forked from OSchip/llvm-project
[AVX512] Add AVX512 run lines to some tests for scalar fma/add/sub/mul/div and regenerate. Follow up commits will bring AVX512 code up to the same quality as AVX/SSE.
llvm-svn: 277118
This commit is contained in:
Craig Topper
parent
5659a2850f
commit
07aa37039e
|
|
@ -1,6 +1,8 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-pc-win32 -mcpu=core-avx2 | FileCheck %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mcpu=core-avx2 | FileCheck %s --check-prefix=CHECK --check-prefix=AVX2
|
||||
; RUN: llc < %s -mcpu=skx | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512
|
||||
|
||||
attributes #0 = { nounwind }
|
||||
target triple = "x86_64-unknown-unknown"
|
||||
|
||||
declare <4 x float> @llvm.x86.fma.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>)
|
||||
declare <4 x float> @llvm.x86.fma.vfmsub.ss(<4 x float>, <4 x float>, <4 x float>)
|
||||
|
|
@ -12,12 +14,21 @@ declare <2 x double> @llvm.x86.fma.vfmsub.sd(<2 x double>, <2 x double>, <2 x do
|
|||
declare <2 x double> @llvm.x86.fma.vfnmadd.sd(<2 x double>, <2 x double>, <2 x double>)
|
||||
declare <2 x double> @llvm.x86.fma.vfnmsub.sd(<2 x double>, <2 x double>, <2 x double>)
|
||||
|
||||
define void @fmadd_aab_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fmadd_aab_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmadd213ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmadd_aab_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fmadd_aab_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfmadd213ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmadd_aab_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfmadd213ss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -37,12 +48,21 @@ define void @fmadd_aab_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmadd_aba_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fmadd_aba_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmadd132ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmadd_aba_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fmadd_aba_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfmadd132ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmadd_aba_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfmadd213ss %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -62,12 +82,21 @@ define void @fmadd_aba_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmsub_aab_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fmsub_aab_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmsub213ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmsub_aab_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fmsub_aab_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfmsub213ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmsub_aab_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfmsub213ss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -87,12 +116,21 @@ define void @fmsub_aab_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmsub_aba_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fmsub_aba_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmsub132ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmsub_aba_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fmsub_aba_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfmsub132ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmsub_aba_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfmsub213ss %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -112,12 +150,21 @@ define void @fmsub_aba_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmadd_aab_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fnmadd_aab_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmadd213ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmadd_aab_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fnmadd_aab_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfnmadd213ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmadd_aab_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfnmadd213ss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -137,12 +184,21 @@ define void @fnmadd_aab_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmadd_aba_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fnmadd_aba_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmadd132ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmadd_aba_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fnmadd_aba_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfnmadd132ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmadd_aba_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfnmadd213ss %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -162,12 +218,21 @@ define void @fnmadd_aba_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmsub_aab_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fnmsub_aab_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmsub213ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmsub_aab_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fnmsub_aab_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfnmsub213ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmsub_aab_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfnmsub213ss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -187,12 +252,21 @@ define void @fnmsub_aab_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmsub_aba_ss(float* %a, float* %b) #0 {
|
||||
; CHECK-LABEL: fnmsub_aba_ss:
|
||||
; CHECK: vmovss (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmsub132ss (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovss %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmsub_aba_ss(float* %a, float* %b) {
|
||||
; AVX2-LABEL: fnmsub_aba_ss:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vfnmsub132ss (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmsub_aba_ss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vfnmsub213ss %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovss %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load float, float* %a
|
||||
%av0 = insertelement <4 x float> undef, float %a.val, i32 0
|
||||
%av1 = insertelement <4 x float> %av0, float 0.000000e+00, i32 1
|
||||
|
|
