Commit b6e27961 authored by Craig Topper's avatar Craig Topper
Browse files

[X86][TwoAddressInstructionPass] Teach tryInstructionCommute to continue... 

[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
parent 211fb91f

llvm/lib/CodeGen/TwoAddressInstructionPass.cpp

+11 −14
Original line number Diff line number Diff line
@@ -1238,8 +1238,9 @@ bool TwoAddressInstructionPass::tryInstructionCommute(MachineInstr *MI, 
                                        Dist)) {

      MadeChange = true;

      ++NumCommuted;

      if (AggressiveCommute) {

      if (AggressiveCommute)

        ++NumAggrCommuted;



      // There might be more than two commutable operands, update BaseOp and

      // continue scanning.

      // FIXME: This assumes that the new instruction's operands are in the
@@ -1249,10 +1250,6 @@ bool TwoAddressInstructionPass::tryInstructionCommute(MachineInstr *MI, 
      // Resamples OpsNum in case the number of operands was reduced. This

      // happens with X86.

      OpsNum = MI->getDesc().getNumOperands();

        continue;

      }

      // If this was a commute based on kill, we won't do better continuing.

      return MadeChange;

    }

  }

  return MadeChange;

llvm/test/CodeGen/X86/fma-commute-loop.ll

+11 −13
Original line number Diff line number Diff line
@@ -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:    vxorpd %xmm1, %xmm1, %xmm1

; CHECK-NEXT:    vxorpd %xmm2, %xmm2, %xmm2

; CHECK-NEXT:    vxorpd %xmm3, %xmm3, %xmm3

; CHECK-NEXT:    vxorpd %xmm4, %xmm4, %xmm4

; CHECK-NEXT:    vxorpd %xmm5, %xmm5, %xmm5

; CHECK-NEXT:    vxorpd %xmm3, %xmm3, %xmm3

; CHECK-NEXT:    .p2align 4, 0x90

; CHECK-NEXT:  LBB0_1: ## %bb15

; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1

; CHECK-NEXT:    vmovapd %zmm5, %zmm6

; CHECK-NEXT:    vmovapd %zmm4, %zmm7

; CHECK-NEXT:    vmovupd (%rax,%r11,8), %zmm4

; CHECK-NEXT:    vmovupd (%rax,%r13,8), %zmm5

; CHECK-NEXT:    vmovupd (%rax,%r11,8), %zmm6

; CHECK-NEXT:    vmovupd (%rax,%r13,8), %zmm7

; CHECK-NEXT:    vmovupd (%rax,%r12,8), %zmm8

; CHECK-NEXT:    vbroadcastsd (%r15,%rbx,8), %zmm9

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm0 = (zmm4 * zmm9) + zmm0

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm1 = (zmm5 * zmm9) + zmm1

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm0 = (zmm6 * zmm9) + zmm0

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm1 = (zmm7 * zmm9) + zmm1

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm2 = (zmm8 * zmm9) + zmm2

; CHECK-NEXT:    vbroadcastsd (%r14,%rbx,8), %zmm9

; CHECK-NEXT:    vfmadd213pd {{.*#+}} zmm4 = (zmm9 * zmm4) + zmm7

; CHECK-NEXT:    vfmadd213pd {{.*#+}} zmm5 = (zmm9 * zmm5) + zmm6

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm3 = (zmm8 * zmm9) + zmm3

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm3 = (zmm9 * zmm6) + zmm3

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm4 = (zmm9 * zmm7) + zmm4

; CHECK-NEXT:    vfmadd231pd {{.*#+}} zmm5 = (zmm8 * zmm9) + zmm5

; CHECK-NEXT:    incq %rbx

; CHECK-NEXT:    cmpq %rbx, %r10

; 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 %zmm1, (%rsi)

; CHECK-NEXT:    vmovapd %zmm2, (%rdx)

; CHECK-NEXT:    vmovapd %zmm4, (%rcx)

; CHECK-NEXT:    vmovapd %zmm5, (%r8)

; CHECK-NEXT:    vmovapd %zmm3, (%r9)

; CHECK-NEXT:    vmovapd %zmm3, (%rcx)

; CHECK-NEXT:    vmovapd %zmm4, (%r8)

; CHECK-NEXT:    vmovapd %zmm5, (%r9)

; CHECK-NEXT:    popq %rbx

; CHECK-NEXT:    popq %r12

; CHECK-NEXT:    popq %r13

llvm/test/CodeGen/X86/recip-fastmath.ll

+32 −34
Original line number Diff line number Diff line
@@ -144,9 +144,8 @@ define float @f32_one_step_variables(float %x, float %y) #1 { 
; FMA-RECIP:       # %bb.0:

; FMA-RECIP-NEXT:    vrcpss %xmm1, %xmm1, %xmm2

; FMA-RECIP-NEXT:    vmulss %xmm2, %xmm0, %xmm3

; FMA-RECIP-NEXT:    vfmsub213ss {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0

