maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][TwoAddressInstructionPass] Teach tryInstructionCommute to continue checking for commutable FMA operands in more cases. 

Previously we would only check for another commutable operand if the first commute was an aggressive commute.

But if we have two kill operands and neither is tied to the def at the start, we should consider both operands as the one to use as the new def.

This improves the loop in the fma-commute-loop.ll test. This test is derived from a post from discourse here https://llvm.discourse.group/t/unnecessary-vmovapd-instructions-generated-can-you-hint-in-favor-of-vfmadd231pd/582

Differential Revision: https://reviews.llvm.org/D75016
This commit is contained in:
Craig Topper 2020-02-27 20:53:17 -08:00
parent 211fb91f10
commit b6e2796114
5 changed files with 76 additions and 83 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
llvm/lib/CodeGen/TwoAddressInstructionPass.cpp
View File

@ -1238,21 +1238,18 @@ bool TwoAddressInstructionPass::tryInstructionCommute(MachineInstr *MI,
Dist)) { Dist)) {
MadeChange = true; MadeChange = true;
++NumCommuted; ++NumCommuted;
if (AggressiveCommute) { if (AggressiveCommute)
++NumAggrCommuted; ++NumAggrCommuted;
// There might be more than two commutable operands, update BaseOp and
// continue scanning. // There might be more than two commutable operands, update BaseOp and
// FIXME: This assumes that the new instruction's operands are in the // continue scanning.
// same positions and were simply swapped. // FIXME: This assumes that the new instruction's operands are in the
BaseOpReg = OtherOpReg; // same positions and were simply swapped.
BaseOpKilled = OtherOpKilled; BaseOpReg = OtherOpReg;
// Resamples OpsNum in case the number of operands was reduced. This BaseOpKilled = OtherOpKilled;
// happens with X86. // Resamples OpsNum in case the number of operands was reduced. This
OpsNum = MI->getDesc().getNumOperands(); // happens with X86.
continue; OpsNum = MI->getDesc().getNumOperands();
}
// If this was a commute based on kill, we won't do better continuing.
return MadeChange;
} }
} }
return MadeChange; return MadeChange;

