summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/recip-fastmath2.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/X86/recip-fastmath2.ll')
-rw-r--r--test/CodeGen/X86/recip-fastmath2.ll1064
1 files changed, 976 insertions, 88 deletions
diff --git a/test/CodeGen/X86/recip-fastmath2.ll b/test/CodeGen/X86/recip-fastmath2.ll
index 0788b036cc52..440a6f0bef13 100644
--- a/test/CodeGen/X86/recip-fastmath2.ll
+++ b/test/CodeGen/X86/recip-fastmath2.ll
@@ -1,6 +1,13 @@
; 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 -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=SSE --check-prefix=SSE-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=FMA-RECIP
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=BTVER2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=SANDY
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=HASWELL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell -print-schedule -mattr=-fma | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=HASWELL-NO-FMA
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=KNL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx -print-schedule | 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 +18,47 @@ 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
+;
+; FMA-RECIP-LABEL: f32_no_step_2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm0
+; FMA-RECIP-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: f32_no_step_2:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vrcpss %xmm0, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: f32_no_step_2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpss %xmm0, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: f32_no_step_2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm0 # sched: [5:1.00]
+; HASWELL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: f32_no_step_2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; AVX512-LABEL: f32_no_step_2:
+; AVX512: # BB#0:
+; AVX512-NEXT: vrcp14ss %xmm0, %xmm0, %xmm0
+; AVX512-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; AVX512-NEXT: retq # sched: [1:1.00]
%div = fdiv fast float 1234.0, %x
ret float %div
}
@@ -33,20 +76,170 @@ 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
+;
+; FMA-RECIP-LABEL: f32_one_step_2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
+; FMA-RECIP-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; FMA-RECIP-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0
+; FMA-RECIP-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: f32_one_step_2:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [5:1.00]
+; BTVER2-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: f32_one_step_2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [4:0.50]
+; SANDY-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: f32_one_step_2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; HASWELL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: f32_one_step_2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [4:0.50]
+; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; 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 # sched: [9:0.50]
+; AVX512-NEXT: retq # sched: [1:1.00]
%div = fdiv fast float 3456.0, %x
ret float %div
}
+define float @f32_one_step_2_divs(float %x) #1 {
+; SSE-LABEL: f32_one_step_2_divs:
+; SSE: # BB#0:
+; SSE-NEXT: rcpss %xmm0, %xmm1
+; SSE-NEXT: mulss %xmm1, %xmm0
+; SSE-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; SSE-NEXT: subss %xmm0, %xmm2
+; SSE-NEXT: mulss %xmm1, %xmm2
+; SSE-NEXT: addss %xmm1, %xmm2
+; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; SSE-NEXT: mulss %xmm2, %xmm0
+; SSE-NEXT: mulss %xmm2, %xmm0
+; SSE-NEXT: retq
+;
+; AVX-RECIP-LABEL: f32_one_step_2_divs:
+; 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, %xmm1
+; AVX-RECIP-NEXT: vmulss %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT: retq
+;
+; FMA-RECIP-LABEL: f32_one_step_2_divs:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
+; FMA-RECIP-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; FMA-RECIP-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0
+; FMA-RECIP-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1
+; FMA-RECIP-NEXT: vmulss %xmm0, %xmm1, %xmm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: f32_one_step_2_divs:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [5:1.00]
+; BTVER2-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [7:1.00]
+; BTVER2-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: f32_one_step_2_divs:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [4:0.50]
+; SANDY-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:1.00]
+; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: f32_one_step_2_divs:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
+; HASWELL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:0.50]
+; HASWELL-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: f32_one_step_2_divs:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [4:0.50]
+; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; AVX512-LABEL: f32_one_step_2_divs:
+; 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, %xmm1 # sched: [9:0.50]
+; AVX512-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; AVX512-NEXT: retq # sched: [1:1.00]
+ %div = fdiv fast float 3456.0, %x
+ %div2 = fdiv fast float %div, %x
+ ret float %div2
+}
+
define float @f32_two_step_2(float %x) #2 {
; SSE-LABEL: f32_two_step_2:
; SSE: # BB#0:
@@ -66,20 +259,101 @@ 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
+;
+; FMA-RECIP-LABEL: f32_two_step_2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
+; FMA-RECIP-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; FMA-RECIP-NEXT: vmovaps %xmm1, %xmm3
+; FMA-RECIP-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3
+; FMA-RECIP-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3
+; FMA-RECIP-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0
+; FMA-RECIP-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0