; FMA-RECIP-NEXT:    vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3

; FMA-RECIP-NEXT:    vmovaps %xmm2, %xmm0

; FMA-RECIP-NEXT:    vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0

; FMA-RECIP-NEXT:    vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3

; FMA-RECIP-NEXT:    retq

;

; 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-NEXT:    vrcpss %xmm1, %xmm1, %xmm2

; HASWELL-NEXT:    vmulss %xmm2, %xmm0, %xmm3

; HASWELL-NEXT:    vfmsub213ss {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0

; HASWELL-NEXT:    vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3

; HASWELL-NEXT:    vmovaps %xmm2, %xmm0

; HASWELL-NEXT:    vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0

; HASWELL-NEXT:    vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3

; HASWELL-NEXT:    retq

;

; 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-NEXT:    vrcpss %xmm1, %xmm1, %xmm2

; AVX512-NEXT:    vmulss %xmm2, %xmm0, %xmm3

; AVX512-NEXT:    vfmsub213ss {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0

; AVX512-NEXT:    vfnmadd213ss {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3

; AVX512-NEXT:    vmovaps %xmm2, %xmm0

; AVX512-NEXT:    vfmsub231ss {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0

; AVX512-NEXT:    vfnmadd213ss {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3

; AVX512-NEXT:    retq

  %div = fdiv fast float %x, %y

  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:       # %bb.0:

; HASWELL-NEXT:    vrcpps %xmm0, %xmm1

; 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:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1

; HASWELL-NEXT:    vrcpps %xmm0, %xmm2

; HASWELL-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]

; HASWELL-NEXT:    vfmsub231ps {{.*#+}} xmm1 = (xmm2 * xmm0) - xmm1

; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} xmm1 = -(xmm1 * xmm2) + xmm2

; HASWELL-NEXT:    vmovaps %xmm1, %xmm0

; HASWELL-NEXT:    retq

;

; 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:       # %bb.0:

; KNL-NEXT:    vrcpps %xmm0, %xmm1

; 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:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1

; KNL-NEXT:    vrcpps %xmm0, %xmm2

; KNL-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]

; KNL-NEXT:    vfmsub231ps {{.*#+}} xmm1 = (xmm2 * xmm0) - xmm1

; KNL-NEXT:    vfnmadd132ps {{.*#+}} xmm1 = -(xmm1 * xmm2) + xmm2

; KNL-NEXT:    vmovaps %xmm1, %xmm0

; KNL-NEXT:    retq

;

; 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-NEXT:    vrcpps %xmm1, %xmm2

; FMA-RECIP-NEXT:    vmulps %xmm2, %xmm0, %xmm3

; FMA-RECIP-NEXT:    vfmsub213ps {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0

; FMA-RECIP-NEXT:    vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3

; FMA-RECIP-NEXT:    vmovaps %xmm2, %xmm0

; FMA-RECIP-NEXT:    vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0

; FMA-RECIP-NEXT:    vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3

; FMA-RECIP-NEXT:    retq

;

; 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-NEXT:    vrcpps %xmm1, %xmm2

; HASWELL-NEXT:    vmulps %xmm2, %xmm0, %xmm3

; HASWELL-NEXT:    vfmsub213ps {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0

; HASWELL-NEXT:    vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3

; HASWELL-NEXT:    vmovaps %xmm2, %xmm0

; HASWELL-NEXT:    vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0

; HASWELL-NEXT:    vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3

; HASWELL-NEXT:    retq

;

; 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-NEXT:    vrcpps %xmm1, %xmm2

; AVX512-NEXT:    vmulps %xmm2, %xmm0, %xmm3

; AVX512-NEXT:    vfmsub213ps {{.*#+}} xmm1 = (xmm3 * xmm1) - xmm0

; AVX512-NEXT:    vfnmadd213ps {{.*#+}} xmm2 = -(xmm1 * xmm2) + xmm3

; AVX512-NEXT:    vmovaps %xmm2, %xmm0

; AVX512-NEXT:    vfmsub231ps {{.*#+}} xmm0 = (xmm3 * xmm1) - xmm0

; AVX512-NEXT:    vfnmadd213ps {{.*#+}} xmm0 = -(xmm2 * xmm0) + xmm3

; AVX512-NEXT:    retq

  %div = fdiv fast <4 x float> %x, %y

  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:       # %bb.0:

; 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:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2

; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1

; HASWELL-NEXT:    vrcpps %ymm0, %ymm2

; 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:    vfmsub231ps {{.*#+}} ymm1 = (ymm2 * ymm0) - ymm1

; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm2) + ymm2

; HASWELL-NEXT:    vmovaps %ymm1, %ymm0

; HASWELL-NEXT:    retq

;

; 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:       # %bb.0:

; 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:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2

; KNL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1

; KNL-NEXT:    vrcpps %ymm0, %ymm2

; 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:    vfmsub231ps {{.*#+}} ymm1 = (ymm2 * ymm0) - ymm1

; KNL-NEXT:    vfnmadd132ps {{.*#+}} ymm1 = -(ymm1 * ymm2) + ymm2

; KNL-NEXT:    vmovaps %ymm1, %ymm0

; KNL-NEXT:    retq

;