24
llvm/test/CodeGen/X86/fma-commute-loop.ll
View File

@ -25,25 +25,23 @@ define void @eggs(<8 x double>* %arg, <8 x double>* %arg1, <8 x double>* %arg2,
; CHECK-NEXT: addq {{[0-9]+}}(%rsp), %r12 ; CHECK-NEXT: addq {{[0-9]+}}(%rsp), %r12
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1 ; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2 ; CHECK-NEXT: vxorpd %xmm2, %xmm2, %xmm2
; CHECK-NEXT: vxorpd %xmm3, %xmm3, %xmm3
; CHECK-NEXT: vxorpd %xmm4, %xmm4, %xmm4 ; CHECK-NEXT: vxorpd %xmm4, %xmm4, %xmm4
; CHECK-NEXT: vxorpd %xmm5, %xmm5, %xmm5 ; CHECK-NEXT: vxorpd %xmm5, %xmm5, %xmm5
; CHECK-NEXT: vxorpd %xmm3, %xmm3, %xmm3
; CHECK-NEXT: .p2align 4, 0x90 ; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: LBB0_1: ## %bb15 ; CHECK-NEXT: LBB0_1: ## %bb15
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1 ; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vmovapd %zmm5, %zmm6 ; CHECK-NEXT: vmovupd (%rax,%r11,8), %zmm6
; CHECK-NEXT: vmovapd %zmm4, %zmm7 ; CHECK-NEXT: vmovupd (%rax,%r13,8), %zmm7
; CHECK-NEXT: vmovupd (%rax,%r11,8), %zmm4
; CHECK-NEXT: vmovupd (%rax,%r13,8), %zmm5
; CHECK-NEXT: vmovupd (%rax,%r12,8), %zmm8 ; CHECK-NEXT: vmovupd (%rax,%r12,8), %zmm8
; CHECK-NEXT: vbroadcastsd (%r15,%rbx,8), %zmm9 ; CHECK-NEXT: vbroadcastsd (%r15,%rbx,8), %zmm9
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm0 = (zmm4 * zmm9) + zmm0 ; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm0 = (zmm6 * zmm9) + zmm0
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm1 = (zmm5 * zmm9) + zmm1 ; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm1 = (zmm7 * zmm9) + zmm1
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm2 = (zmm8 * zmm9) + zmm2 ; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm2 = (zmm8 * zmm9) + zmm2
; CHECK-NEXT: vbroadcastsd (%r14,%rbx,8), %zmm9 ; CHECK-NEXT: vbroadcastsd (%r14,%rbx,8), %zmm9
; CHECK-NEXT: vfmadd213pd {{.*#+}} zmm4 = (zmm9 * zmm4) + zmm7 ; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm3 = (zmm9 * zmm6) + zmm3
; CHECK-NEXT: vfmadd213pd {{.*#+}} zmm5 = (zmm9 * zmm5) + zmm6 ; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm4 = (zmm9 * zmm7) + zmm4
; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm3 = (zmm8 * zmm9) + zmm3 ; CHECK-NEXT: vfmadd231pd {{.*#+}} zmm5 = (zmm8 * zmm9) + zmm5
; CHECK-NEXT: incq %rbx ; CHECK-NEXT: incq %rbx
; CHECK-NEXT: cmpq %rbx, %r10 ; CHECK-NEXT: cmpq %rbx, %r10
; CHECK-NEXT: jne LBB0_1 ; CHECK-NEXT: jne LBB0_1
@ -51,9 +49,9 @@ define void @eggs(<8 x double>* %arg, <8 x double>* %arg1, <8 x double>* %arg2,
; CHECK-NEXT: vmovapd %zmm0, (%rdi) ; CHECK-NEXT: vmovapd %zmm0, (%rdi)
; CHECK-NEXT: vmovapd %zmm1, (%rsi) ; CHECK-NEXT: vmovapd %zmm1, (%rsi)
; CHECK-NEXT: vmovapd %zmm2, (%rdx) ; CHECK-NEXT: vmovapd %zmm2, (%rdx)
; CHECK-NEXT: vmovapd %zmm4, (%rcx) ; CHECK-NEXT: vmovapd %zmm3, (%rcx)
; CHECK-NEXT: vmovapd %zmm5, (%r8) ; CHECK-NEXT: vmovapd %zmm4, (%r8)
; CHECK-NEXT: vmovapd %zmm3, (%r9) ; CHECK-NEXT: vmovapd %zmm5, (%r9)
; CHECK-NEXT: popq %rbx ; CHECK-NEXT: popq %rbx
; CHECK-NEXT: popq %r12 ; CHECK-NEXT: popq %r12
; CHECK-NEXT: popq %r13 ; CHECK-NEXT: popq %r13

