summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--llvm/lib/Target/X86/X86InstrSSE.td9
-rw-r--r--llvm/test/CodeGen/X86/avx-schedule.ll2
-rw-r--r--llvm/test/CodeGen/X86/avx2-schedule.ll18
3 files changed, 15 insertions, 14 deletions
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index 17cc8068078..7c07cfa02bd 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -7482,7 +7482,8 @@ class avx2_broadcast_rr<bits<8> opc, string OpcodeStr, RegisterClass RC,
let ExeDomain = SSEPackedSingle, Predicates = [HasAVX, NoVLX] in {
def VBROADCASTSSrm : avx_broadcast_rm<0x18, "vbroadcastss", VR128,
- f32mem, v4f32, loadf32, WriteLoad>;
+ f32mem, v4f32, loadf32,
+ WriteFShuffleLd>;
def VBROADCASTSSYrm : avx_broadcast_rm<0x18, "vbroadcastss", VR256,
f32mem, v8f32, loadf32,
WriteFShuffleLd>, VEX_L;
@@ -7518,7 +7519,7 @@ let mayLoad = 1, hasSideEffects = 0, Predicates = [HasAVX2] in
def VBROADCASTI128 : AVX8I<0x5A, MRMSrcMem, (outs VR256:$dst),
(ins i128mem:$src),
"vbroadcasti128\t{$src, $dst|$dst, $src}", []>,
- Sched<[WriteLoad]>, VEX, VEX_L;
+ Sched<[WriteShuffleLd]>, VEX, VEX_L;
let mayLoad = 1, hasSideEffects = 0, Predicates = [HasAVX],
ExeDomain = SSEPackedSingle in
@@ -7974,7 +7975,7 @@ multiclass avx2_broadcast<bits<8> opc, string OpcodeStr,
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst,
(OpVT128 (X86VBroadcast (ld_frag addr:$src))))]>,
- Sched<[WriteLoad]>, VEX;
+ Sched<[WriteShuffleLd]>, VEX;
def Yrr : AVX28I<opc, MRMSrcReg, (outs VR256:$dst), (ins VR128:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR256:$dst,
@@ -7984,7 +7985,7 @@ multiclass avx2_broadcast<bits<8> opc, string OpcodeStr,
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR256:$dst,
(OpVT256 (X86VBroadcast (ld_frag addr:$src))))]>,
- Sched<[WriteLoad]>, VEX, VEX_L;
+ Sched<[WriteShuffleLd]>, VEX, VEX_L;
// Provide aliases for broadcast from the same register class that
// automatically does the extract.
diff --git a/llvm/test/CodeGen/X86/avx-schedule.ll b/llvm/test/CodeGen/X86/avx-schedule.ll
index 5800917faae..6d25787c190 100644
--- a/llvm/test/CodeGen/X86/avx-schedule.ll
+++ b/llvm/test/CodeGen/X86/avx-schedule.ll
@@ -859,7 +859,7 @@ define <4 x float> @test_broadcastss(float *%a0) {
;
; BTVER2-LABEL: test_broadcastss:
; BTVER2: # %bb.0:
-; BTVER2-NEXT: vbroadcastss (%rdi), %xmm0 # sched: [5:1.00]
+; BTVER2-NEXT: vbroadcastss (%rdi), %xmm0 # sched: [6:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_broadcastss:
diff --git a/llvm/test/CodeGen/X86/avx2-schedule.ll b/llvm/test/CodeGen/X86/avx2-schedule.ll
index 89903e7c5c9..d06b6a78a8c 100644
--- a/llvm/test/CodeGen/X86/avx2-schedule.ll
+++ b/llvm/test/CodeGen/X86/avx2-schedule.ll
@@ -9,7 +9,7 @@
define <8 x i32> @test_broadcasti128(<8 x i32> %a0, <4 x i32> *%a1) {
; GENERIC-LABEL: test_broadcasti128:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vbroadcasti128 {{.*#+}} ymm1 = mem[0,1,0,1] sched: [4:0.50]
+; GENERIC-NEXT: vbroadcasti128 {{.*#+}} ymm1 = mem[0,1,0,1] sched: [5:1.00]
; GENERIC-NEXT: vpaddd %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -1762,7 +1762,7 @@ define <16 x i8> @test_pbroadcastb(<16 x i8> %a0, <16 x i8> *%a1) {
; GENERIC-LABEL: test_pbroadcastb:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastb %xmm0, %xmm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastb (%rdi), %xmm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastb (%rdi), %xmm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddb %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -1811,7 +1811,7 @@ define <32 x i8> @test_pbroadcastb_ymm(<32 x i8> %a0, <32 x i8> *%a1) {
; GENERIC-LABEL: test_pbroadcastb_ymm:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastb %xmm0, %ymm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastb (%rdi), %ymm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastb (%rdi), %ymm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddb %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -1860,7 +1860,7 @@ define <4 x i32> @test_pbroadcastd(<4 x i32> %a0, <4 x i32> *%a1) {
; GENERIC-LABEL: test_pbroadcastd:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastd %xmm0, %xmm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastd (%rdi), %xmm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastd (%rdi), %xmm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddd %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -1908,7 +1908,7 @@ define <8 x i32> @test_pbroadcastd_ymm(<8 x i32> %a0, <8 x i32> *%a1) {
; GENERIC-LABEL: test_pbroadcastd_ymm:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastd %xmm0, %ymm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastd (%rdi), %ymm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastd (%rdi), %ymm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddd %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -1956,7 +1956,7 @@ define <2 x i64> @test_pbroadcastq(<2 x i64> %a0, <2 x i64> *%a1) {
; GENERIC-LABEL: test_pbroadcastq:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastq %xmm0, %xmm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastq (%rdi), %xmm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastq (%rdi), %xmm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddq %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -2004,7 +2004,7 @@ define <4 x i64> @test_pbroadcastq_ymm(<4 x i64> %a0, <4 x i64> *%a1) {
; GENERIC-LABEL: test_pbroadcastq_ymm:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastq %xmm0, %ymm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastq (%rdi), %ymm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastq (%rdi), %ymm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddq %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -2052,7 +2052,7 @@ define <8 x i16> @test_pbroadcastw(<8 x i16> %a0, <8 x i16> *%a1) {
; GENERIC-LABEL: test_pbroadcastw:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastw %xmm0, %xmm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastw (%rdi), %xmm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastw (%rdi), %xmm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddw %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
@@ -2101,7 +2101,7 @@ define <16 x i16> @test_pbroadcastw_ymm(<16 x i16> %a0, <16 x i16> *%a1) {
; GENERIC-LABEL: test_pbroadcastw_ymm:
; GENERIC: # %bb.0:
; GENERIC-NEXT: vpbroadcastw %xmm0, %ymm0 # sched: [1:1.00]
-; GENERIC-NEXT: vpbroadcastw (%rdi), %ymm1 # sched: [4:0.50]
+; GENERIC-NEXT: vpbroadcastw (%rdi), %ymm1 # sched: [5:1.00]
; GENERIC-NEXT: vpaddw %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
OpenPOWER on IntegriCloud