; SKX-LABEL: v8f32_one_step:

llvm/test/CodeGen/X86/recip-fastmath2.ll

+16 −16
Original line number Diff line number Diff line
@@ -530,10 +530,10 @@ define <4 x float> @v4f32_one_step_2_divs(<4 x float> %x) #1 { 
; HASWELL:       # %bb.0:

; HASWELL-NEXT:    vrcpps %xmm0, %xmm1

; 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:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1

; HASWELL-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm1

; HASWELL-NEXT:    vmulps %xmm0, %xmm1, %xmm0

; HASWELL-NEXT:    vfmsub231ps {{.*#+}} xmm2 = (xmm1 * xmm0) - xmm2

; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} xmm2 = -(xmm2 * xmm1) + xmm1

; HASWELL-NEXT:    vmulps {{.*}}(%rip), %xmm2, %xmm0

; HASWELL-NEXT:    vmulps %xmm2, %xmm0, %xmm0

; HASWELL-NEXT:    retq

;

; 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-NEXT:    vrcpps %xmm0, %xmm1

; 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:    vfnmadd132ps {{.*#+}} xmm0 = -(xmm0 * xmm1) + xmm1

; KNL-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm1

; KNL-NEXT:    vmulps %xmm0, %xmm1, %xmm0

; KNL-NEXT:    vfmsub231ps {{.*#+}} xmm2 = (xmm1 * xmm0) - xmm2

; KNL-NEXT:    vfnmadd132ps {{.*#+}} xmm2 = -(xmm2 * xmm1) + xmm1

; KNL-NEXT:    vmulps {{.*}}(%rip), %xmm2, %xmm0

; KNL-NEXT:    vmulps %xmm2, %xmm0, %xmm0

; KNL-NEXT:    retq

;

; 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-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:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2

; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1

; HASWELL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm1

; HASWELL-NEXT:    vmulps %ymm0, %ymm1, %ymm0

; HASWELL-NEXT:    vfmsub231ps {{.*#+}} ymm2 = (ymm1 * ymm0) - ymm2

; HASWELL-NEXT:    vfnmadd132ps {{.*#+}} ymm2 = -(ymm2 * ymm1) + ymm1

; HASWELL-NEXT:    vmulps {{.*}}(%rip), %ymm2, %ymm0

; HASWELL-NEXT:    vmulps %ymm2, %ymm0, %ymm0

; HASWELL-NEXT:    retq

;

; 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-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:    vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2

; KNL-NEXT:    vfnmadd132ps {{.*#+}} ymm0 = -(ymm0 * ymm1) + ymm1

; KNL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm1

; KNL-NEXT:    vmulps %ymm0, %ymm1, %ymm0

; KNL-NEXT:    vfmsub231ps {{.*#+}} ymm2 = (ymm1 * ymm0) - ymm2

; KNL-NEXT:    vfnmadd132ps {{.*#+}} ymm2 = -(ymm2 * ymm1) + ymm1

; KNL-NEXT:    vmulps {{.*}}(%rip), %ymm2, %ymm0

; KNL-NEXT:    vmulps %ymm2, %ymm0, %ymm0

; KNL-NEXT:    retq

;

; SKX-LABEL: v8f32_one_step_2_divs:

llvm/test/CodeGen/X86/sqrt-fastmath.ll

+6 −6
Original line number Diff line number Diff line
@@ -328,10 +328,10 @@ define <4 x float> @v4f32_estimate(<4 x float> %x) #1 { 
; AVX512-NEXT:    vrsqrtps %xmm0, %xmm1

; AVX512-NEXT:    vmulps %xmm1, %xmm0, %xmm0

; 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:    vbroadcastss {{.*#+}} xmm2 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1]

; AVX512-NEXT:    vmulps %xmm2, %xmm1, %xmm1

; AVX512-NEXT:    vfmadd231ps {{.*#+}} xmm2 = (xmm1 * xmm0) + xmm2

; AVX512-NEXT:    vbroadcastss {{.*#+}} xmm0 = [-5.0E-1,-5.0E-1,-5.0E-1,-5.0E-1]

; AVX512-NEXT:    vmulps %xmm0, %xmm1, %xmm0

; AVX512-NEXT:    vmulps %xmm2, %xmm0, %xmm0

; AVX512-NEXT:    retq

  %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
@@ -401,10 +401,10 @@ define <8 x float> @v8f32_estimate(<8 x float> %x) #1 { 
; AVX512-NEXT:    vrsqrtps %ymm0, %ymm1

; 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:    vfmadd213ps {{.*#+}} ymm0 = (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:    vmulps %ymm2, %ymm1, %ymm1

; AVX512-NEXT:    vfmadd231ps {{.*#+}} ymm2 = (ymm1 * ymm0) + ymm2

; 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 %ymm0, %ymm1, %ymm0

; AVX512-NEXT:    vmulps %ymm2, %ymm0, %ymm0

; AVX512-NEXT:    retq

  %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