@ -212,12 +286,21 @@ define void @fnmsub_aba_ss(float* %a, float* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmadd_aab_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fmadd_aab_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmadd213sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmadd_aab_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fmadd_aab_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfmadd213sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmadd_aab_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfmadd213sd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -233,12 +316,21 @@ define void @fmadd_aab_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmadd_aba_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fmadd_aba_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmadd132sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmadd_aba_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fmadd_aba_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfmadd132sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmadd_aba_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfmadd213sd %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -254,12 +346,21 @@ define void @fmadd_aba_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmsub_aab_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fmsub_aab_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmsub213sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmsub_aab_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fmsub_aab_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfmsub213sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmsub_aab_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfmsub213sd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -275,12 +376,21 @@ define void @fmsub_aab_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fmsub_aba_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fmsub_aba_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfmsub132sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fmsub_aba_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fmsub_aba_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfmsub132sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fmsub_aba_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfmsub213sd %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -296,12 +406,21 @@ define void @fmsub_aba_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmadd_aab_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fnmadd_aab_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmadd213sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmadd_aab_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fnmadd_aab_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfnmadd213sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmadd_aab_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfnmadd213sd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -317,12 +436,21 @@ define void @fnmadd_aab_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmadd_aba_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fnmadd_aba_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmadd132sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmadd_aba_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fnmadd_aba_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfnmadd132sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmadd_aba_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfnmadd213sd %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -338,12 +466,21 @@ define void @fnmadd_aba_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmsub_aab_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fnmsub_aab_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmsub213sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmsub_aab_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fnmsub_aab_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfnmsub213sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmsub_aab_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfnmsub213sd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
@ -359,12 +496,21 @@ define void @fnmsub_aab_sd(double* %a, double* %b) #0 {
|
|||
ret void
|
||||
}
|
||||
|
||||
define void @fnmsub_aba_sd(double* %a, double* %b) #0 {
|
||||
; CHECK-LABEL: fnmsub_aba_sd:
|
||||
; CHECK: vmovsd (%rcx), %[[XMM:xmm[0-9]+]]
|
||||
; CHECK-NEXT: vfnmsub132sd (%rdx), %[[XMM]], %[[XMM]]
|
||||
; CHECK-NEXT: vmovlpd %[[XMM]], (%rcx)
|
||||
; CHECK-NEXT: ret
|
||||
define void @fnmsub_aba_sd(double* %a, double* %b) {
|
||||
; AVX2-LABEL: fnmsub_aba_sd:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vfnmsub132sd (%rsi), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: fnmsub_aba_sd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vfnmsub213sd %xmm0, %xmm1, %xmm0
|
||||
; AVX512-NEXT: vmovlpd %xmm0, (%rdi)
|
||||
; AVX512-NEXT: retq
|
||||
%a.val = load double, double* %a
|
||||
%av0 = insertelement <2 x double> undef, double %a.val, i32 0
|
||||
%av = insertelement <2 x double> %av0, double 0.000000e+00, i32 1
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse2 < %s | FileCheck %s --check-prefix=SSE
|
||||
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s --check-prefix=AVX
|
||||
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
|
||||
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx512f < %s | FileCheck %s --check-prefix=AVX --check-prefix=AVX512
|
||||
|
||||
; Verify that we're folding the load into the math instruction.
|
||||
; This pattern is generated out of the simplest intrinsics usage:
|
||||
|
|
@ -12,10 +13,16 @@ define <4 x float> @addss(<4 x float> %va, float* %pb) {
|
|||
; SSE-NEXT: addss (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: addss:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vaddss (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: addss:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vaddss (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: addss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vaddss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <4 x float> %va, i32 0
|
||||
%b = load float, float* %pb
|
||||
%r = fadd float %a, %b
|
||||
|
|
@ -29,10 +36,16 @@ define <2 x double> @addsd(<2 x double> %va, double* %pb) {
|
|||
