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/fma-intrinsics-canonical.ll

902 lines
47 KiB
LLVM
Raw Normal View History

[X86] Lowering FMA intrinsics to native IR (LLVM part) Support for Clang lowering of fused intrinsics. This patch: 1. Removes bindings to clang fma intrinsics. 2. Introduces new LLVM unmasked intrinsics with rounding mode: int_x86_avx512_vfmadd_pd_512 int_x86_avx512_vfmadd_ps_512 int_x86_avx512_vfmaddsub_pd_512 int_x86_avx512_vfmaddsub_ps_512 supported with a new intrinsic type (INTR_TYPE_3OP_RM). 3. Introduces new x86 fmaddsub/fmsubadd folding. 4. Introduces new tests for code emitted by sequentions introduced in Clang part. Patch by tkrupa Reviewers: craig.topper, sroland, spatel, RKSimon Reviewed By: craig.topper, RKSimon Differential Revision: https://reviews.llvm.org/D47443 llvm-svn: 333554
2018-05-30 23:25:16 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+fma,-fma4 -show-mc-encoding | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FMA
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,-fma4 -show-mc-encoding | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-AVX512VL
; RUN: llc < %s -mtriple=x86_64-pc-windows -mattr=+fma,-fma4 -show-mc-encoding | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-FMA-WIN
; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/fma-builtins.c
define <4 x float> @test_mm_fmadd_ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fmadd_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmadd213ps %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xa8,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmadd_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmadd213ps %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xa8,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmadd_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm1 # encoding: [0xc5,0xf8,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmadd213ps (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0x71,0xa8,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
ret <4 x float> %0
}
define <2 x double> @test_mm_fmadd_pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fmadd_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmadd213pd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xa8,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmadd_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmadd213pd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xa8,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmadd_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm1 # encoding: [0xc5,0xf9,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmadd213pd (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0xf1,0xa8,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c) #2
ret <2 x double> %0
}
define <4 x float> @test_mm_fmadd_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fmadd_ss:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmadd213ss %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xa9,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmadd_ss:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmadd213ss %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xa9,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmadd_ss:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovss (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7a,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero,zero,zero
; CHECK-FMA-WIN-NEXT: vfmadd132ss (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0x99,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm0 * mem) + xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <4 x float> %a, i64 0
%1 = extractelement <4 x float> %b, i64 0
%2 = extractelement <4 x float> %c, i64 0
%3 = tail call float @llvm.fma.f32(float %0, float %1, float %2) #2
%4 = insertelement <4 x float> %a, float %3, i64 0
ret <4 x float> %4
}
define <2 x double> @test_mm_fmadd_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fmadd_sd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmadd213sd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xa9,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmadd_sd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmadd213sd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xa9,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmadd_sd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovsd (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7b,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero
; CHECK-FMA-WIN-NEXT: vfmadd132sd (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0x99,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm0 * mem) + xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <2 x double> %a, i64 0
%1 = extractelement <2 x double> %b, i64 0
%2 = extractelement <2 x double> %c, i64 0
%3 = tail call double @llvm.fma.f64(double %0, double %1, double %2) #2
%4 = insertelement <2 x double> %a, double %3, i64 0
ret <2 x double> %4
}
define <4 x float> @test_mm_fmsub_ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fmsub_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsub213ps %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xaa,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmsub_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsub213ps %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xaa,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmsub_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm1 # encoding: [0xc5,0xf8,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsub213ps (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0x71,0xaa,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i) #2
ret <4 x float> %0
}
define <2 x double> @test_mm_fmsub_pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fmsub_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsub213pd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xaa,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmsub_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsub213pd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xaa,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmsub_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm1 # encoding: [0xc5,0xf9,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsub213pd (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0xf1,0xaa,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %c
%0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %sub.i) #2
ret <2 x double> %0
}
define <4 x float> @test_mm_fmsub_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fmsub_ss:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsub213ss %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xab,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmsub_ss:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsub213ss %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xab,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmsub_ss:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovss (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7a,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero,zero,zero