66
llvm/test/CodeGen/X86/recip-fastmath.ll
View File

@ -144,9 +144,8 @@ define float @f32_one_step_variables(float %x, float %y) #1 {
; FMA-RECIP: # %bb.0: ; FMA-RECIP: # %bb.0:
; FMA-RECIP-NEXT: vrcpss %xmm1, %xmm1, %xmm2 ; FMA-RECIP-NEXT: vrcpss %xmm1, %xmm1, %xmm2
; FMA-RECIP-NEXT: vmulss %xmm2, %xmm0, %xmm3 ; FMA-RECIP-NEXT: vmulss %xmm2, %xmm0, %xmm3
; FMA-RECIP-NEXT: vfmsub213ss {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0 ; FMA-RECIP-NEXT: vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; FMA-RECIP-NEXT: vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3 ; FMA-RECIP-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; FMA-RECIP-NEXT: vmovaps %xmm2, %xmm0
; FMA-RECIP-NEXT: retq ; FMA-RECIP-NEXT: retq
; ;
; BDVER2-LABEL: f32_one_step_variables: ; BDVER2-LABEL: f32_one_step_variables:
@ -181,9 +180,8 @@ define float @f32_one_step_variables(float %x, float %y) #1 {
; HASWELL: # %bb.0: ; HASWELL: # %bb.0:
; HASWELL-NEXT: vrcpss %xmm1, %xmm1, %xmm2 ; HASWELL-NEXT: vrcpss %xmm1, %xmm1, %xmm2
; HASWELL-NEXT: vmulss %xmm2, %xmm0, %xmm3 ; HASWELL-NEXT: vmulss %xmm2, %xmm0, %xmm3
; HASWELL-NEXT: vfmsub213ss {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0 ; HASWELL-NEXT: vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; HASWELL-NEXT: vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3 ; HASWELL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; HASWELL-NEXT: vmovaps %xmm2, %xmm0
; HASWELL-NEXT: retq ; HASWELL-NEXT: retq
; ;
; HASWELL-NO-FMA-LABEL: f32_one_step_variables: ; HASWELL-NO-FMA-LABEL: f32_one_step_variables:
@ -200,9 +198,8 @@ define float @f32_one_step_variables(float %x, float %y) #1 {
; AVX512: # %bb.0: ; AVX512: # %bb.0:
; AVX512-NEXT: vrcpss %xmm1, %xmm1, %xmm2 ; AVX512-NEXT: vrcpss %xmm1, %xmm1, %xmm2
; AVX512-NEXT: vmulss %xmm2, %xmm0, %xmm3 ; AVX512-NEXT: vmulss %xmm2, %xmm0, %xmm3
; AVX512-NEXT: vfmsub213ss {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0 ; AVX512-NEXT: vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; AVX512-NEXT: vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3 ; AVX512-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; AVX512-NEXT: vmovaps %xmm2, %xmm0
; AVX512-NEXT: retq ; AVX512-NEXT: retq
%div = fdiv fast float %x, %y %div = fdiv fast float %x, %y
ret float %div ret float %div
@ -445,10 +442,11 @@ define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
; ;
; HASWELL-LABEL: v4f32_one_step: ; HASWELL-LABEL: v4f32_one_step:
; HASWELL: # %bb.0: ; HASWELL: # %bb.0:
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 ; HASWELL-NEXT: vrcpps %xmm0, %xmm2
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT: vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - xmm2 ; HASWELL-NEXT: vfmsub231ps {{.*#+}} xmm1 = (xmm2 * xmm0) - xmm1
; HASWELL-NEXT: vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1 ; HASWELL-NEXT: vfnmadd132ps {{.*#+}} xmm1 = -(xmm1 * xmm2) + xmm2
; HASWELL-NEXT: vmovaps %xmm1, %xmm0
; HASWELL-NEXT: retq ; HASWELL-NEXT: retq
; ;
; HASWELL-NO-FMA-LABEL: v4f32_one_step: ; HASWELL-NO-FMA-LABEL: v4f32_one_step:
@ -463,10 +461,11 @@ define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
; ;
; KNL-LABEL: v4f32_one_step: ; KNL-LABEL: v4f32_one_step:
; KNL: # %bb.0: ; KNL: # %bb.0:
; KNL-NEXT: vrcpps %xmm0, %xmm1 ; KNL-NEXT: vrcpps %xmm0, %xmm2
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; KNL-NEXT: vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; KNL-NEXT: vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - xmm2 ; KNL-NEXT: vfmsub231ps {{.*#+}} xmm1 = (xmm2 * xmm0) - xmm1
; KNL-NEXT: vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1 ; KNL-NEXT: vfnmadd132ps {{.*#+}} xmm1 = -(xmm1 * xmm2) + xmm2
; KNL-NEXT: vmovaps %xmm1, %xmm0
; KNL-NEXT: retq ; KNL-NEXT: retq
; ;
