forked from OSchip/llvm-project
804 lines
36 KiB
LLVM
804 lines
36 KiB
LLVM
; 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 --check-prefix=SSE-RECIP
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX-RECIP
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma | 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 -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
|
|
|
|
; If the target's divss/divps instructions are substantially
|
|
; slower than rcpss/rcpps with a Newton-Raphson refinement,
|
|
; we should generate the estimate sequence.
|
|
|
|
; See PR21385 ( http://llvm.org/bugs/show_bug.cgi?id=21385 )
|
|
; for details about the accuracy, speed, and implementation
|
|
; differences of x86 reciprocal estimates.
|
|
|
|
define float @f32_no_estimate(float %x) #0 {
|
|
; SSE-LABEL: f32_no_estimate:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: divss %xmm0, %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: f32_no_estimate:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; AVX-RECIP-NEXT: vdivss %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: f32_no_estimate:
|
|
; FMA-RECIP: # BB#0:
|
|
; FMA-RECIP-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; FMA-RECIP-NEXT: vdivss %xmm0, %xmm1, %xmm0
|
|
; FMA-RECIP-NEXT: retq
|
|
;
|
|
; BTVER2-LABEL: f32_no_estimate:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [5:1.00]
|
|
; BTVER2-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [19:19.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: f32_no_estimate:
|
|
; SANDY: # BB#0:
|
|
; SANDY-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [6:0.50]
|
|
; SANDY-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [14:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: f32_no_estimate:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [1:0.50]
|
|
; HASWELL-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: f32_no_estimate:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; HASWELL-NO-FMA-NEXT: vdivss %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: f32_no_estimate:
|
|
; AVX512: # BB#0:
|
|
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [1:0.50]
|
|
; AVX512-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
|
|
; AVX512-NEXT: retq # sched: [2:1.00]
|
|
%div = fdiv fast float 1.0, %x
|
|
ret float %div
|
|
}
|
|
|
|
define float @f32_one_step(float %x) #1 {
|
|
; SSE-LABEL: f32_one_step:
|
|
; 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: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: f32_one_step:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
|
|
; AVX-RECIP-NEXT: vmulss %xmm1, %xmm0, %xmm0
|
|
; AVX-RECIP-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; AVX-RECIP-NEXT: vsubss %xmm0, %xmm2, %xmm0
|
|
; AVX-RECIP-NEXT: vmulss %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: vaddss %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: f32_one_step:
|
|
; 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: retq
|
|
;
|
|
; BTVER2-LABEL: f32_one_step:
|
|
; 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: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: f32_one_step:
|
|
; 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: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: f32_one_step:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: f32_one_step:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
|
|
; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm2, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: f32_one_step:
|
|
; AVX512: # BB#0:
|
|
; AVX512-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1
|
|
; AVX512-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0 # sched: [5:0.50]
|
|
; AVX512-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; AVX512-NEXT: retq # sched: [2:1.00]
|
|
%div = fdiv fast float 1.0, %x
|
|
ret float %div
|
|
}
|
|
|
|
define float @f32_two_step(float %x) #2 {
|
|
; SSE-LABEL: f32_two_step:
|
|
; 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: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: f32_two_step:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
|
|
; AVX-RECIP-NEXT: vmulss %xmm1, %xmm0, %xmm2
|
|
; AVX-RECIP-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
|
|
; AVX-RECIP-NEXT: vsubss %xmm2, %xmm3, %xmm2
|
|
; AVX-RECIP-NEXT: vmulss %xmm2, %xmm1, %xmm2
|
|
; AVX-RECIP-NEXT: vaddss %xmm2, %xmm1, %xmm1
|
|
; AVX-RECIP-NEXT: vmulss %xmm1, %xmm0, %xmm0
|
|
; AVX-RECIP-NEXT: vsubss %xmm0, %xmm3, %xmm0
|
|
; AVX-RECIP-NEXT: vmulss %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: vaddss %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: f32_two_step:
|
|
; 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: retq
|
|
;
|
|
; BTVER2-LABEL: f32_two_step:
|
|
; 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: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: f32_two_step:
|
|
; 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: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: f32_two_step:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [1:0.50]
|
|
; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: f32_two_step:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm2
|
|
; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
|
|
; HASWELL-NO-FMA-NEXT: vsubss %xmm2, %xmm3, %xmm2
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm2, %xmm1, %xmm2
|
|
; HASWELL-NO-FMA-NEXT: vaddss %xmm2, %xmm1, %xmm1
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm3, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: f32_two_step:
|
|
; AVX512: # BB#0:
|
|
; AVX512-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1
|
|
; AVX512-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [1:0.50]
|
|
; AVX512-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; AVX512-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
|
|
; AVX512-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
|
|
; AVX512-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; AVX512-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; AVX512-NEXT: retq # sched: [2:1.00]
|
|
%div = fdiv fast float 1.0, %x
|
|
ret float %div
|
|
}
|
|
|
|
define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 {
|
|
; SSE-LABEL: v4f32_no_estimate:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: divps %xmm0, %xmm1
|
|
; SSE-NEXT: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: v4f32_no_estimate:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; AVX-RECIP-NEXT: vdivps %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: v4f32_no_estimate:
|
|
; FMA-RECIP: # BB#0:
|
|
; FMA-RECIP-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; FMA-RECIP-NEXT: vdivps %xmm0, %xmm1, %xmm0
|
|
; FMA-RECIP-NEXT: retq
|
|
;
|
|
; BTVER2-LABEL: v4f32_no_estimate:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
|
|
; BTVER2-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [19:19.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v4f32_no_estimate:
|
|
; SANDY: # BB#0:
|
|
; SANDY-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [6:0.50]
|
|
; SANDY-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [14:1.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v4f32_no_estimate:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1] sched: [1:0.50]
|
|
; HASWELL-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v4f32_no_estimate:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1]
|
|
; HASWELL-NO-FMA-NEXT: vdivps %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v4f32_no_estimate:
|
|
; AVX512: # BB#0:
|
|
; AVX512-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1] sched: [1:0.50]
|
|
; AVX512-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
|
|
; AVX512-NEXT: retq # sched: [2:1.00]
|
|
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
|
|
ret <4 x float> %div
|
|
}
|
|
|
|
define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
|
|
; SSE-LABEL: v4f32_one_step:
|
|
; 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: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: v4f32_one_step:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vrcpps %xmm0, %xmm1
|
|
; AVX-RECIP-NEXT: vmulps %xmm1, %xmm0, %xmm0
|
|
; AVX-RECIP-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; AVX-RECIP-NEXT: vsubps %xmm0, %xmm2, %xmm0
|
|
; AVX-RECIP-NEXT: vmulps %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: v4f32_one_step:
|
|
; 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: retq
|
|
;
|
|
; BTVER2-LABEL: v4f32_one_step:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] 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: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v4f32_one_step:
|
|
; 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: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v4f32_one_step:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v4f32_one_step:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm2, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; KNL-LABEL: v4f32_one_step:
|
|
; KNL: # BB#0:
|
|
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
|
|
; KNL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; SKX-LABEL: v4f32_one_step:
|
|
; SKX: # BB#0:
|
|
; SKX-NEXT: vrcp14ps %xmm0, %xmm1
|
|
; SKX-NEXT: vfnmadd213ps {{.*}}(%rip){1to4}, %xmm1, %xmm0
|
|
; SKX-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
|
|
; SKX-NEXT: retq # sched: [2:1.00]
|
|
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
|
|
ret <4 x float> %div
|
|
}
|
|
|
|
define <4 x float> @v4f32_two_step(<4 x float> %x) #2 {
|
|
; SSE-LABEL: v4f32_two_step:
|
|
; 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: movaps %xmm1, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: v4f32_two_step:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vrcpps %xmm0, %xmm1
|
|
; AVX-RECIP-NEXT: vmulps %xmm1, %xmm0, %xmm2
|
|
; AVX-RECIP-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; AVX-RECIP-NEXT: vsubps %xmm2, %xmm3, %xmm2
|
|
; AVX-RECIP-NEXT: vmulps %xmm2, %xmm1, %xmm2
|
|
; AVX-RECIP-NEXT: vaddps %xmm2, %xmm1, %xmm1
|
|
; AVX-RECIP-NEXT: vmulps %xmm1, %xmm0, %xmm0
|
|
; AVX-RECIP-NEXT: vsubps %xmm0, %xmm3, %xmm0
|
|