; CHECK-FMA-WIN-NEXT: vfmsub132ss (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0x9b,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm0 * mem) - xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <4 x float> %a, i64 0
%1 = extractelement <4 x float> %b, i64 0
%.rhs.i = extractelement <4 x float> %c, i64 0
%2 = fsub float -0.000000e+00, %.rhs.i
%3 = tail call float @llvm.fma.f32(float %0, float %1, float %2) #2
%4 = insertelement <4 x float> %a, float %3, i64 0
ret <4 x float> %4
}
define <2 x double> @test_mm_fmsub_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fmsub_sd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsub213sd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xab,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmsub_sd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsub213sd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xab,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmsub_sd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovsd (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7b,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero
; CHECK-FMA-WIN-NEXT: vfmsub132sd (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0x9b,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm0 * mem) - xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <2 x double> %a, i64 0
%1 = extractelement <2 x double> %b, i64 0
%.rhs.i = extractelement <2 x double> %c, i64 0
%2 = fsub double -0.000000e+00, %.rhs.i
%3 = tail call double @llvm.fma.f64(double %0, double %1, double %2) #2
%4 = insertelement <2 x double> %a, double %3, i64 0
ret <2 x double> %4
}
define <4 x float> @test_mm_fnmadd_ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fnmadd_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xac,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmadd_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xac,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmadd_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm1 # encoding: [0xc5,0xf8,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmadd213ps (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0x71,0xac,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm1 * xmm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
%0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %sub.i, <4 x float> %b, <4 x float> %c) #2
ret <4 x float> %0
}
define <2 x double> @test_mm_fnmadd_pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fnmadd_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmadd213pd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xac,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmadd_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmadd213pd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xac,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmadd_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm1 # encoding: [0xc5,0xf9,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmadd213pd (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0xf1,0xac,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm1 * xmm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %a
%0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %sub.i, <2 x double> %b, <2 x double> %c) #2
ret <2 x double> %0
}
define <4 x float> @test_mm_fnmadd_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fnmadd_ss:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmadd213ss %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xad,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmadd_ss:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmadd213ss %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xad,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmadd_ss:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovss (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7a,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero,zero,zero
; CHECK-FMA-WIN-NEXT: vfnmadd132ss (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0x9d,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm0 * mem) + xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <4 x float> %a, i64 0
%.rhs.i = extractelement <4 x float> %b, i64 0
%1 = fsub float -0.000000e+00, %.rhs.i
%2 = extractelement <4 x float> %c, i64 0
%3 = tail call float @llvm.fma.f32(float %0, float %1, float %2) #2
%4 = insertelement <4 x float> %a, float %3, i64 0
ret <4 x float> %4
}
define <2 x double> @test_mm_fnmadd_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fnmadd_sd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmadd213sd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xad,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmadd_sd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmadd213sd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xad,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) + xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmadd_sd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovsd (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7b,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero
; CHECK-FMA-WIN-NEXT: vfnmadd132sd (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0x9d,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm0 * mem) + xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <2 x double> %a, i64 0
%.rhs.i = extractelement <2 x double> %b, i64 0
%1 = fsub double -0.000000e+00, %.rhs.i
%2 = extractelement <2 x double> %c, i64 0
%3 = tail call double @llvm.fma.f64(double %0, double %1, double %2) #2
%4 = insertelement <2 x double> %a, double %3, i64 0
ret <2 x double> %4
}
define <4 x float> @test_mm_fnmsub_ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fnmsub_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmsub213ps %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xae,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmsub_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmsub213ps %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xae,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmsub_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm1 # encoding: [0xc5,0xf8,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmsub213ps (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0x71,0xae,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm1 * xmm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
%sub1.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %sub.i, <4 x float> %b, <4 x float> %sub1.i) #2
ret <4 x float> %0
}
define <2 x double> @test_mm_fnmsub_pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fnmsub_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmsub213pd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xae,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmsub_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmsub213pd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xae,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmsub_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm1 # encoding: [0xc5,0xf9,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmsub213pd (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0xf1,0xae,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm1 * xmm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %a
%sub1.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %c
%0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %sub.i, <2 x double> %b, <2 x double> %sub1.i) #2
ret <2 x double> %0
}
define <4 x float> @test_mm_fnmsub_ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fnmsub_ss:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmsub213ss %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xaf,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmsub_ss:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmsub213ss %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xaf,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmsub_ss:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovss (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7a,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero,zero,zero
; CHECK-FMA-WIN-NEXT: vfnmsub132ss (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0x9f,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm0 * mem) - xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <4 x float> %a, i64 0
%.rhs.i = extractelement <4 x float> %b, i64 0
%1 = fsub float -0.000000e+00, %.rhs.i
%.rhs2.i = extractelement <4 x float> %c, i64 0
%2 = fsub float -0.000000e+00, %.rhs2.i
%3 = tail call float @llvm.fma.f32(float %0, float %1, float %2) #2
%4 = insertelement <4 x float> %a, float %3, i64 0
ret <4 x float> %4
}
define <2 x double> @test_mm_fnmsub_sd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fnmsub_sd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmsub213sd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xaf,0xc2]
; CHECK-FMA-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fnmsub_sd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmsub213sd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xaf,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = -(xmm1 * xmm0) - xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fnmsub_sd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x01]
; CHECK-FMA-WIN-NEXT: vmovsd (%r8), %xmm1 # encoding: [0xc4,0xc1,0x7b,0x10,0x08]
; CHECK-FMA-WIN-NEXT: # xmm1 = mem[0],zero
; CHECK-FMA-WIN-NEXT: vfnmsub132sd (%rdx), %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0x9f,0x02]
; CHECK-FMA-WIN-NEXT: # xmm0 = -(xmm0 * mem) - xmm1
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = extractelement <2 x double> %a, i64 0
%.rhs.i = extractelement <2 x double> %b, i64 0
%1 = fsub double -0.000000e+00, %.rhs.i
%.rhs2.i = extractelement <2 x double> %c, i64 0
%2 = fsub double -0.000000e+00, %.rhs2.i
%3 = tail call double @llvm.fma.f64(double %0, double %1, double %2) #2
%4 = insertelement <2 x double> %a, double %3, i64 0
ret <2 x double> %4
}
define <4 x float> @test_mm_fmaddsub_ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fmaddsub_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmaddsub213ps %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xa6,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) +/- xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmaddsub_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmaddsub213ps %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xa6,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) +/- xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmaddsub_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm1 # encoding: [0xc5,0xf8,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmaddsub213ps (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0x71,0xa6,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) +/- mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
%1 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%2 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %1) #2
%3 = shufflevector <4 x float> %2, <4 x float> %0, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
ret <4 x float> %3
}
define <2 x double> @test_mm_fmaddsub_pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fmaddsub_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmaddsub213pd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xa6,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) +/- xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmaddsub_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmaddsub213pd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xa6,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) +/- xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmaddsub_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm1 # encoding: [0xc5,0xf9,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmaddsub213pd (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0xf1,0xa6,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) +/- mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c) #2
%1 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %c
%2 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %1) #2
%3 = shufflevector <2 x double> %2, <2 x double> %0, <2 x i32> <i32 0, i32 3>
ret <2 x double> %3
}
define <4 x float> @test_mm_fmsubadd_ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-FMA-LABEL: test_mm_fmsubadd_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsubadd213ps %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0x71,0xa7,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) -/+ xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmsubadd_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsubadd213ps %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x71,0xa7,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) -/+ xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmsubadd_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %xmm1 # encoding: [0xc5,0xf8,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %xmm0 # encoding: [0xc5,0xf8,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsubadd213ps (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0x71,0xa7,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) -/+ mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i) #2
%1 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
%2 = shufflevector <4 x float> %1, <4 x float> %0, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
ret <4 x float> %2
}
define <2 x double> @test_mm_fmsubadd_pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-FMA-LABEL: test_mm_fmsubadd_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsubadd213pd %xmm2, %xmm1, %xmm0 # encoding: [0xc4,0xe2,0xf1,0xa7,0xc2]
; CHECK-FMA-NEXT: # xmm0 = (xmm1 * xmm0) -/+ xmm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm_fmsubadd_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsubadd213pd %xmm2, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf1,0xa7,0xc2]
; CHECK-AVX512VL-NEXT: # xmm0 = (xmm1 * xmm0) -/+ xmm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm_fmsubadd_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %xmm1 # encoding: [0xc5,0xf9,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %xmm0 # encoding: [0xc5,0xf9,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsubadd213pd (%r8), %xmm1, %xmm0 # encoding: [0xc4,0xc2,0xf1,0xa7,0x00]
