forked from OSchip/llvm-project
1198 lines
56 KiB
LLVM
1198 lines
56 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; 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.
|
|
|
|
define float @f32_no_step_2(float %x) #3 {
|
|
; SSE-LABEL: f32_no_step_2:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: rcpss %xmm0, %xmm0
|
|
; SSE-NEXT: mulss {{.*}}(%rip), %xmm0
|
|
; SSE-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: [11:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; 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: [10:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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: [10:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: f32_no_step_2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpss %xmm0, %xmm0, %xmm0 # sched: [5:1.00]
|
|
; KNL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: f32_no_step_2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpss %xmm0, %xmm0, %xmm0 # sched: [4:1.00]
|
|
; SKX-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%div = fdiv fast float 1234.0, %x
|
|
ret float %div
|
|
}
|
|
|
|
define float @f32_one_step_2(float %x) #1 {
|
|
; SSE-LABEL: f32_one_step_2:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: rcpss %xmm0, %xmm2
|
|
; SSE-NEXT: mulss %xmm2, %xmm0
|
|
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: subss %xmm0, %xmm1
|
|
; SSE-NEXT: mulss %xmm2, %xmm1
|
|
; SSE-NEXT: addss %xmm2, %xmm1
|
|
; SSE-NEXT: mulss {{.*}}(%rip), %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-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 {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem
|
|
; FMA-RECIP-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1
|
|
; 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: [6:0.50]
|
|
; 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: [11:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: f32_one_step_2:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [10:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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: [5:0.50]
|
|
; 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: [10:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: f32_one_step_2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [10:0.50]
|
|
; KNL-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; KNL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: f32_one_step_2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [9:0.50]
|
|
; SKX-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [4:0.33]
|
|
; SKX-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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 {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem
|
|
; FMA-RECIP-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1
|
|
; 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: [6:0.50]
|
|
; 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: [11:1.00]
|
|
; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: f32_one_step_2_divs:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [10:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [10:0.50]
|
|
; HASWELL-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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: [5:0.50]
|
|
; 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: [10:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: f32_one_step_2_divs:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [10:0.50]
|
|
; KNL-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; KNL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [10:0.50]
|
|
; KNL-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: f32_one_step_2_divs:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [9:0.50]
|
|
; SKX-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [4:0.33]
|
|
; SKX-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm1 # sched: [9:0.50]
|
|
; SKX-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [4:0.33]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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:
|
|
; SSE-NEXT: rcpss %xmm0, %xmm2
|
|
; SSE-NEXT: movaps %xmm0, %xmm3
|
|
; SSE-NEXT: mulss %xmm2, %xmm3
|
|
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: movaps %xmm1, %xmm4
|
|
; SSE-NEXT: subss %xmm3, %xmm4
|
|
; SSE-NEXT: mulss %xmm2, %xmm4
|
|
; SSE-NEXT: addss %xmm2, %xmm4
|
|
; SSE-NEXT: mulss %xmm4, %xmm0
|
|
; SSE-NEXT: subss %xmm0, %xmm1
|
|
; SSE-NEXT: mulss %xmm4, %xmm1
|
|
; SSE-NEXT: addss %xmm4, %xmm1
|
|
; SSE-NEXT: mulss {{.*}}(%rip), %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-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 {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2
|
|
; FMA-RECIP-NEXT: vfmadd132ss {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1
|
|
; FMA-RECIP-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2
|
|
; FMA-RECIP-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3
|
|
; 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: [6:0.50]
|
|
; 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: [11:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; 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: [5:0.50]
|
|
; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ss {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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: [5:0.50]
|
|
; 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: [10:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: f32_two_step_2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [5:0.50]