; AVX-RECIP-NEXT: vmulps %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: v4f32_two_step:
|
|
; 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: retq
|
|
;
|
|
; BTVER2-LABEL: v4f32_two_step:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] 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: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v4f32_two_step:
|
|
; 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: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v4f32_two_step:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
|
|
; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v4f32_two_step:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm2
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} xmm3 = [1,1,1,1]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %xmm2, %xmm3, %xmm2
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm2, %xmm1, %xmm2
|
|
; HASWELL-NO-FMA-NEXT: vaddps %xmm2, %xmm1, %xmm1
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm3, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; KNL-LABEL: v4f32_two_step:
|
|
; KNL: # BB#0:
|
|
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
|
|
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
|
|
; KNL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; KNL-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
|
|
; KNL-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; SKX-LABEL: v4f32_two_step:
|
|
; SKX: # BB#0:
|
|
; SKX-NEXT: vrcp14ps %xmm0, %xmm1
|
|
; SKX-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
|
|
; SKX-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
|
|
; SKX-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
|
|
; SKX-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
|
|
; SKX-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; SKX-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
|
|
; SKX-NEXT: retq # sched: [2:1.00]
|
|
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
|
|
ret <4 x float> %div
|
|
}
|
|
|
|
define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 {
|
|
; SSE-LABEL: v8f32_no_estimate:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: movaps %xmm2, %xmm3
|
|
; SSE-NEXT: divps %xmm0, %xmm3
|
|
; SSE-NEXT: divps %xmm1, %xmm2
|
|
; SSE-NEXT: movaps %xmm3, %xmm0
|
|
; SSE-NEXT: movaps %xmm2, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: v8f32_no_estimate:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; AVX-RECIP-NEXT: vdivps %ymm0, %ymm1, %ymm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: v8f32_no_estimate:
|
|
; FMA-RECIP: # BB#0:
|
|
; FMA-RECIP-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; FMA-RECIP-NEXT: vdivps %ymm0, %ymm1, %ymm0
|
|
; FMA-RECIP-NEXT: retq
|
|
;
|
|
; BTVER2-LABEL: v8f32_no_estimate:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
|
|
; BTVER2-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [38:38.00]
|
|
; BTVER2-NEXT: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_no_estimate:
|
|
; SANDY: # BB#0:
|
|
; SANDY-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [7:0.50]
|
|
; SANDY-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [29:2.00]
|
|
; SANDY-NEXT: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_no_estimate:
|
|
; HASWELL: # BB#0:
|
|
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
|
|
; HASWELL-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [21:2.00]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_no_estimate:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
|
|
; HASWELL-NO-FMA-NEXT: vdivps %ymm0, %ymm1, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; AVX512-LABEL: v8f32_no_estimate:
|
|
; AVX512: # BB#0:
|
|
; AVX512-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
|
|
; AVX512-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [21:2.00]
|
|
; AVX512-NEXT: retq # sched: [2:1.00]
|
|
%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_one_step(<8 x float> %x) #1 {
|
|
; SSE-LABEL: v8f32_one_step:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: rcpps %xmm0, %xmm4
|
|
; SSE-NEXT: mulps %xmm4, %xmm0
|
|
; SSE-NEXT: movaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: movaps %xmm2, %xmm3
|
|
; SSE-NEXT: subps %xmm0, %xmm3
|
|
; SSE-NEXT: mulps %xmm4, %xmm3
|
|
; SSE-NEXT: addps %xmm4, %xmm3
|
|
; SSE-NEXT: rcpps %xmm1, %xmm0
|
|
; SSE-NEXT: mulps %xmm0, %xmm1
|
|
; SSE-NEXT: subps %xmm1, %xmm2
|
|
; SSE-NEXT: mulps %xmm0, %xmm2
|
|
; SSE-NEXT: addps %xmm0, %xmm2
|
|
; SSE-NEXT: movaps %xmm3, %xmm0
|
|
; SSE-NEXT: movaps %xmm2, %xmm1
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: v8f32_one_step:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vrcpps %ymm0, %ymm1
|
|
; AVX-RECIP-NEXT: vmulps %ymm1, %ymm0, %ymm0
|
|
; AVX-RECIP-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; AVX-RECIP-NEXT: vsubps %ymm0, %ymm2, %ymm0
|
|
; AVX-RECIP-NEXT: vmulps %ymm0, %ymm1, %ymm0
|
|
; AVX-RECIP-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: v8f32_one_step:
|
|
; 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: retq
|
|
;
|
|