; CHECK-FMA-WIN-NEXT: # xmm0 = (xmm1 * xmm0) -/+ mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %c
%0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %sub.i) #2
%1 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c) #2
%2 = shufflevector <2 x double> %1, <2 x double> %0, <2 x i32> <i32 0, i32 3>
ret <2 x double> %2
}
define <8 x float> @test_mm256_fmadd_ps(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-FMA-LABEL: test_mm256_fmadd_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmadd213ps %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x75,0xa8,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) + ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmadd_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmadd213ps %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x75,0xa8,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) + ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmadd_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %ymm1 # encoding: [0xc5,0xfc,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %ymm0 # encoding: [0xc5,0xfc,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmadd213ps (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0x75,0xa8,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2
ret <8 x float> %0
}
define <4 x double> @test_mm256_fmadd_pd(<4 x double> %a, <4 x double> %b, <4 x double> %c) {
; CHECK-FMA-LABEL: test_mm256_fmadd_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmadd213pd %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0xf5,0xa8,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) + ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmadd_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmadd213pd %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf5,0xa8,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) + ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmadd_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %ymm1 # encoding: [0xc5,0xfd,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %ymm0 # encoding: [0xc5,0xfd,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmadd213pd (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0xf5,0xa8,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c) #2
ret <4 x double> %0
}
define <8 x float> @test_mm256_fmsub_ps(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-FMA-LABEL: test_mm256_fmsub_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsub213ps %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x75,0xaa,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) - ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmsub_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsub213ps %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x75,0xaa,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) - ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmsub_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %ymm1 # encoding: [0xc5,0xfc,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %ymm0 # encoding: [0xc5,0xfc,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsub213ps (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0x75,0xaa,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %sub.i) #2
ret <8 x float> %0
}
define <4 x double> @test_mm256_fmsub_pd(<4 x double> %a, <4 x double> %b, <4 x double> %c) {
; CHECK-FMA-LABEL: test_mm256_fmsub_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsub213pd %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0xf5,0xaa,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) - ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmsub_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsub213pd %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf5,0xaa,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) - ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmsub_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %ymm1 # encoding: [0xc5,0xfd,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %ymm0 # encoding: [0xc5,0xfd,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsub213pd (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0xf5,0xaa,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %c
%0 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %sub.i) #2
ret <4 x double> %0
}
define <8 x float> @test_mm256_fnmadd_ps(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-FMA-LABEL: test_mm256_fnmadd_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x75,0xac,0xc2]
; CHECK-FMA-NEXT: # ymm0 = -(ymm1 * ymm0) + ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fnmadd_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x75,0xac,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = -(ymm1 * ymm0) + ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fnmadd_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %ymm1 # encoding: [0xc5,0xfc,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %ymm0 # encoding: [0xc5,0xfc,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmadd213ps (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0x75,0xac,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = -(ymm1 * ymm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
%0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %sub.i, <8 x float> %b, <8 x float> %c) #2
ret <8 x float> %0
}
define <4 x double> @test_mm256_fnmadd_pd(<4 x double> %a, <4 x double> %b, <4 x double> %c) {
; CHECK-FMA-LABEL: test_mm256_fnmadd_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmadd213pd %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0xf5,0xac,0xc2]
; CHECK-FMA-NEXT: # ymm0 = -(ymm1 * ymm0) + ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fnmadd_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmadd213pd %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf5,0xac,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = -(ymm1 * ymm0) + ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fnmadd_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %ymm1 # encoding: [0xc5,0xfd,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %ymm0 # encoding: [0xc5,0xfd,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmadd213pd (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0xf5,0xac,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = -(ymm1 * ymm0) + mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a
%0 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %sub.i, <4 x double> %b, <4 x double> %c) #2
ret <4 x double> %0
}
define <8 x float> @test_mm256_fnmsub_ps(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-FMA-LABEL: test_mm256_fnmsub_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmsub213ps %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x75,0xae,0xc2]