; SSE-NEXT: addsd (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: addsd:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vaddsd (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: addsd:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vaddsd (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: addsd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vaddsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <2 x double> %va, i32 0
|
||||
%b = load double, double* %pb
|
||||
%r = fadd double %a, %b
|
||||
|
|
@ -46,10 +59,16 @@ define <4 x float> @subss(<4 x float> %va, float* %pb) {
|
|||
; SSE-NEXT: subss (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: subss:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vsubss (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: subss:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vsubss (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: subss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vsubss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <4 x float> %va, i32 0
|
||||
%b = load float, float* %pb
|
||||
%r = fsub float %a, %b
|
||||
|
|
@ -63,10 +82,16 @@ define <2 x double> @subsd(<2 x double> %va, double* %pb) {
|
|||
; SSE-NEXT: subsd (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: subsd:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vsubsd (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: subsd:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vsubsd (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: subsd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vsubsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <2 x double> %va, i32 0
|
||||
%b = load double, double* %pb
|
||||
%r = fsub double %a, %b
|
||||
|
|
@ -80,10 +105,16 @@ define <4 x float> @mulss(<4 x float> %va, float* %pb) {
|
|||
; SSE-NEXT: mulss (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: mulss:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vmulss (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: mulss:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vmulss (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: mulss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vmulss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <4 x float> %va, i32 0
|
||||
%b = load float, float* %pb
|
||||
%r = fmul float %a, %b
|
||||
|
|
@ -97,10 +128,16 @@ define <2 x double> @mulsd(<2 x double> %va, double* %pb) {
|
|||
; SSE-NEXT: mulsd (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: mulsd:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vmulsd (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: mulsd:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vmulsd (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: mulsd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vmulsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <2 x double> %va, i32 0
|
||||
%b = load double, double* %pb
|
||||
%r = fmul double %a, %b
|
||||
|
|
@ -114,10 +151,16 @@ define <4 x float> @divss(<4 x float> %va, float* %pb) {
|
|||
; SSE-NEXT: divss (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: divss:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vdivss (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: divss:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vdivss (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: divss:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512-NEXT: vdivss %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <4 x float> %va, i32 0
|
||||
%b = load float, float* %pb
|
||||
%r = fdiv float %a, %b
|
||||
|
|
@ -131,10 +174,16 @@ define <2 x double> @divsd(<2 x double> %va, double* %pb) {
|
|||
; SSE-NEXT: divsd (%rdi), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: divsd:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vdivsd (%rdi), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: divsd:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vdivsd (%rdi), %xmm0, %xmm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: divsd:
|
||||
; AVX512: # BB#0:
|
||||
; AVX512-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512-NEXT: vdivsd %xmm1, %xmm0, %xmm0
|
||||
; AVX512-NEXT: retq
|
||||
%a = extractelement <2 x double> %va, i32 0
|
||||
%b = load double, double* %pb
|
||||
%r = fdiv double %a, %b
|
||||
|
|
|
|||
|
|
@ -1,6 +1,8 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc -mcpu=x86-64 -mattr=+sse2 < %s | FileCheck --check-prefix=SSE --check-prefix=SSE2 %s
|
||||
; RUN: llc -mcpu=x86-64 -mattr=+sse4.1 < %s | FileCheck --check-prefix=SSE --check-prefix=SSE41 %s
|
||||
; RUN: llc -mcpu=x86-64 -mattr=+avx < %s | FileCheck --check-prefix=AVX %s
|
||||
; RUN: llc -mcpu=x86-64 -mattr=+avx < %s | FileCheck --check-prefix=AVX --check-prefix=AVX1 %s
|
||||
; RUN: llc -mcpu=x86-64 -mattr=+avx512f < %s | FileCheck --check-prefix=AVX --check-prefix=AVX512 %s
|
||||
|
||||
target triple = "x86_64-unknown-unknown"
|
||||
|
||||
|
|
@ -79,15 +81,15 @@ define <4 x float> @test_div_ss(<4 x float> %a, <4 x float> %b) {
|
|||
define <4 x float> @test_sqrt_ss(<4 x float> %a) {
|
||||
; SSE2-LABEL: test_sqrt_ss:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: sqrtss %xmm0, %xmm1
|
||||
; SSE2-NEXT: movss %xmm1, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
; SSE2-NEXT: sqrtss %xmm0, %xmm1
|
||||
; SSE2-NEXT: movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: test_sqrt_ss:
|
||||
; SSE41: # BB#0:
|
||||
; SSE41-NEXT: sqrtss %xmm0, %xmm1
|
||||
; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
||||
; SSE41-NEXT: retq
|
||||
; SSE41-NEXT: sqrtss %xmm0, %xmm1
|
||||
; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_sqrt_ss:
|
||||
; AVX: # BB#0:
|
||||
|
|
@ -173,13 +175,13 @@ define <2 x double> @test_sqrt_sd(<2 x double> %a) {
|
|||
; SSE-LABEL: test_sqrt_sd:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: sqrtsd %xmm0, %xmm1
|
||||
; SSE-NEXT: movsd %xmm1, %xmm0
|
||||
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_sqrt_sd:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm1
|
||||
; AVX-NEXT: vmovsd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
|
||||
; AVX-NEXT: retq
|
||||
%1 = extractelement <2 x double> %a, i32 0
|
||||
%2 = call double @llvm.sqrt.f64(double %1)
|
||||
|
|
|
|||
Loading…
Reference in New Issue