|
|
; KNL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; KNL-NEXT: vfnmadd213ss {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ss {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1 sched: [5:0.50]
|
|
; KNL-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3 sched: [5:0.50]
|
|
; KNL-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: f32_two_step_2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [5:0.50]
|
|
; SKX-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:0.33]
|
|
; SKX-NEXT: vfnmadd213ss {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2 sched: [4:0.33]
|
|
; SKX-NEXT: vfmadd132ss {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1 sched: [4:0.33]
|
|
; SKX-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2 sched: [4:0.33]
|
|
; SKX-NEXT: vfmadd132ss {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3 sched: [4:0.33]
|
|
; SKX-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0 # sched: [9:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%div = fdiv fast float 6789.0, %x
|
|
ret float %div
|
|
}
|
|
|
|
define <4 x float> @v4f32_one_step2(<4 x float> %x) #1 {
|
|
; SSE-LABEL: v4f32_one_step2:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: rcpps %xmm0, %xmm2
|
|
; SSE-NEXT: mulps %xmm2, %xmm0
|
|
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: subps %xmm0, %xmm1
|
|
; SSE-NEXT: mulps %xmm2, %xmm1
|
|
; SSE-NEXT: addps %xmm2, %xmm1
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-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 {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1
|
|
; 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: [6:0.50]
|
|
; 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: [11:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v4f32_one_step2:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [11:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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 {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; 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: [11:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v4f32_one_step2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [11:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v4f32_one_step2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %xmm0, %xmm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [10:0.50]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [4:0.33]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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 {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1
|
|
; 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: [6:0.50]
|
|
; 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: [11:1.00]
|
|
; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v4f32_one_step_2_divs:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [11:0.50]
|
|
; HASWELL-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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 {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; 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: [11:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v4f32_one_step_2_divs:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [5:0.50]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [11:0.50]
|
|
; KNL-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v4f32_one_step_2_divs:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %xmm0, %xmm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) + mem sched: [10:0.50]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm1) + xmm1 sched: [4:0.33]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm1 # sched: [10:0.50]
|
|
; SKX-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [4:0.33]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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:
|
|
; SSE-NEXT: rcpps %xmm0, %xmm2
|
|
; SSE-NEXT: movaps %xmm0, %xmm3
|
|
; SSE-NEXT: mulps %xmm2, %xmm3
|
|
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: movaps %xmm1, %xmm4
|
|
; SSE-NEXT: subps %xmm3, %xmm4
|
|
; SSE-NEXT: mulps %xmm2, %xmm4
|
|
; SSE-NEXT: addps %xmm2, %xmm4
|
|
; SSE-NEXT: mulps %xmm4, %xmm0
|
|
; SSE-NEXT: subps %xmm0, %xmm1
|
|
; SSE-NEXT: mulps %xmm4, %xmm1
|
|
; SSE-NEXT: addps %xmm4, %xmm1
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-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 {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1
|
|
; FMA-RECIP-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3
|
|
; 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: [6:0.50]
|
|
; 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: [11:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v4f32_two_step2:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [11:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; 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 {{.*#+}} xmm3 = [1,1,1,1] sched: [6:0.50]
|
|
; 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: [11:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v4f32_two_step2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; KNL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1 sched: [5:0.50]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3 sched: [5:0.50]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [11:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v4f32_two_step2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %xmm0, %xmm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
