-NEXT: addq $-1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill +; AVX512-NEXT: movl $0, %ebx +; AVX512-NEXT: adcq $-1, %rbx +; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Reload ; AVX512-NEXT: addq $-1, %rbp +; AVX512-NEXT: movl $0, %r11d +; AVX512-NEXT: adcq $-1, %r11 +; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload +; AVX512-NEXT: addq $-1, %rax ; AVX512-NEXT: movl $0, %r10d ; AVX512-NEXT: adcq $-1, %r10 ; AVX512-NEXT: addq $-1, %r14 +; AVX512-NEXT: movl $0, %r8d +; AVX512-NEXT: adcq $-1, %r8 +; AVX512-NEXT: addq $-1, %r9 ; AVX512-NEXT: movl $0, %edi ; AVX512-NEXT: adcq $-1, %rdi -; AVX512-NEXT: addq $-1, %r9 -; AVX512-NEXT: movl $0, %esi -; AVX512-NEXT: adcq $-1, %rsi ; AVX512-NEXT: addq $-1, %rdx -; AVX512-NEXT: movl $0, %eax -; AVX512-NEXT: adcq $-1, %rax -; AVX512-NEXT: shldq $63, %rdx, %rax -; AVX512-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill -; AVX512-NEXT: shldq $63, %r9, %rsi -; AVX512-NEXT: shldq $63, %r14, %rdi -; AVX512-NEXT: shldq $63, %rbp, %r10 -; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX512-NEXT: shldq $63, %rdx, %r8 +; AVX512-NEXT: movl $0, %ecx +; AVX512-NEXT: adcq $-1, %rcx +; AVX512-NEXT: shldq $63, %rdx, %rcx +; AVX512-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: shldq $63, %r9, %rdi +; AVX512-NEXT: shldq $63, %r14, %r8 +; AVX512-NEXT: shldq $63, %rax, %r10 +; AVX512-NEXT: shldq $63, %rbp, %r11 ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX512-NEXT: shldq $63, %rdx, %r11 +; AVX512-NEXT: shldq $63, %rdx, %rbx ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX512-NEXT: shldq $63, %rdx, %r15 +; AVX512-NEXT: shldq $63, %rdx, %r12 ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload -; AVX512-NEXT: shldq $63, %rdx, %r13 +; AVX512-NEXT: shldq $63, %rdx, %rsi +; AVX512-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload -; AVX512-NEXT: shldq $63, %rax, %rbx +; AVX512-NEXT: shldq $63, %rax, %r15 ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload -; AVX512-NEXT: shldq $63, %rax, %r12 +; AVX512-NEXT: shldq $63, %rax, %r13 +; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rsi # 8-byte Reload ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload -; AVX512-NEXT: shldq $63, %rax, %rcx -; AVX512-NEXT: movq %rcx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill +; AVX512-NEXT: shldq $63, %rax, %rsi ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload ; AVX512-NEXT: shldq $63, %rax, %rcx ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload ; AVX512-NEXT: shldq $63, %rdx, %rax -; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r14 # 8-byte Reload +; AVX512-NEXT: movq (%rsp), %r14 # 8-byte Reload ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload ; AVX512-NEXT: shldq $63, %rdx, %r14 -; AVX512-NEXT: movq (%rsp), %r9 # 8-byte Reload +; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %r9 # 8-byte Reload ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload ; AVX512-NEXT: shldq $63, %rdx, %r9 ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload ; AVX512-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rbp # 8-byte Reload -; AVX512-NEXT: shldq $63, %rbp, %rdx -; AVX512-NEXT: vmovq %rdx, %xmm8 +; AVX512-NEXT: shldq $63, %rdx, %rbp +; AVX512-NEXT: vmovq %rbp, %xmm8 ; AVX512-NEXT: vmovq %r9, %xmm9 ; AVX512-NEXT: vmovq %r14, %xmm10 ; AVX512-NEXT: vmovq %rax, %xmm11 ; AVX512-NEXT: vmovq %rcx, %xmm12 -; AVX512-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm13 # 8-byte Folded Reload -; AVX512-NEXT: # xmm13 = mem[0],zero -; AVX512-NEXT: vmovq %r12, %xmm14 -; AVX512-NEXT: vmovq %rbx, %xmm15 -; AVX512-NEXT: vmovq %r13, %xmm0 -; AVX512-NEXT: vmovq %r15, %xmm1 -; AVX512-NEXT: vmovq %r11, %xmm2 -; AVX512-NEXT: vmovq %r8, %xmm3 +; AVX512-NEXT: vmovq %rsi, %xmm13 +; AVX512-NEXT: vmovq %r13, %xmm14 +; AVX512-NEXT: vmovq %r15, %xmm15 +; AVX512-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Folded Reload +; AVX512-NEXT: # xmm0 = mem[0],zero +; AVX512-NEXT: vmovq %r12, %xmm1 +; AVX512-NEXT: vmovq %rbx, %xmm2 +; AVX512-NEXT: vmovq %r11, %xmm3 ; AVX512-NEXT: vmovq %r10, %xmm4 -; AVX512-NEXT: vmovq %rdi, %xmm5 -; AVX512-NEXT: vmovq %rsi, %xmm6 +; AVX512-NEXT: vmovq %r8, %xmm5 +; AVX512-NEXT: vmovq %rdi, %xmm6 ; AVX512-NEXT: vmovq {{[-0-9]+}}(%r{{[sb]}}p), %xmm7 # 8-byte Folded Reload ; AVX512-NEXT: # xmm7 = mem[0],zero ; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm8 = xmm9[0],xmm8[0] @@ -2860,7 +2869,7 @@ define void @not_avg_v16i8_wide_constants(<16 x i8>* %a, <16 x i8>* %b) nounwind ; AVX512-NEXT: vpmovqd %zmm0, %ymm0 ; AVX512-NEXT: vinserti64x4 $1, %ymm0, %zmm2, %zmm0 ; AVX512-NEXT: vpmovdb %zmm0, (%rax) -; AVX512-NEXT: addq $16, %rsp +; AVX512-NEXT: addq $24, %rsp ; AVX512-NEXT: popq %rbx ; AVX512-NEXT: popq %r12 ; AVX512-NEXT: popq %r13 |