; SKX-LABEL: v4f32_one_step: ; SKX-LABEL: v4f32_one_step:
@ -505,9 +504,8 @@ define <4 x float> @v4f32_one_step_variables(<4 x float> %x, <4 x float> %y) #1
; FMA-RECIP: # %bb.0: ; FMA-RECIP: # %bb.0:
; FMA-RECIP-NEXT: vrcpps %xmm1, %xmm2 ; FMA-RECIP-NEXT: vrcpps %xmm1, %xmm2
; FMA-RECIP-NEXT: vmulps %xmm2, %xmm0, %xmm3 ; FMA-RECIP-NEXT: vmulps %xmm2, %xmm0, %xmm3
; FMA-RECIP-NEXT: vfmsub213ps {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0 ; FMA-RECIP-NEXT: vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; FMA-RECIP-NEXT: vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3 ; FMA-RECIP-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; FMA-RECIP-NEXT: vmovaps %xmm2, %xmm0
; FMA-RECIP-NEXT: retq ; FMA-RECIP-NEXT: retq
; ;
; BDVER2-LABEL: v4f32_one_step_variables: ; BDVER2-LABEL: v4f32_one_step_variables:
@ -542,9 +540,8 @@ define <4 x float> @v4f32_one_step_variables(<4 x float> %x, <4 x float> %y) #1
; HASWELL: # %bb.0: ; HASWELL: # %bb.0:
; HASWELL-NEXT: vrcpps %xmm1, %xmm2 ; HASWELL-NEXT: vrcpps %xmm1, %xmm2
; HASWELL-NEXT: vmulps %xmm2, %xmm0, %xmm3 ; HASWELL-NEXT: vmulps %xmm2, %xmm0, %xmm3
; HASWELL-NEXT: vfmsub213ps {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0 ; HASWELL-NEXT: vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3 ; HASWELL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; HASWELL-NEXT: vmovaps %xmm2, %xmm0
; HASWELL-NEXT: retq ; HASWELL-NEXT: retq
; ;
; HASWELL-NO-FMA-LABEL: v4f32_one_step_variables: ; HASWELL-NO-FMA-LABEL: v4f32_one_step_variables:
@ -561,9 +558,8 @@ define <4 x float> @v4f32_one_step_variables(<4 x float> %x, <4 x float> %y) #1
; AVX512: # %bb.0: ; AVX512: # %bb.0:
; AVX512-NEXT: vrcpps %xmm1, %xmm2 ; AVX512-NEXT: vrcpps %xmm1, %xmm2
; AVX512-NEXT: vmulps %xmm2, %xmm0, %xmm3 ; AVX512-NEXT: vmulps %xmm2, %xmm0, %xmm3
; AVX512-NEXT: vfmsub213ps {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0 ; AVX512-NEXT: vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0
; AVX512-NEXT: vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3 ; AVX512-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3
; AVX512-NEXT: vmovaps %xmm2, %xmm0
; AVX512-NEXT: retq ; AVX512-NEXT: retq
%div = fdiv fast <4 x float> %x, %y %div = fdiv fast <4 x float> %x, %y
ret <4 x float> %div ret <4 x float> %div
@ -816,10 +812,11 @@ define <8 x float> @v8f32_one_step(<8 x float> %x) #1 {
; ;
; HASWELL-LABEL: v8f32_one_step: ; HASWELL-LABEL: v8f32_one_step:
; HASWELL: # %bb.0: ; HASWELL: # %bb.0:
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 ; HASWELL-NEXT: vrcpps %ymm0, %ymm2
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2 ; HASWELL-NEXT: vfmsub231ps {{.*#+}} ymm1 = (ymm2 * ymm0) - ymm1
; HASWELL-NEXT: vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1 ; HASWELL-NEXT: vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm2) + ymm2
; HASWELL-NEXT: vmovaps %ymm1, %ymm0
; HASWELL-NEXT: retq ; HASWELL-NEXT: retq
; ;
; HASWELL-NO-FMA-LABEL: v8f32_one_step: ; HASWELL-NO-FMA-LABEL: v8f32_one_step:
@ -834,10 +831,11 @@ define <8 x float> @v8f32_one_step(<8 x float> %x) #1 {
; ;
; KNL-LABEL: v8f32_one_step: ; KNL-LABEL: v8f32_one_step:
; KNL: # %bb.0: ; KNL: # %bb.0:
; KNL-NEXT: vrcpps %ymm0, %ymm1 ; KNL-NEXT: vrcpps %ymm0, %ymm2
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; KNL-NEXT: vbroadcastss {{.*#+}} ymm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; KNL-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2 ; KNL-NEXT: vfmsub231ps {{.*#+}} ymm1 = (ymm2 * ymm0) - ymm1
; KNL-NEXT: vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1 ; KNL-NEXT: vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm2) + ymm2
; KNL-NEXT: vmovaps %ymm1, %ymm0
; KNL-NEXT: retq ; KNL-NEXT: retq
; ;
; SKX-LABEL: v8f32_one_step: ; SKX-LABEL: v8f32_one_step:

32
llvm/test/CodeGen/X86/recip-fastmath2.ll
View File

@ -530,10 +530,10 @@ define <4 x float> @v4f32_one_step_2_divs(<4 x float> %x) #1 {
; HASWELL: # %bb.0: ; HASWELL: # %bb.0:
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 ; HASWELL-NEXT: vrcpps %xmm0, %xmm1
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT: vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - xmm2 ; HASWELL-NEXT: vfmsub231ps {{.*#+}} xmm2 = (xmm1 * xmm0) - xmm2
; HASWELL-NEXT: vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1 ; HASWELL-NEXT: vfnmadd132ps {{.*#+}} xmm2 = -(xmm2 * xmm1) + xmm1
; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 ; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm2, %xmm0
; HASWELL-NEXT: vmulps %xmm0, %xmm1, %xmm0 ; HASWELL-NEXT: vmulps %xmm2, %xmm0, %xmm0
; HASWELL-NEXT: retq ; HASWELL-NEXT: retq
; ;
; HASWELL-NO-FMA-LABEL: v4f32_one_step_2_divs: ; HASWELL-NO-FMA-LABEL: v4f32_one_step_2_divs:
@ -552,10 +552,10 @@ define <4 x float> @v4f32_one_step_2_divs(<4 x float> %x) #1 {
; KNL: # %bb.0: ; KNL: # %bb.0:
; KNL-NEXT: vrcpps %xmm0, %xmm1 ; KNL-NEXT: vrcpps %xmm0, %xmm1
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; KNL-NEXT: vfmsub213ps {{.*#+}} xmm0 = (xmm1 * xmm0) - xmm2 ; KNL-NEXT: vfmsub231ps {{.*#+}} xmm2 = (xmm1 * xmm0) - xmm2
; KNL-NEXT: vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1 ; KNL-NEXT: vfnmadd132ps {{.*#+}} xmm2 = -(xmm2 * xmm1) + xmm1
; KNL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 ; KNL-NEXT: vmulps {{.*}}(%rip), %xmm2, %xmm0
; KNL-NEXT: vmulps %xmm0, %xmm1, %xmm0 ; KNL-NEXT: vmulps %xmm2, %xmm0, %xmm0
; KNL-NEXT: retq ; KNL-NEXT: retq
; ;
; SKX-LABEL: v4f32_one_step_2_divs: ; SKX-LABEL: v4f32_one_step_2_divs:
@ -892,10 +892,10 @@ define <8 x float> @v8f32_one_step_2_divs(<8 x float> %x) #1 {
; HASWELL: # %bb.0: ; HASWELL: # %bb.0:
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 ; HASWELL-NEXT: vrcpps %ymm0, %ymm1
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; HASWELL-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2 ; HASWELL-NEXT: vfmsub231ps {{.*#+}} ymm2 = (ymm1 * ymm0) - ymm2
; HASWELL-NEXT: vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1 ; HASWELL-NEXT: vfnmadd132ps {{.*#+}} ymm2 = -(ymm2 * ymm1) + ymm1
; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 ; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm2, %ymm0
; HASWELL-NEXT: vmulps %ymm0, %ymm1, %ymm0 ; HASWELL-NEXT: vmulps %ymm2, %ymm0, %ymm0
; HASWELL-NEXT: retq ; HASWELL-NEXT: retq
; ;
; HASWELL-NO-FMA-LABEL: v8f32_one_step_2_divs: ; HASWELL-NO-FMA-LABEL: v8f32_one_step_2_divs:
@ -914,10 +914,10 @@ define <8 x float> @v8f32_one_step_2_divs(<8 x float> %x) #1 {
; KNL: # %bb.0: ; KNL: # %bb.0:
; KNL-NEXT: vrcpps %ymm0, %ymm1 ; KNL-NEXT: vrcpps %ymm0, %ymm1
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0] ; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; KNL-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2 ; KNL-NEXT: vfmsub231ps {{.*#+}} ymm2 = (ymm1 * ymm0) - ymm2
; KNL-NEXT: vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1 ; KNL-NEXT: vfnmadd132ps {{.*#+}} ymm2 = -(ymm2 * ymm1) + ymm1
; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 ; KNL-NEXT: vmulps {{.*}}(%rip), %ymm2, %ymm0
; KNL-NEXT: vmulps %ymm0, %ymm1, %ymm0 ; KNL-NEXT: vmulps %ymm2, %ymm0, %ymm0
; KNL-NEXT: retq ; KNL-NEXT: retq
; ;
; SKX-LABEL: v8f32_one_step_2_divs: ; SKX-LABEL: v8f32_one_step_2_divs:

12
llvm/test/CodeGen/X86/sqrt-fastmath.ll
View File

@ -328,10 +328,10 @@ define <4 x float> @v4f32_estimate(<4 x float> %x) #1 {
; AVX512-NEXT: vrsqrtps %xmm0, %xmm1 ; AVX512-NEXT: vrsqrtps %xmm0, %xmm1
; AVX512-NEXT: vmulps %xmm1, %xmm0, %xmm0 ; AVX512-NEXT: vmulps %xmm1, %xmm0, %xmm0
; AVX512-NEXT: vbroadcastss {{.*#+}} xmm2 = [-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0] ; AVX512-NEXT: vbroadcastss {{.*#+}} xmm2 = [-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0]
; AVX512-NEXT: vfmadd213ps {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2 ; AVX512-NEXT: vfmadd231ps {{.*#+}} xmm2 = (xmm1 * xmm0) + xmm2
; AVX512-NEXT: vbroadcastss {{.*#+}} xmm2 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1] ; AVX512-NEXT: vbroadcastss {{.*#+}} xmm0 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1]
; AVX512-NEXT: vmulps %xmm2, %xmm1, %xmm1
; AVX512-NEXT: vmulps %xmm0, %xmm1, %xmm0 ; AVX512-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX512-NEXT: vmulps %xmm2, %xmm0, %xmm0
; AVX512-NEXT: retq ; AVX512-NEXT: retq
%sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x) %sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
@ -401,10 +401,10 @@ define <8 x float> @v8f32_estimate(<8 x float> %x) #1 {
; AVX512-NEXT: vrsqrtps %ymm0, %ymm1 ; AVX512-NEXT: vrsqrtps %ymm0, %ymm1
; AVX512-NEXT: vmulps %ymm1, %ymm0, %ymm0 ; AVX512-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vbroadcastss {{.*#+}} ymm2 = [-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0] ; AVX512-NEXT: vbroadcastss {{.*#+}} ymm2 = [-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0,-3.0E+0]
; AVX512-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2 ; AVX512-NEXT: vfmadd231ps {{.*#+}} ymm2 = (ymm1 * ymm0) + ymm2
; AVX512-NEXT: vbroadcastss {{.*#+}} ymm2 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1] ; AVX512-NEXT: vbroadcastss {{.*#+}} ymm0 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1]
; AVX512-NEXT: vmulps %ymm2, %ymm1, %ymm1
; AVX512-NEXT: vmulps %ymm0, %ymm1, %ymm0 ; AVX512-NEXT: vmulps %ymm0, %ymm1, %ymm0
; AVX512-NEXT: vmulps %ymm2, %ymm0, %ymm0
; AVX512-NEXT: retq ; AVX512-NEXT: retq
%sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x) %sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x)
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt