[X86][SSE] Add target cpu specific reciprocal tests

As discussed on D26855, check individual cpu targets as part of the investigation into moving more combines to MachineCombiner

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294128 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/CodeGen/X86/recip-fastmath.ll b/test/CodeGen/X86/recip-fastmath.ll
index 0a99254cd6253350b33d3b560c38516c9e1fddb5..8425a5c445c1d9c264a54d7d81c714a3a58e8ab7 100644 (file)
--- a/test/CodeGen/X86/recip-fastmath.ll
+++ b/test/CodeGen/X86/recip-fastmath.ll
@@ -1,6 +1,11 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=CHECK --check-prefix=AVX
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE --check-prefix=SSE-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=BTVER2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge| FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=SANDY
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell  | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=HASWELL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl      | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=KNL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx      | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=SKX
 
 ; If the target's divss/divps instructions are substantially
 ; slower than rcpss/rcpps with a Newton-Raphson refinement,
@@ -39,15 +44,49 @@ define float @f32_one_step(float %x) #1 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: f32_one_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
-; AVX-NEXT:    vmulss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
-; AVX-NEXT:    vsubss %xmm0, %xmm2, %xmm0
-; AVX-NEXT:    vmulss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: f32_one_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; AVX-RECIP-NEXT:    vsubss %xmm0, %xmm2, %xmm0
+; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: f32_one_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubss %xmm0, %xmm2, %xmm0
+; BTVER2-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: f32_one_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; SANDY-NEXT:    vsubss %xmm0, %xmm2, %xmm0
+; SANDY-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: f32_one_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; HASWELL-NEXT:    vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; HASWELL-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: f32_one_step:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm1
+; AVX512-NEXT:    vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; AVX512-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm0
+; AVX512-NEXT:    retq
   %div = fdiv fast float 1.0, %x
   ret float %div
 }
@@ -70,19 +109,69 @@ define float @f32_two_step(float %x) #2 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: f32_two_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
-; AVX-NEXT:    vmulss %xmm1, %xmm0, %xmm2
-; AVX-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
-; AVX-NEXT:    vsubss %xmm2, %xmm3, %xmm2
-; AVX-NEXT:    vmulss %xmm2, %xmm1, %xmm2
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vmulss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vsubss %xmm0, %xmm3, %xmm0
-; AVX-NEXT:    vmulss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: f32_two_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm2
+; AVX-RECIP-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; AVX-RECIP-NEXT:    vsubss %xmm2, %xmm3, %xmm2
+; AVX-RECIP-NEXT:    vmulss %xmm2, %xmm1, %xmm2
+; AVX-RECIP-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vsubss %xmm0, %xmm3, %xmm0
+; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: f32_two_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm2
+; BTVER2-NEXT:    vsubss %xmm2, %xmm3, %xmm2
+; BTVER2-NEXT:    vmulss %xmm2, %xmm1, %xmm2
+; BTVER2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubss %xmm0, %xmm3, %xmm0
+; BTVER2-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: f32_two_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm2
+; SANDY-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; SANDY-NEXT:    vsubss %xmm2, %xmm3, %xmm2
+; SANDY-NEXT:    vmulss %xmm2, %xmm1, %xmm2
+; SANDY-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vsubss %xmm0, %xmm3, %xmm0
+; SANDY-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: f32_two_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; HASWELL-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; HASWELL-NEXT:    vmovaps %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ss %xmm2, %xmm0, %xmm3
+; HASWELL-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ss %xmm2, %xmm3, %xmm0
+; HASWELL-NEXT:    vfmadd132ss %xmm3, %xmm3, %xmm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: f32_two_step:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm1
+; AVX512-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; AVX512-NEXT:    vmovaps %xmm1, %xmm3
+; AVX512-NEXT:    vfnmadd213ss %xmm2, %xmm0, %xmm3
+; AVX512-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm3
+; AVX512-NEXT:    vfnmadd213ss %xmm2, %xmm3, %xmm0
+; AVX512-NEXT:    vfmadd132ss %xmm3, %xmm3, %xmm0
+; AVX512-NEXT:    retq
   %div = fdiv fast float 1.0, %x
   ret float %div
 }
@@ -95,11 +184,35 @@ define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v4f32_no_estimate:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vdivps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v4f32_no_estimate:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vdivps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v4f32_no_estimate:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vdivps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v4f32_no_estimate:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vdivps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v4f32_no_estimate:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm1
+; HASWELL-NEXT:    vdivps %xmm0, %xmm1, %xmm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: v4f32_no_estimate:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vbroadcastss {{.*}}(%rip), %xmm1
+; AVX512-NEXT:    vdivps %xmm0, %xmm1, %xmm0
+; AVX512-NEXT:    retq
   %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
   ret <4 x float> %div
 }
@@ -116,15 +229,58 @@ define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v4f32_one_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %xmm0, %xmm1
-; AVX-NEXT:    vmulps %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %xmm0, %xmm2, %xmm0
-; AVX-NEXT:    vmulps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v4f32_one_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %xmm0, %xmm2, %xmm0
+; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v4f32_one_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %xmm0, %xmm1
+; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubps %xmm0, %xmm2, %xmm0
+; BTVER2-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v4f32_one_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %xmm0, %xmm1
+; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %xmm0, %xmm2, %xmm0
+; SANDY-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v4f32_one_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %xmm0, %xmm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; HASWELL-NEXT:    vfnmadd213ps %xmm2, %xmm1, %xmm0
+; HASWELL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v4f32_one_step:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %xmm0, %xmm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; KNL-NEXT:    vfnmadd213ps %xmm2, %xmm1, %xmm0
+; KNL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v4f32_one_step:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %xmm0, %xmm1
+; SKX-NEXT:    vfnmadd213ps {{.*}}(%rip){1to4}, %xmm1, %xmm0
+; SKX-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm0
+; SKX-NEXT:    retq
   %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
   ret <4 x float> %div
 }
@@ -147,19 +303,80 @@ define <4 x float> @v4f32_two_step(<4 x float> %x) #2 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v4f32_two_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %xmm0, %xmm1
-; AVX-NEXT:    vmulps %xmm1, %xmm0, %xmm2
-; AVX-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %xmm2, %xmm3, %xmm2
-; AVX-NEXT:    vmulps %xmm2, %xmm1, %xmm2
-; AVX-NEXT:    vaddps %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vmulps %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vsubps %xmm0, %xmm3, %xmm0
-; AVX-NEXT:    vmulps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v4f32_two_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm2
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %xmm2, %xmm3, %xmm2
+; AVX-RECIP-NEXT:    vmulps %xmm2, %xmm1, %xmm2
+; AVX-RECIP-NEXT:    vaddps %xmm2, %xmm1, %xmm1
+; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vsubps %xmm0, %xmm3, %xmm0
+; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v4f32_two_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %xmm0, %xmm1
+; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm2
+; BTVER2-NEXT:    vsubps %xmm2, %xmm3, %xmm2
+; BTVER2-NEXT:    vmulps %xmm2, %xmm1, %xmm2
+; BTVER2-NEXT:    vaddps %xmm2, %xmm1, %xmm1
+; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubps %xmm0, %xmm3, %xmm0
+; BTVER2-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v4f32_two_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %xmm0, %xmm1
+; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm2
+; SANDY-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %xmm2, %xmm3, %xmm2
+; SANDY-NEXT:    vmulps %xmm2, %xmm1, %xmm2
+; SANDY-NEXT:    vaddps %xmm2, %xmm1, %xmm1
+; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vsubps %xmm0, %xmm3, %xmm0
+; SANDY-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v4f32_two_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %xmm0, %xmm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; HASWELL-NEXT:    vmovaps %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ps %xmm2, %xmm0, %xmm3
+; HASWELL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ps %xmm2, %xmm3, %xmm0
+; HASWELL-NEXT:    vfmadd132ps %xmm3, %xmm3, %xmm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v4f32_two_step:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %xmm0, %xmm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; KNL-NEXT:    vmovaps %xmm1, %xmm3
+; KNL-NEXT:    vfnmadd213ps %xmm2, %xmm0, %xmm3
+; KNL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm3
+; KNL-NEXT:    vfnmadd213ps %xmm2, %xmm3, %xmm0
+; KNL-NEXT:    vfmadd132ps %xmm3, %xmm3, %xmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v4f32_two_step:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %xmm0, %xmm1
+; SKX-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; SKX-NEXT:    vmovaps %xmm1, %xmm3
+; SKX-NEXT:    vfnmadd213ps %xmm2, %xmm0, %xmm3
+; SKX-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm3
+; SKX-NEXT:    vfnmadd213ps %xmm2, %xmm3, %xmm0
+; SKX-NEXT:    vfmadd132ps %xmm3, %xmm3, %xmm0
+; SKX-NEXT:    retq
   %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
   ret <4 x float> %div
 }
@@ -175,11 +392,35 @@ define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 {
 ; SSE-NEXT:    movaps %xmm2, %xmm1
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_no_estimate:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vdivps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_no_estimate:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vdivps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_no_estimate:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vdivps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_no_estimate:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vdivps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_no_estimate:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm1
+; HASWELL-NEXT:    vdivps %ymm0, %ymm1, %ymm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: v8f32_no_estimate:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vbroadcastss {{.*}}(%rip), %ymm1
+; AVX512-NEXT:    vdivps %ymm0, %ymm1, %ymm0
+; AVX512-NEXT:    retq
   %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>, %x
   ret <8 x float> %div
 }
@@ -203,15 +444,58 @@ define <8 x float> @v8f32_one_step(<8 x float> %x) #1 {
 ; SSE-NEXT:    movaps %xmm2, %xmm1
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_one_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %ymm0, %ymm1
-; AVX-NEXT:    vmulps %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %ymm0, %ymm2, %ymm0
-; AVX-NEXT:    vmulps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    vaddps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_one_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm1
+; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm2, %ymm0
+; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_one_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %ymm0, %ymm1
+; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; BTVER2-NEXT:    vsubps %ymm0, %ymm2, %ymm0
+; BTVER2-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_one_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %ymm0, %ymm1
+; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; SANDY-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %ymm0, %ymm2, %ymm0
+; SANDY-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_one_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %ymm0, %ymm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; HASWELL-NEXT:    vfnmadd213ps %ymm2, %ymm1, %ymm0
+; HASWELL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v8f32_one_step:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %ymm0, %ymm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; KNL-NEXT:    vfnmadd213ps %ymm2, %ymm1, %ymm0
+; KNL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v8f32_one_step:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %ymm0, %ymm1
+; SKX-NEXT:    vfnmadd213ps {{.*}}(%rip){1to8}, %ymm1, %ymm0
+; SKX-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm0
+; SKX-NEXT:    retq
   %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>, %x
   ret <8 x float> %div
 }
@@ -247,19 +531,80 @@ define <8 x float> @v8f32_two_step(<8 x float> %x) #2 {
 ; SSE-NEXT:    movaps %xmm3, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_two_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %ymm0, %ymm1
-; AVX-NEXT:    vmulps %ymm1, %ymm0, %ymm2
-; AVX-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %ymm2, %ymm3, %ymm2
-; AVX-NEXT:    vmulps %ymm2, %ymm1, %ymm2
-; AVX-NEXT:    vaddps %ymm2, %ymm1, %ymm1
-; AVX-NEXT:    vmulps %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vsubps %ymm0, %ymm3, %ymm0
-; AVX-NEXT:    vmulps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    vaddps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_two_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm1
+; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm2
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %ymm2, %ymm3, %ymm2
+; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm1, %ymm2
+; AVX-RECIP-NEXT:    vaddps %ymm2, %ymm1, %ymm1
+; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm3, %ymm0
+; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_two_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %ymm0, %ymm1
+; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm2
+; BTVER2-NEXT:    vsubps %ymm2, %ymm3, %ymm2
+; BTVER2-NEXT:    vmulps %ymm2, %ymm1, %ymm2
+; BTVER2-NEXT:    vaddps %ymm2, %ymm1, %ymm1
+; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; BTVER2-NEXT:    vsubps %ymm0, %ymm3, %ymm0
+; BTVER2-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_two_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %ymm0, %ymm1
+; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm2
+; SANDY-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %ymm2, %ymm3, %ymm2
+; SANDY-NEXT:    vmulps %ymm2, %ymm1, %ymm2
+; SANDY-NEXT:    vaddps %ymm2, %ymm1, %ymm1
+; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; SANDY-NEXT:    vsubps %ymm0, %ymm3, %ymm0
+; SANDY-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_two_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %ymm0, %ymm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; HASWELL-NEXT:    vmovaps %ymm1, %ymm3
+; HASWELL-NEXT:    vfnmadd213ps %ymm2, %ymm0, %ymm3
+; HASWELL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm3
+; HASWELL-NEXT:    vfnmadd213ps %ymm2, %ymm3, %ymm0
+; HASWELL-NEXT:    vfmadd132ps %ymm3, %ymm3, %ymm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v8f32_two_step:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %ymm0, %ymm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; KNL-NEXT:    vmovaps %ymm1, %ymm3
+; KNL-NEXT:    vfnmadd213ps %ymm2, %ymm0, %ymm3
+; KNL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm3
+; KNL-NEXT:    vfnmadd213ps %ymm2, %ymm3, %ymm0
+; KNL-NEXT:    vfmadd132ps %ymm3, %ymm3, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v8f32_two_step:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %ymm0, %ymm1
+; SKX-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; SKX-NEXT:    vmovaps %ymm1, %ymm3
+; SKX-NEXT:    vfnmadd213ps %ymm2, %ymm0, %ymm3
+; SKX-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm3
+; SKX-NEXT:    vfnmadd213ps %ymm2, %ymm3, %ymm0
+; SKX-NEXT:    vfmadd132ps %ymm3, %ymm3, %ymm0
+; SKX-NEXT:    retq
   %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>, %x
   ret <8 x float> %div
 }

diff --git a/test/CodeGen/X86/recip-fastmath2.ll b/test/CodeGen/X86/recip-fastmath2.ll
index 0788b036cc5214d9a81cfd8fc1c9672f54146709..5eb731b1c9bb217d37288f7096e62685ce1e2abf 100644 (file)
--- a/test/CodeGen/X86/recip-fastmath2.ll
+++ b/test/CodeGen/X86/recip-fastmath2.ll
@@ -1,6 +1,11 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=CHECK --check-prefix=AVX
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE --check-prefix=SSE-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=BTVER2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge| FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=SANDY
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell  | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=HASWELL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl      | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=KNL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx      | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=SKX
 
 ; It's the extra tests coverage for recip as discussed on D26855.
 
@@ -11,11 +16,35 @@ define float @f32_no_step_2(float %x) #3 {
 ; SSE-NEXT:    mulss {{.*}}(%rip), %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: f32_no_step_2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpss %xmm0, %xmm0, %xmm0
-; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: f32_no_step_2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: f32_no_step_2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm0
+; BTVER2-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: f32_no_step_2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm0
+; SANDY-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: f32_no_step_2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm0
+; HASWELL-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: f32_no_step_2:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm0
+; AVX512-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; AVX512-NEXT:    retq
   %div = fdiv fast float 1234.0, %x
   ret float %div
 }
@@ -33,16 +62,54 @@ define float @f32_one_step_2(float %x) #1 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: f32_one_step_2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
-; AVX-NEXT:    vmulss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
-; AVX-NEXT:    vsubss %xmm0, %xmm2, %xmm0
-; AVX-NEXT:    vmulss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: f32_one_step_2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; AVX-RECIP-NEXT:    vsubss %xmm0, %xmm2, %xmm0
+; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: f32_one_step_2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubss %xmm0, %xmm2, %xmm0
+; BTVER2-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: f32_one_step_2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; SANDY-NEXT:    vsubss %xmm0, %xmm2, %xmm0
+; SANDY-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: f32_one_step_2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; HASWELL-NEXT:    vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; HASWELL-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: f32_one_step_2:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm1
+; AVX512-NEXT:    vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; AVX512-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm0
+; AVX512-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; AVX512-NEXT:    retq
   %div = fdiv fast float 3456.0, %x
   ret float %div
 }
@@ -66,20 +133,74 @@ define float @f32_two_step_2(float %x) #2 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: f32_two_step_2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
-; AVX-NEXT:    vmulss %xmm1, %xmm0, %xmm2
-; AVX-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
-; AVX-NEXT:    vsubss %xmm2, %xmm3, %xmm2
-; AVX-NEXT:    vmulss %xmm2, %xmm1, %xmm2
-; AVX-NEXT:    vaddss %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vmulss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vsubss %xmm0, %xmm3, %xmm0
-; AVX-NEXT:    vmulss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: f32_two_step_2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm2
+; AVX-RECIP-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; AVX-RECIP-NEXT:    vsubss %xmm2, %xmm3, %xmm2
+; AVX-RECIP-NEXT:    vmulss %xmm2, %xmm1, %xmm2
+; AVX-RECIP-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; AVX-RECIP-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vsubss %xmm0, %xmm3, %xmm0
+; AVX-RECIP-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: f32_two_step_2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; BTVER2-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm2
+; BTVER2-NEXT:    vsubss %xmm2, %xmm3, %xmm2
+; BTVER2-NEXT:    vmulss %xmm2, %xmm1, %xmm2
+; BTVER2-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; BTVER2-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubss %xmm0, %xmm3, %xmm0
+; BTVER2-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: f32_two_step_2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm2
+; SANDY-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
+; SANDY-NEXT:    vsubss %xmm2, %xmm3, %xmm2
+; SANDY-NEXT:    vmulss %xmm2, %xmm1, %xmm2
+; SANDY-NEXT:    vaddss %xmm2, %xmm1, %xmm1
+; SANDY-NEXT:    vmulss %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vsubss %xmm0, %xmm3, %xmm0
+; SANDY-NEXT:    vmulss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddss %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: f32_two_step_2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpss %xmm0, %xmm0, %xmm1
+; HASWELL-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; HASWELL-NEXT:    vmovaps %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ss %xmm2, %xmm0, %xmm3
+; HASWELL-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ss %xmm2, %xmm3, %xmm0
+; HASWELL-NEXT:    vfmadd132ss %xmm3, %xmm3, %xmm0
+; HASWELL-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; HASWELL-NEXT:    retq
+;
+; AVX512-LABEL: f32_two_step_2:
+; AVX512:       # BB#0:
+; AVX512-NEXT:    vrcp14ss %xmm0, %xmm0, %xmm1
+; AVX512-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; AVX512-NEXT:    vmovaps %xmm1, %xmm3
+; AVX512-NEXT:    vfnmadd213ss %xmm2, %xmm0, %xmm3
+; AVX512-NEXT:    vfmadd132ss %xmm1, %xmm1, %xmm3
+; AVX512-NEXT:    vfnmadd213ss %xmm2, %xmm3, %xmm0
+; AVX512-NEXT:    vfmadd132ss %xmm3, %xmm3, %xmm0
+; AVX512-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
+; AVX512-NEXT:    retq
   %div = fdiv fast float 6789.0, %x
   ret float %div
 }
@@ -97,16 +218,64 @@ define <4 x float> @v4f32_one_step2(<4 x float> %x) #1 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v4f32_one_step2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %xmm0, %xmm1
-; AVX-NEXT:    vmulps %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %xmm0, %xmm2, %xmm0
-; AVX-NEXT:    vmulps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v4f32_one_step2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %xmm0, %xmm2, %xmm0
+; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v4f32_one_step2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %xmm0, %xmm1
+; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubps %xmm0, %xmm2, %xmm0
+; BTVER2-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v4f32_one_step2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %xmm0, %xmm1
+; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %xmm0, %xmm2, %xmm0
+; SANDY-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v4f32_one_step2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %xmm0, %xmm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; HASWELL-NEXT:    vfnmadd213ps %xmm2, %xmm1, %xmm0
+; HASWELL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v4f32_one_step2:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %xmm0, %xmm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; KNL-NEXT:    vfnmadd213ps %xmm2, %xmm1, %xmm0
+; KNL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm0
+; KNL-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v4f32_one_step2:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %xmm0, %xmm1
+; SKX-NEXT:    vfnmadd213ps {{.*}}(%rip){1to4}, %xmm1, %xmm0
+; SKX-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm0
+; SKX-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; SKX-NEXT:    retq
   %div = fdiv fast <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
   ret <4 x float> %div
 }
@@ -130,20 +299,86 @@ define <4 x float> @v4f32_two_step2(<4 x float> %x) #2 {
 ; SSE-NEXT:    movaps %xmm1, %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v4f32_two_step2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %xmm0, %xmm1
-; AVX-NEXT:    vmulps %xmm1, %xmm0, %xmm2
-; AVX-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %xmm2, %xmm3, %xmm2
-; AVX-NEXT:    vmulps %xmm2, %xmm1, %xmm2
-; AVX-NEXT:    vaddps %xmm2, %xmm1, %xmm1
-; AVX-NEXT:    vmulps %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vsubps %xmm0, %xmm3, %xmm0
-; AVX-NEXT:    vmulps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vaddps %xmm0, %xmm1, %xmm0
-; AVX-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v4f32_two_step2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %xmm0, %xmm1
+; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm2
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %xmm2, %xmm3, %xmm2
+; AVX-RECIP-NEXT:    vmulps %xmm2, %xmm1, %xmm2
+; AVX-RECIP-NEXT:    vaddps %xmm2, %xmm1, %xmm1
+; AVX-RECIP-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; AVX-RECIP-NEXT:    vsubps %xmm0, %xmm3, %xmm0
+; AVX-RECIP-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v4f32_two_step2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %xmm0, %xmm1
+; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm2
+; BTVER2-NEXT:    vsubps %xmm2, %xmm3, %xmm2
+; BTVER2-NEXT:    vmulps %xmm2, %xmm1, %xmm2
+; BTVER2-NEXT:    vaddps %xmm2, %xmm1, %xmm1
+; BTVER2-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; BTVER2-NEXT:    vsubps %xmm0, %xmm3, %xmm0
+; BTVER2-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; BTVER2-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v4f32_two_step2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %xmm0, %xmm1
+; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm2
+; SANDY-NEXT:    vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %xmm2, %xmm3, %xmm2
+; SANDY-NEXT:    vmulps %xmm2, %xmm1, %xmm2
+; SANDY-NEXT:    vaddps %xmm2, %xmm1, %xmm1
+; SANDY-NEXT:    vmulps %xmm1, %xmm0, %xmm0
+; SANDY-NEXT:    vsubps %xmm0, %xmm3, %xmm0
+; SANDY-NEXT:    vmulps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vaddps %xmm0, %xmm1, %xmm0
+; SANDY-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v4f32_two_step2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %xmm0, %xmm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; HASWELL-NEXT:    vmovaps %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ps %xmm2, %xmm0, %xmm3
+; HASWELL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm3
+; HASWELL-NEXT:    vfnmadd213ps %xmm2, %xmm3, %xmm0
+; HASWELL-NEXT:    vfmadd132ps %xmm3, %xmm3, %xmm0
+; HASWELL-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v4f32_two_step2:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %xmm0, %xmm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; KNL-NEXT:    vmovaps %xmm1, %xmm3
+; KNL-NEXT:    vfnmadd213ps %xmm2, %xmm0, %xmm3
+; KNL-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm3
+; KNL-NEXT:    vfnmadd213ps %xmm2, %xmm3, %xmm0
+; KNL-NEXT:    vfmadd132ps %xmm3, %xmm3, %xmm0
+; KNL-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v4f32_two_step2:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %xmm0, %xmm1
+; SKX-NEXT:    vbroadcastss {{.*}}(%rip), %xmm2
+; SKX-NEXT:    vmovaps %xmm1, %xmm3
+; SKX-NEXT:    vfnmadd213ps %xmm2, %xmm0, %xmm3
+; SKX-NEXT:    vfmadd132ps %xmm1, %xmm1, %xmm3
+; SKX-NEXT:    vfnmadd213ps %xmm2, %xmm3, %xmm0
+; SKX-NEXT:    vfmadd132ps %xmm3, %xmm3, %xmm0
+; SKX-NEXT:    vmulps {{.*}}(%rip), %xmm0, %xmm0
+; SKX-NEXT:    retq
   %div = fdiv fast <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
   ret <4 x float> %div
 }
@@ -169,16 +404,64 @@ define <8 x float> @v8f32_one_step2(<8 x float> %x) #1 {
 ; SSE-NEXT:    movaps %xmm3, %xmm1
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_one_step2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %ymm0, %ymm1
-; AVX-NEXT:    vmulps %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %ymm0, %ymm2, %ymm0
-; AVX-NEXT:    vmulps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    vaddps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_one_step2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm1
+; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm2, %ymm0
+; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_one_step2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %ymm0, %ymm1
+; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; BTVER2-NEXT:    vsubps %ymm0, %ymm2, %ymm0
+; BTVER2-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_one_step2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %ymm0, %ymm1
+; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; SANDY-NEXT:    vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %ymm0, %ymm2, %ymm0
+; SANDY-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_one_step2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %ymm0, %ymm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; HASWELL-NEXT:    vfnmadd213ps %ymm2, %ymm1, %ymm0
+; HASWELL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm0
+; HASWELL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v8f32_one_step2:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %ymm0, %ymm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; KNL-NEXT:    vfnmadd213ps %ymm2, %ymm1, %ymm0
+; KNL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm0
+; KNL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v8f32_one_step2:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %ymm0, %ymm1
+; SKX-NEXT:    vfnmadd213ps {{.*}}(%rip){1to8}, %ymm1, %ymm0
+; SKX-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm0
+; SKX-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; SKX-NEXT:    retq
   %div = fdiv fast <8 x float> <float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, float 8.0>, %x
   ret <8 x float> %div
 }
@@ -216,20 +499,86 @@ define <8 x float> @v8f32_two_step2(<8 x float> %x) #2 {
 ; SSE-NEXT:    movaps %xmm3, %xmm1
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_two_step2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %ymm0, %ymm1
-; AVX-NEXT:    vmulps %ymm1, %ymm0, %ymm2
-; AVX-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; AVX-NEXT:    vsubps %ymm2, %ymm3, %ymm2
-; AVX-NEXT:    vmulps %ymm2, %ymm1, %ymm2
-; AVX-NEXT:    vaddps %ymm2, %ymm1, %ymm1
-; AVX-NEXT:    vmulps %ymm1, %ymm0, %ymm0
-; AVX-NEXT:    vsubps %ymm0, %ymm3, %ymm0
-; AVX-NEXT:    vmulps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    vaddps %ymm0, %ymm1, %ymm0
-; AVX-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_two_step2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm1
+; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm2
+; AVX-RECIP-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; AVX-RECIP-NEXT:    vsubps %ymm2, %ymm3, %ymm2
+; AVX-RECIP-NEXT:    vmulps %ymm2, %ymm1, %ymm2
+; AVX-RECIP-NEXT:    vaddps %ymm2, %ymm1, %ymm1
+; AVX-RECIP-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; AVX-RECIP-NEXT:    vsubps %ymm0, %ymm3, %ymm0
+; AVX-RECIP-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_two_step2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; BTVER2-NEXT:    vrcpps %ymm0, %ymm1
+; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm2
+; BTVER2-NEXT:    vsubps %ymm2, %ymm3, %ymm2
+; BTVER2-NEXT:    vmulps %ymm2, %ymm1, %ymm2
+; BTVER2-NEXT:    vaddps %ymm2, %ymm1, %ymm1
+; BTVER2-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; BTVER2-NEXT:    vsubps %ymm0, %ymm3, %ymm0
+; BTVER2-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; BTVER2-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_two_step2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %ymm0, %ymm1
+; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm2
+; SANDY-NEXT:    vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SANDY-NEXT:    vsubps %ymm2, %ymm3, %ymm2
+; SANDY-NEXT:    vmulps %ymm2, %ymm1, %ymm2
+; SANDY-NEXT:    vaddps %ymm2, %ymm1, %ymm1
+; SANDY-NEXT:    vmulps %ymm1, %ymm0, %ymm0
+; SANDY-NEXT:    vsubps %ymm0, %ymm3, %ymm0
+; SANDY-NEXT:    vmulps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    vaddps %ymm0, %ymm1, %ymm0
+; SANDY-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_two_step2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %ymm0, %ymm1
+; HASWELL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; HASWELL-NEXT:    vmovaps %ymm1, %ymm3
+; HASWELL-NEXT:    vfnmadd213ps %ymm2, %ymm0, %ymm3
+; HASWELL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm3
+; HASWELL-NEXT:    vfnmadd213ps %ymm2, %ymm3, %ymm0
+; HASWELL-NEXT:    vfmadd132ps %ymm3, %ymm3, %ymm0
+; HASWELL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v8f32_two_step2:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %ymm0, %ymm1
+; KNL-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; KNL-NEXT:    vmovaps %ymm1, %ymm3
+; KNL-NEXT:    vfnmadd213ps %ymm2, %ymm0, %ymm3
+; KNL-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm3
+; KNL-NEXT:    vfnmadd213ps %ymm2, %ymm3, %ymm0
+; KNL-NEXT:    vfmadd132ps %ymm3, %ymm3, %ymm0
+; KNL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v8f32_two_step2:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %ymm0, %ymm1
+; SKX-NEXT:    vbroadcastss {{.*}}(%rip), %ymm2
+; SKX-NEXT:    vmovaps %ymm1, %ymm3
+; SKX-NEXT:    vfnmadd213ps %ymm2, %ymm0, %ymm3
+; SKX-NEXT:    vfmadd132ps %ymm1, %ymm1, %ymm3
+; SKX-NEXT:    vfnmadd213ps %ymm2, %ymm3, %ymm0
+; SKX-NEXT:    vfmadd132ps %ymm3, %ymm3, %ymm0
+; SKX-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; SKX-NEXT:    retq
   %div = fdiv fast <8 x float> <float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, float 8.0>, %x
   ret <8 x float> %div
 }
@@ -241,10 +590,35 @@ define <8 x float> @v8f32_no_step(<8 x float> %x) #3 {
 ; SSE-NEXT:    rcpps %xmm1, %xmm1
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_no_step:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %ymm0, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_no_step:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_no_step:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vrcpps %ymm0, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_no_step:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %ymm0, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_no_step:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %ymm0, %ymm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v8f32_no_step:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %ymm0, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v8f32_no_step:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %ymm0, %ymm0
+; SKX-NEXT:    retq
   %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>, %x
   ret <8 x float> %div
 }
@@ -258,11 +632,41 @@ define <8 x float> @v8f32_no_step2(<8 x float> %x) #3 {
 ; SSE-NEXT:    mulps {{.*}}(%rip), %xmm1
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: v8f32_no_step2:
-; AVX:       # BB#0:
-; AVX-NEXT:    vrcpps %ymm0, %ymm0
-; AVX-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
-; AVX-NEXT:    retq
+; AVX-RECIP-LABEL: v8f32_no_step2:
+; AVX-RECIP:       # BB#0:
+; AVX-RECIP-NEXT:    vrcpps %ymm0, %ymm0
+; AVX-RECIP-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; AVX-RECIP-NEXT:    retq
+;
+; BTVER2-LABEL: v8f32_no_step2:
+; BTVER2:       # BB#0:
+; BTVER2-NEXT:    vrcpps %ymm0, %ymm0
+; BTVER2-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; BTVER2-NEXT:    retq
+;
+; SANDY-LABEL: v8f32_no_step2:
+; SANDY:       # BB#0:
+; SANDY-NEXT:    vrcpps %ymm0, %ymm0
+; SANDY-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; SANDY-NEXT:    retq
+;
+; HASWELL-LABEL: v8f32_no_step2:
+; HASWELL:       # BB#0:
+; HASWELL-NEXT:    vrcpps %ymm0, %ymm0
+; HASWELL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; HASWELL-NEXT:    retq
+;
+; KNL-LABEL: v8f32_no_step2:
+; KNL:       # BB#0:
+; KNL-NEXT:    vrcpps %ymm0, %ymm0
+; KNL-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: v8f32_no_step2:
+; SKX:       # BB#0:
+; SKX-NEXT:    vrcp14ps %ymm0, %ymm0
+; SKX-NEXT:    vmulps {{.*}}(%rip), %ymm0, %ymm0
+; SKX-NEXT:    retq
   %div = fdiv fast <8 x float> <float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, float 8.0>, %x
   ret <8 x float> %div
 }