+; FMA-RECIP-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: f32_two_step_2:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero sched: [5:1.00]
+; BTVER2-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm2 # sched: [2:1.00]
+; BTVER2-NEXT: vsubss %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss %xmm2, %xmm1, %xmm2 # sched: [2:1.00]
+; BTVER2-NEXT: vaddss %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubss %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: f32_two_step_2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm2 # sched: [5:1.00]
+; SANDY-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero sched: [4:0.50]
+; SANDY-NEXT: vsubss %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
+; SANDY-NEXT: vmulss %xmm2, %xmm1, %xmm2 # sched: [5:1.00]
+; SANDY-NEXT: vaddss %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
+; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vsubss %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: f32_two_step_2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [4:0.50]
+; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
+; 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 # sched: [9:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: f32_two_step_2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm2 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero sched: [4:0.50]
+; HASWELL-NO-FMA-NEXT: vsubss %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm2, %xmm1, %xmm2 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddss %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; AVX512-LABEL: f32_two_step_2:
+; AVX512: # BB#0:
+; AVX512-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1
+; AVX512-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [4:0.50]
+; AVX512-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
+; 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 # sched: [9:0.50]
+; AVX512-NEXT: retq # sched: [1:1.00]
%div = fdiv fast float 6789.0, %x
ret float %div
}
@@ -97,20 +371,191 @@ 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
+;
+; FMA-RECIP-LABEL: v4f32_one_step2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %xmm0, %xmm1
+; FMA-RECIP-NEXT: vfnmadd213ps {{.*}}(%rip), %xmm1, %xmm0
+; FMA-RECIP-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0
+; FMA-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] sched: [5:1.00]
+; BTVER2-NEXT: vrcpps %xmm0, %xmm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v4f32_one_step2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [4:0.50]
+; SANDY-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v4f32_one_step2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0
+; HASWELL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v4f32_one_step2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v4f32_one_step2:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; KNL-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; KNL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0
+; KNL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
+; KNL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; 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 # sched: [9:0.50]
+; SKX-NEXT: retq # sched: [1:1.00]
%div = fdiv fast <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
ret <4 x float> %div
}
+define <4 x float> @v4f32_one_step_2_divs(<4 x float> %x) #1 {
+; SSE-LABEL: v4f32_one_step_2_divs:
+; SSE: # BB#0:
+; SSE-NEXT: rcpps %xmm0, %xmm1
+; SSE-NEXT: mulps %xmm1, %xmm0
+; SSE-NEXT: movaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SSE-NEXT: subps %xmm0, %xmm2
+; SSE-NEXT: mulps %xmm1, %xmm2
+; SSE-NEXT: addps %xmm1, %xmm2
+; SSE-NEXT: movaps {{.*#+}} xmm0 = [1.000000e+00,2.000000e+00,3.000000e+00,4.000000e+00]
+; SSE-NEXT: mulps %xmm2, %xmm0
+; SSE-NEXT: mulps %xmm2, %xmm0
+; SSE-NEXT: retq
+;
+; AVX-RECIP-LABEL: v4f32_one_step_2_divs:
+; 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, %xmm1
+; AVX-RECIP-NEXT: vmulps %xmm0, %xmm1, %xmm0
+; AVX-RECIP-NEXT: retq
+;
+; FMA-RECIP-LABEL: v4f32_one_step_2_divs:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %xmm0, %xmm1
+; FMA-RECIP-NEXT: vfnmadd213ps {{.*}}(%rip), %xmm1, %xmm0
+; FMA-RECIP-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1
+; FMA-RECIP-NEXT: vmulps %xmm0, %xmm1, %xmm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: v4f32_one_step_2_divs:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
+; BTVER2-NEXT: vrcpps %xmm0, %xmm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [7:1.00]
+; BTVER2-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v4f32_one_step_2_divs:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [4:0.50]
+; SANDY-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:1.00]
+; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v4f32_one_step_2_divs:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0
+; HASWELL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
+; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:0.50]
+; HASWELL-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v4f32_one_step_2_divs:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v4f32_one_step_2_divs:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; KNL-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; KNL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0
+; KNL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
+; KNL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:0.50]
+; KNL-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; SKX-LABEL: v4f32_one_step_2_divs:
+; 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, %xmm1 # sched: [9:0.50]
+; SKX-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; SKX-NEXT: retq # sched: [1:1.00]
+ %div = fdiv fast <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
+ %div2 = fdiv fast <4 x float> %div, %x
+ ret <4 x float> %div2
+}
+
define <4 x float> @v4f32_two_step2(<4 x float> %x) #2 {
; SSE-LABEL: v4f32_two_step2:
; SSE: # BB#0:
@@ -130,20 +575,113 @@ 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
+;
+; FMA-RECIP-LABEL: v4f32_two_step2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %xmm0, %xmm1
+; FMA-RECIP-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; FMA-RECIP-NEXT: vmovaps %xmm1, %xmm3
+; FMA-RECIP-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3
+; FMA-RECIP-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3
+; FMA-RECIP-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0
+; FMA-RECIP-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0
+; FMA-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] sched: [5:1.00]
+; BTVER2-NEXT: vrcpps %xmm0, %xmm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm2 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %xmm2, %xmm1, %xmm2 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v4f32_two_step2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm2 # sched: [5:1.00]
+; SANDY-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [4:0.50]
+; SANDY-NEXT: vsubps %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %xmm2, %xmm1, %xmm2 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vsubps %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v4f32_two_step2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
+; 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 # sched: [9:0.50]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v4f32_two_step2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm2 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*}}(%rip), %xmm3 # sched: [4:0.50]
+; HASWELL-NO-FMA-NEXT: vsubps %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm2, %xmm1, %xmm2 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddps %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
+; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v4f32_two_step2:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
+; KNL-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; KNL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
+; 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 # sched: [9:0.50]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; SKX-LABEL: v4f32_two_step2:
+; SKX: # BB#0:
+; SKX-NEXT: vrcp14ps %xmm0, %xmm1
+; SKX-NEXT: vbroadcastss {{.*}}(%rip), %xmm2 # sched: [4:0.50]
+; SKX-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
+; 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 # sched: [9:0.50]
+; SKX-NEXT: retq # sched: [1:1.00]
%div = fdiv fast <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
ret <4 x float> %div
}
@@ -169,20 +707,200 @@ 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
+;
+; FMA-RECIP-LABEL: v8f32_one_step2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm1
+; FMA-RECIP-NEXT: vfnmadd213ps {{.*}}(%rip), %ymm1, %ymm0
+; FMA-RECIP-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0
+; FMA-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] sched: [5:1.00]
+; BTVER2-NEXT: vrcpps %ymm0, %ymm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v8f32_one_step2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
+; 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] sched: [4:0.50]
+; SANDY-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v8f32_one_step2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; HASWELL-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0
+; HASWELL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
+; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v8f32_one_step2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v8f32_one_step2:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; KNL-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; KNL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0
+; KNL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
+; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; 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 # sched: [9:1.00]
+; SKX-NEXT: retq # sched: [1:1.00]
%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
}
+define <8 x float> @v8f32_one_step_2_divs(<8 x float> %x) #1 {
+; SSE-LABEL: v8f32_one_step_2_divs:
+; SSE: # BB#0:
+; SSE-NEXT: rcpps %xmm0, %xmm2
+; SSE-NEXT: mulps %xmm2, %xmm0
+; SSE-NEXT: movaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
+; SSE-NEXT: movaps %xmm3, %xmm4
+; SSE-NEXT: subps %xmm0, %xmm4
+; SSE-NEXT: mulps %xmm2, %xmm4
+; SSE-NEXT: addps %xmm2, %xmm4
+; SSE-NEXT: rcpps %xmm1, %xmm0
+; SSE-NEXT: mulps %xmm0, %xmm1
+; SSE-NEXT: subps %xmm1, %xmm3
+; SSE-NEXT: mulps %xmm0, %xmm3
+; SSE-NEXT: addps %xmm0, %xmm3
+; SSE-NEXT: movaps {{.*#+}} xmm1 = [5.000000e+00,6.000000e+00,7.000000e+00,8.000000e+00]
+; SSE-NEXT: mulps %xmm3, %xmm1
+; SSE-NEXT: movaps {{.*#+}} xmm0 = [1.000000e+00,2.000000e+00,3.000000e+00,4.000000e+00]
+; SSE-NEXT: mulps %xmm4, %xmm0
+; SSE-NEXT: mulps %xmm4, %xmm0
+; SSE-NEXT: mulps %xmm3, %xmm1
+; SSE-NEXT: retq
+;
+; AVX-RECIP-LABEL: v8f32_one_step_2_divs:
+; 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, %ymm1
+; AVX-RECIP-NEXT: vmulps %ymm0, %ymm1, %ymm0
+; AVX-RECIP-NEXT: retq
+;
+; FMA-RECIP-LABEL: v8f32_one_step_2_divs:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm1
+; FMA-RECIP-NEXT: vfnmadd213ps {{.*}}(%rip), %ymm1, %ymm0
+; FMA-RECIP-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1
+; FMA-RECIP-NEXT: vmulps %ymm0, %ymm1, %ymm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: v8f32_one_step_2_divs:
+; 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] sched: [5:1.00]
+; BTVER2-NEXT: vrcpps %ymm0, %ymm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [7:1.00]
+; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v8f32_one_step_2_divs:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
+; 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] sched: [4:0.50]
+; SANDY-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [9:1.00]
+; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v8f32_one_step_2_divs:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; HASWELL-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0
+; HASWELL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
+; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [9:1.00]
+; HASWELL-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v8f32_one_step_2_divs:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [9:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v8f32_one_step_2_divs:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; KNL-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; KNL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0
+; KNL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
+; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [9:1.00]
+; KNL-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; SKX-LABEL: v8f32_one_step_2_divs:
+; 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, %ymm1 # sched: [9:1.00]
+; SKX-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; SKX-NEXT: retq # sched: [1:1.00]
+ %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
+ %div2 = fdiv fast <8 x float> %div, %x
+ ret <8 x float> %div2
+}
+
define <8 x float> @v8f32_two_step2(<8 x float> %x) #2 {
; SSE-LABEL: v8f32_two_step2:
; SSE: # BB#0:
@@ -216,20 +934,113 @@ 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
+;
+; FMA-RECIP-LABEL: v8f32_two_step2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm1
+; FMA-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]
+; FMA-RECIP-NEXT: vmovaps %ymm1, %ymm3
+; FMA-RECIP-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3
+; FMA-RECIP-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3
+; FMA-RECIP-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0
+; FMA-RECIP-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0
+; FMA-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] sched: [5:1.00]
+; BTVER2-NEXT: vrcpps %ymm0, %ymm1 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v8f32_two_step2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [5:1.00]
+; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [5:1.00]
+; 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] sched: [4:0.50]
+; SANDY-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v8f32_two_step2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; HASWELL-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; HASWELL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
+; 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 # sched: [9:1.00]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v8f32_two_step2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*}}(%rip), %ymm3 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
+; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v8f32_two_step2:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
+; KNL-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; KNL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
+; 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 # sched: [9:1.00]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; SKX-LABEL: v8f32_two_step2:
+; SKX: # BB#0:
+; SKX-NEXT: vrcp14ps %ymm0, %ymm1
+; SKX-NEXT: vbroadcastss {{.*}}(%rip), %ymm2 # sched: [5:1.00]
+; SKX-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
+; 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 # sched: [9:1.00]
+; SKX-NEXT: retq # sched: [1:1.00]
%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 +1052,45 @@ 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
+;
+; FMA-RECIP-LABEL: v8f32_no_step:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: v8f32_no_step:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vrcpps %ymm0, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v8f32_no_step:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %ymm0, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v8f32_no_step:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v8f32_no_step:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v8f32_no_step:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; SKX-LABEL: v8f32_no_step:
+; SKX: # BB#0:
+; SKX-NEXT: vrcp14ps %ymm0, %ymm0
+; SKX-NEXT: retq # sched: [1:1.00]
%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 +1104,53 @@ 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
+;
+; FMA-RECIP-LABEL: v8f32_no_step2:
+; FMA-RECIP: # BB#0:
+; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm0
+; FMA-RECIP-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0
+; FMA-RECIP-NEXT: retq
+;
+; BTVER2-LABEL: v8f32_no_step2:
+; BTVER2: # BB#0:
+; BTVER2-NEXT: vrcpps %ymm0, %ymm0 # sched: [2:1.00]
+; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [7:1.00]
+; BTVER2-NEXT: retq # sched: [4:1.00]
+;
+; SANDY-LABEL: v8f32_no_step2:
+; SANDY: # BB#0:
+; SANDY-NEXT: vrcpps %ymm0, %ymm0 # sched: [5:1.00]
+; SANDY-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; SANDY-NEXT: retq # sched: [5:1.00]
+;
+; HASWELL-LABEL: v8f32_no_step2:
+; HASWELL: # BB#0:
+; HASWELL-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
+; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; HASWELL-NEXT: retq # sched: [1:1.00]
+;
+; HASWELL-NO-FMA-LABEL: v8f32_no_step2:
+; HASWELL-NO-FMA: # BB#0:
+; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
+; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; HASWELL-NO-FMA-NEXT: retq # sched: [1:1.00]
+;
+; KNL-LABEL: v8f32_no_step2:
+; KNL: # BB#0:
+; KNL-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
+; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; KNL-NEXT: retq # sched: [1:1.00]
+;
+; SKX-LABEL: v8f32_no_step2:
+; SKX: # BB#0:
+; SKX-NEXT: vrcp14ps %ymm0, %ymm0
+; SKX-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [9:1.00]
+; SKX-NEXT: retq # sched: [1:1.00]
%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
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-17 12:57:53 +0000