maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/fma4-scalar-memfold.ll

105 lines
4.0 KiB
LLVM
Raw Normal View History

[X86] Add separate intrinsics for scalar FMA4 instructions. Summary: These instructions zero the non-scalar part of the lower 128-bits which makes them different than the FMA3 instructions which pass through the non-scalar part of the lower 128-bits. I've only added fmadd because we should be able to derive all other variants using operand negation in the intrinsic header like we do for AVX512. I think there are still some missed negate folding opportunities with the FMA4 instructions in light of this behavior difference that I hadn't noticed before. I've split the tests so that we can use different intrinsics for scalar testing between the two. I just copied the tests split the RUN lines and changed out the scalar intrinsics. fma4-fneg-combine.ll is a new test to make sure we negate the fma4 intrinsics correctly though there are a couple TODOs in it. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D39851 llvm-svn: 318984
2017-11-26 02:32:43 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mattr=fma4 | FileCheck %s
target triple = "x86_64-unknown-unknown"
declare <4 x float> @llvm.x86.fma4.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>)
declare <2 x double> @llvm.x86.fma4.vfmadd.sd(<2 x double>, <2 x double>, <2 x double>)
define void @fmadd_aab_ss(float* %a, float* %b) {
; CHECK-LABEL: fmadd_aab_ss:
; CHECK: # BB#0:
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vfmaddss (%rsi), %xmm0, %xmm0, %xmm0
; CHECK-NEXT: vmovss %xmm0, (%rdi)
; CHECK-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
%av2 = insertelement <4 x float> %av1, float 0.000000e+00, i32 2
%av = insertelement <4 x float> %av2, float 0.000000e+00, i32 3
%b.val = load float, float* %b
%bv0 = insertelement <4 x float> undef, float %b.val, i32 0
%bv1 = insertelement <4 x float> %bv0, float 0.000000e+00, i32 1
%bv2 = insertelement <4 x float> %bv1, float 0.000000e+00, i32 2
%bv = insertelement <4 x float> %bv2, float 0.000000e+00, i32 3
%vr = call <4 x float> @llvm.x86.fma4.vfmadd.ss(<4 x float> %av, <4 x float> %av, <4 x float> %bv)
%sr = extractelement <4 x float> %vr, i32 0
store float %sr, float* %a
ret void
}
define void @fmadd_aba_ss(float* %a, float* %b) {
; CHECK-LABEL: fmadd_aba_ss:
; CHECK: # BB#0:
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: vfmaddss %xmm0, (%rsi), %xmm0, %xmm0
; CHECK-NEXT: vmovss %xmm0, (%rdi)
; CHECK-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
%av2 = insertelement <4 x float> %av1, float 0.000000e+00, i32 2
%av = insertelement <4 x float> %av2, float 0.000000e+00, i32 3
%b.val = load float, float* %b
%bv0 = insertelement <4 x float> undef, float %b.val, i32 0
%bv1 = insertelement <4 x float> %bv0, float 0.000000e+00, i32 1
%bv2 = insertelement <4 x float> %bv1, float 0.000000e+00, i32 2
%bv = insertelement <4 x float> %bv2, float 0.000000e+00, i32 3
%vr = call <4 x float> @llvm.x86.fma4.vfmadd.ss(<4 x float> %av, <4 x float> %bv, <4 x float> %av)
%sr = extractelement <4 x float> %vr, i32 0
store float %sr, float* %a
ret void
}
define void @fmadd_aab_sd(double* %a, double* %b) {
; CHECK-LABEL: fmadd_aab_sd:
; CHECK: # BB#0:
; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT: vfmaddsd (%rsi), %xmm0, %xmm0, %xmm0
; CHECK-NEXT: vmovlpd %xmm0, (%rdi)
; CHECK-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
%b.val = load double, double* %b
%bv0 = insertelement <2 x double> undef, double %b.val, i32 0
%bv = insertelement <2 x double> %bv0, double 0.000000e+00, i32 1
%vr = call <2 x double> @llvm.x86.fma4.vfmadd.sd(<2 x double> %av, <2 x double> %av, <2 x double> %bv)
%sr = extractelement <2 x double> %vr, i32 0
store double %sr, double* %a
ret void
}
define void @fmadd_aba_sd(double* %a, double* %b) {
; CHECK-LABEL: fmadd_aba_sd:
; CHECK: # BB#0:
; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT: vfmaddsd %xmm0, (%rsi), %xmm0, %xmm0
; CHECK-NEXT: vmovlpd %xmm0, (%rdi)
; CHECK-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
%b.val = load double, double* %b
%bv0 = insertelement <2 x double> undef, double %b.val, i32 0
%bv = insertelement <2 x double> %bv0, double 0.000000e+00, i32 1
%vr = call <2 x double> @llvm.x86.fma4.vfmadd.sd(<2 x double> %av, <2 x double> %bv, <2 x double> %av)
%sr = extractelement <2 x double> %vr, i32 0
store double %sr, double* %a
ret void
}