; BTVER2-LABEL: v8f32_one_step:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] 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: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_one_step:
|
|
; 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: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_one_step:
|
|
; 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: [1:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_one_step:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm2, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; KNL-LABEL: v8f32_one_step:
|
|
; 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: [1:0.50]
|
|
; KNL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_one_step:
|
|
; SKX: # BB#0:
|
|
; SKX-NEXT: vrcp14ps %ymm0, %ymm1
|
|
; SKX-NEXT: vfnmadd213ps {{.*}}(%rip){1to8}, %ymm1, %ymm0
|
|
; SKX-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0 # sched: [5:0.50]
|
|
; SKX-NEXT: retq # sched: [2:1.00]
|
|
%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_two_step(<8 x float> %x) #2 {
|
|
; SSE-LABEL: v8f32_two_step:
|
|
; SSE: # BB#0:
|
|
; SSE-NEXT: movaps %xmm1, %xmm2
|
|
; SSE-NEXT: rcpps %xmm0, %xmm3
|
|
; SSE-NEXT: movaps %xmm0, %xmm4
|
|
; SSE-NEXT: mulps %xmm3, %xmm4
|
|
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; SSE-NEXT: movaps %xmm1, %xmm5
|
|
; SSE-NEXT: subps %xmm4, %xmm5
|
|
; SSE-NEXT: mulps %xmm3, %xmm5
|
|
; SSE-NEXT: addps %xmm3, %xmm5
|
|
; SSE-NEXT: mulps %xmm5, %xmm0
|
|
; SSE-NEXT: movaps %xmm1, %xmm3
|
|
; SSE-NEXT: subps %xmm0, %xmm3
|
|
; SSE-NEXT: mulps %xmm5, %xmm3
|
|
; SSE-NEXT: addps %xmm5, %xmm3
|
|
; SSE-NEXT: rcpps %xmm2, %xmm0
|
|
; SSE-NEXT: movaps %xmm2, %xmm4
|
|
; SSE-NEXT: mulps %xmm0, %xmm4
|
|
; SSE-NEXT: movaps %xmm1, %xmm5
|
|
; SSE-NEXT: subps %xmm4, %xmm5
|
|
; SSE-NEXT: mulps %xmm0, %xmm5
|
|
; SSE-NEXT: addps %xmm0, %xmm5
|
|
; SSE-NEXT: mulps %xmm5, %xmm2
|
|
; SSE-NEXT: subps %xmm2, %xmm1
|
|
; SSE-NEXT: mulps %xmm5, %xmm1
|
|
; SSE-NEXT: addps %xmm5, %xmm1
|
|
; SSE-NEXT: movaps %xmm3, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-RECIP-LABEL: v8f32_two_step:
|
|
; AVX-RECIP: # BB#0:
|
|
; AVX-RECIP-NEXT: vrcpps %ymm0, %ymm1
|
|
; AVX-RECIP-NEXT: vmulps %ymm1, %ymm0, %ymm2
|
|
; AVX-RECIP-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; AVX-RECIP-NEXT: vsubps %ymm2, %ymm3, %ymm2
|
|
; AVX-RECIP-NEXT: vmulps %ymm2, %ymm1, %ymm2
|
|
; AVX-RECIP-NEXT: vaddps %ymm2, %ymm1, %ymm1
|
|
; AVX-RECIP-NEXT: vmulps %ymm1, %ymm0, %ymm0
|
|
; AVX-RECIP-NEXT: vsubps %ymm0, %ymm3, %ymm0
|
|
; AVX-RECIP-NEXT: vmulps %ymm0, %ymm1, %ymm0
|
|
; AVX-RECIP-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; AVX-RECIP-NEXT: retq
|
|
;
|
|
; FMA-RECIP-LABEL: v8f32_two_step:
|
|
; 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: retq
|
|
;
|
|
; BTVER2-LABEL: v8f32_two_step:
|
|
; BTVER2: # BB#0:
|
|
; BTVER2-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] 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: retq # sched: [4:1.00]
|
|
;
|
|
; SANDY-LABEL: v8f32_two_step:
|
|
; 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: retq # sched: [1:1.00]
|
|
;
|
|
; HASWELL-LABEL: v8f32_two_step:
|
|
; 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: [1:0.50]
|
|
; HASWELL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
|
|
; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0 # sched: [5:0.50]
|
|
; HASWELL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; HASWELL-NO-FMA-LABEL: v8f32_two_step:
|
|
; HASWELL-NO-FMA: # BB#0:
|
|
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm2
|
|
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm2, %ymm3, %ymm2
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm2, %ymm1, %ymm2
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm2, %ymm1, %ymm1
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm3, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; HASWELL-NO-FMA-NEXT: retq
|
|
;
|
|
; KNL-LABEL: v8f32_two_step:
|
|
; 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: [1:0.50]
|
|
; KNL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
|
|
; KNL-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3 # sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3 # sched: [5:0.50]
|
|
; KNL-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0 # sched: [5:0.50]
|
|
; KNL-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0 # sched: [5:0.50]
|
|
; KNL-NEXT: retq # sched: [2:1.00]
|
|
;
|
|
; SKX-LABEL: v8f32_two_step:
|
|
; SKX: # BB#0:
|
|
; SKX-NEXT: vrcp14ps %ymm0, %ymm1
|
|
; SKX-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
|
|
; SKX-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
|
|
; SKX-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3 # sched: [5:0.50]
|
|
; SKX-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3 # sched: [5:0.50]
|
|
; SKX-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0 # sched: [5:0.50]
|
|
; SKX-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0 # sched: [5:0.50]
|
|
; SKX-NEXT: retq # sched: [2:1.00]
|
|
%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
|
|
}
|
|
|
|
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" }
|
|
|