|
|
; SKX-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:0.33]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} xmm3 = -(xmm0 * xmm3) + xmm2 sched: [4:0.33]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} xmm3 = (xmm3 * xmm1) + xmm1 sched: [4:0.33]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} xmm0 = -(xmm3 * xmm0) + xmm2 sched: [4:0.33]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} xmm0 = (xmm0 * xmm3) + xmm3 sched: [4:0.33]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %xmm0, %xmm0 # sched: [10:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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 <8 x float> @v8f32_one_step2(<8 x float> %x) #1 {
|
|
; SSE-LABEL: v8f32_one_step2:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: rcpps %xmm1, %xmm4
|
|
; SSE-NEXT: mulps %xmm4, %xmm1
|
|
; SSE-NEXT: movaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: movaps %xmm2, %xmm3
|
|
; SSE-NEXT: subps %xmm1, %xmm3
|
|
; SSE-NEXT: mulps %xmm4, %xmm3
|
|
; SSE-NEXT: addps %xmm4, %xmm3
|
|
; SSE-NEXT: rcpps %xmm0, %xmm1
|
|
; SSE-NEXT: mulps %xmm1, %xmm0
|
|
; SSE-NEXT: subps %xmm0, %xmm2
|
|
; SSE-NEXT: mulps %xmm1, %xmm2
|
|
; SSE-NEXT: addps %xmm1, %xmm2
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm2
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm3
|
|
; SSE-NEXT: movaps %xmm2, %xmm0
|
|
; SSE-NEXT: movaps %xmm3, %xmm1
|
|
; SSE-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 {{.*#+}} ymm0 = -(ymm1 * ymm0) + mem
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1
|
|
; 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: [2:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [7:2.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_one_step2:
|
|
; SANDY: # %bb.0:
|
|
; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
|
|
; 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: [7:0.50]
|
|
; 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: [12:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_one_step2:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_one_step2:
|
|
; HASWELL-NO-FMA: # %bb.0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v8f32_one_step2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1 sched: [5:0.50]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_one_step2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %ymm0, %ymm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + mem sched: [11:0.50]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1 sched: [4:0.33]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [11:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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 {{.*#+}} ymm0 = -(ymm1 * ymm0) + mem
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1
|
|
; 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: [2:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [7:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_one_step_2_divs:
|
|
; SANDY: # %bb.0:
|
|
; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
|
|
; 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: [7:0.50]
|
|
; 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: [12:1.00]
|
|
; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_one_step_2_divs:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [12:0.50]
|
|
; HASWELL-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_one_step_2_divs:
|
|
; HASWELL-NO-FMA: # %bb.0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [12:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v8f32_one_step_2_divs:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1 sched: [5:0.50]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [12:0.50]
|
|
; KNL-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_one_step_2_divs:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %ymm0, %ymm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + mem sched: [11:0.50]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm1) + ymm1 sched: [4:0.33]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm1 # sched: [11:0.50]
|
|
; SKX-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [4:0.33]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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:
|
|
; SSE-NEXT: movaps %xmm0, %xmm2
|
|
; SSE-NEXT: rcpps %xmm1, %xmm3
|
|
; SSE-NEXT: movaps %xmm1, %xmm4
|
|
; SSE-NEXT: mulps %xmm3, %xmm4
|
|
; SSE-NEXT: movaps {{.*#+}} xmm0 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: movaps %xmm0, %xmm5
|
|
; SSE-NEXT: subps %xmm4, %xmm5
|
|
; SSE-NEXT: mulps %xmm3, %xmm5
|
|
; SSE-NEXT: addps %xmm3, %xmm5
|
|
; SSE-NEXT: mulps %xmm5, %xmm1
|
|
; SSE-NEXT: movaps %xmm0, %xmm3
|
|
; SSE-NEXT: subps %xmm1, %xmm3
|
|
; SSE-NEXT: mulps %xmm5, %xmm3
|
|
; SSE-NEXT: addps %xmm5, %xmm3
|
|
; SSE-NEXT: rcpps %xmm2, %xmm1
|
|
; SSE-NEXT: movaps %xmm2, %xmm4
|
|
; SSE-NEXT: mulps %xmm1, %xmm4
|
|
; SSE-NEXT: movaps %xmm0, %xmm5
|
|
; SSE-NEXT: subps %xmm4, %xmm5
|
|
; SSE-NEXT: mulps %xmm1, %xmm5
|
|
; SSE-NEXT: addps %xmm1, %xmm5
|
|
; SSE-NEXT: mulps %xmm5, %xmm2
|
|
; SSE-NEXT: subps %xmm2, %xmm0
|
|
; SSE-NEXT: mulps %xmm5, %xmm0
|
|
; SSE-NEXT: addps %xmm5, %xmm0
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm0
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm3
|
|
; SSE-NEXT: movaps %xmm3, %xmm1
|
|
; SSE-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 {{.*#+}} ymm3 = -(ymm0 * ymm3) + ymm2
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} ymm3 = (ymm3 * ymm1) + ymm1
|
|
; FMA-RECIP-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm3 * ymm0) + ymm2
|
|
; FMA-RECIP-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm3) + ymm3
|
|
; 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: [2:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:2.00]
|
|
; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:2.00]
|
|
; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [7:2.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_two_step2:
|
|
; SANDY: # %bb.0:
|
|
; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
|
|
; 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: [7:0.50]
|
|
; 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: [12:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_two_step2:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; HASWELL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} ymm3 = -(ymm0 * ymm3) + ymm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} ymm3 = (ymm3 * ymm1) + ymm1 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm3 * ymm0) + ymm2 sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm3) + ymm3 sched: [5:0.50]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_two_step2:
|
|
; HASWELL-NO-FMA: # %bb.0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v8f32_two_step2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; KNL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} ymm3 = -(ymm0 * ymm3) + ymm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} ymm3 = (ymm3 * ymm1) + ymm1 sched: [5:0.50]
|
|
; KNL-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm3 * ymm0) + ymm2 sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm3) + ymm3 sched: [5:0.50]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_two_step2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %ymm0, %ymm1 # sched: [4:1.00]
|
|
; SKX-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
|
|
; SKX-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:0.33]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} ymm3 = -(ymm0 * ymm3) + ymm2 sched: [4:0.33]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} ymm3 = (ymm3 * ymm1) + ymm1 sched: [4:0.33]
|
|
; SKX-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm3 * ymm0) + ymm2 sched: [4:0.33]
|
|
; SKX-NEXT: vfmadd132ps {{.*#+}} ymm0 = (ymm0 * ymm3) + ymm3 sched: [4:0.33]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [11:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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_no_step(<8 x float> %x) #3 {
|
|
; SSE-LABEL: v8f32_no_step:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: rcpps %xmm0, %xmm0
|
|
; SSE-NEXT: rcpps %xmm1, %xmm1
|
|
; SSE-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: [2:2.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_no_step:
|
|
; SANDY: # %bb.0:
|
|
; SANDY-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_no_step:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %ymm0, %ymm0 # sched: [11:2.00]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_no_step:
|
|
; HASWELL-NO-FMA: # %bb.0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm0 # sched: [11:2.00]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v8f32_no_step:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %ymm0, %ymm0 # sched: [11:2.00]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_no_step:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %ymm0, %ymm0 # sched: [4:1.00]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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
|
|
}
|
|
|
|
define <8 x float> @v8f32_no_step2(<8 x float> %x) #3 {
|
|
; SSE-LABEL: v8f32_no_step2:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: rcpps %xmm1, %xmm1
|
|
; SSE-NEXT: rcpps %xmm0, %xmm0
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm0
|
|
; SSE-NEXT: mulps {{.*}}(%rip), %xmm1
|
|
; SSE-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: [2:2.00]
|
|
; BTVER2-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [7:2.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_no_step2:
|
|
; SANDY: # %bb.0:
|
|
; SANDY-NEXT: vrcpps %ymm0, %ymm0 # sched: [7:2.00]
|
|
; SANDY-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_no_step2:
|
|
; HASWELL: # %bb.0:
|
|
; HASWELL-NEXT: vrcpps %ymm0, %ymm0 # sched: [11:2.00]
|
|
; HASWELL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; HASWELL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_no_step2:
|
|
; HASWELL-NO-FMA: # %bb.0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm0 # sched: [11:2.00]
|
|
; HASWELL-NO-FMA-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; HASWELL-NO-FMA-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; KNL-LABEL: v8f32_no_step2:
|
|
; KNL: # %bb.0:
|
|
; KNL-NEXT: vrcpps %ymm0, %ymm0 # sched: [11:2.00]
|
|
; KNL-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [12:0.50]
|
|
; KNL-NEXT: retq # sched: [7:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_no_step2:
|
|
; SKX: # %bb.0:
|
|
; SKX-NEXT: vrcpps %ymm0, %ymm0 # sched: [4:1.00]
|
|
; SKX-NEXT: vmulps {{.*}}(%rip), %ymm0, %ymm0 # sched: [11:0.50]
|
|
; SKX-NEXT: retq # sched: [7:1.00]
|
|
%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
|
|
}
|
|
|
|
attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!divf,!vec-divf" }
|
|
attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" }
|
|
attributes #2 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf:2,vec-divf:2" }
|
|
attributes #3 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf:0,vec-divf:0" }
|
|
|