; CHECK-FMA-NEXT: # ymm0 = -(ymm1 * ymm0) - ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fnmsub_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmsub213ps %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x75,0xae,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = -(ymm1 * ymm0) - ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fnmsub_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %ymm1 # encoding: [0xc5,0xfc,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %ymm0 # encoding: [0xc5,0xfc,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmsub213ps (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0x75,0xae,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = -(ymm1 * ymm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
%sub1.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %sub.i, <8 x float> %b, <8 x float> %sub1.i) #2
ret <8 x float> %0
}
define <4 x double> @test_mm256_fnmsub_pd(<4 x double> %a, <4 x double> %b, <4 x double> %c) {
; CHECK-FMA-LABEL: test_mm256_fnmsub_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfnmsub213pd %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0xf5,0xae,0xc2]
; CHECK-FMA-NEXT: # ymm0 = -(ymm1 * ymm0) - ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fnmsub_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfnmsub213pd %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf5,0xae,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = -(ymm1 * ymm0) - ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fnmsub_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %ymm1 # encoding: [0xc5,0xfd,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %ymm0 # encoding: [0xc5,0xfd,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfnmsub213pd (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0xf5,0xae,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = -(ymm1 * ymm0) - mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a
%sub1.i = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %c
%0 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %sub.i, <4 x double> %b, <4 x double> %sub1.i) #2
ret <4 x double> %0
}
define <8 x float> @test_mm256_fmaddsub_ps(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-FMA-LABEL: test_mm256_fmaddsub_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmaddsub213ps %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x75,0xa6,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) +/- ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmaddsub_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmaddsub213ps %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x75,0xa6,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) +/- ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmaddsub_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %ymm1 # encoding: [0xc5,0xfc,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %ymm0 # encoding: [0xc5,0xfc,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmaddsub213ps (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0x75,0xa6,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) +/- mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2
%1 = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%2 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %1) #2
%3 = shufflevector <8 x float> %2, <8 x float> %0, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
ret <8 x float> %3
}
define <4 x double> @test_mm256_fmaddsub_pd(<4 x double> %a, <4 x double> %b, <4 x double> %c) {
; CHECK-FMA-LABEL: test_mm256_fmaddsub_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmaddsub213pd %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0xf5,0xa6,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) +/- ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmaddsub_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmaddsub213pd %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf5,0xa6,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) +/- ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmaddsub_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %ymm1 # encoding: [0xc5,0xfd,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %ymm0 # encoding: [0xc5,0xfd,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmaddsub213pd (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0xf5,0xa6,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) +/- mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%0 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c) #2
%1 = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %c
%2 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %1) #2
%3 = shufflevector <4 x double> %2, <4 x double> %0, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
ret <4 x double> %3
}
define <8 x float> @test_mm256_fmsubadd_ps(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-FMA-LABEL: test_mm256_fmsubadd_ps:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsubadd213ps %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0x75,0xa7,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) -/+ ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmsubadd_ps:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsubadd213ps %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x75,0xa7,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) -/+ ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmsubadd_ps:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovaps (%rcx), %ymm1 # encoding: [0xc5,0xfc,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovaps (%rdx), %ymm0 # encoding: [0xc5,0xfc,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsubadd213ps (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0x75,0xa7,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) -/+ mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %sub.i) #2
%1 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2
%2 = shufflevector <8 x float> %1, <8 x float> %0, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
ret <8 x float> %2
}
define <4 x double> @test_mm256_fmsubadd_pd(<4 x double> %a, <4 x double> %b, <4 x double> %c) {
; CHECK-FMA-LABEL: test_mm256_fmsubadd_pd:
; CHECK-FMA: # %bb.0: # %entry
; CHECK-FMA-NEXT: vfmsubadd213pd %ymm2, %ymm1, %ymm0 # encoding: [0xc4,0xe2,0xf5,0xa7,0xc2]
; CHECK-FMA-NEXT: # ymm0 = (ymm1 * ymm0) -/+ ymm2
; CHECK-FMA-NEXT: retq # encoding: [0xc3]
;
; CHECK-AVX512VL-LABEL: test_mm256_fmsubadd_pd:
; CHECK-AVX512VL: # %bb.0: # %entry
; CHECK-AVX512VL-NEXT: vfmsubadd213pd %ymm2, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0xf5,0xa7,0xc2]
; CHECK-AVX512VL-NEXT: # ymm0 = (ymm1 * ymm0) -/+ ymm2
; CHECK-AVX512VL-NEXT: retq # encoding: [0xc3]
;
; CHECK-FMA-WIN-LABEL: test_mm256_fmsubadd_pd:
; CHECK-FMA-WIN: # %bb.0: # %entry
; CHECK-FMA-WIN-NEXT: vmovapd (%rcx), %ymm1 # encoding: [0xc5,0xfd,0x28,0x09]
; CHECK-FMA-WIN-NEXT: vmovapd (%rdx), %ymm0 # encoding: [0xc5,0xfd,0x28,0x02]
; CHECK-FMA-WIN-NEXT: vfmsubadd213pd (%r8), %ymm1, %ymm0 # encoding: [0xc4,0xc2,0xf5,0xa7,0x00]
; CHECK-FMA-WIN-NEXT: # ymm0 = (ymm1 * ymm0) -/+ mem
; CHECK-FMA-WIN-NEXT: retq # encoding: [0xc3]
entry:
%sub.i = fsub <4 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %c
%0 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %sub.i) #2
%1 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c) #2
%2 = shufflevector <4 x double> %1, <4 x double> %0, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
ret <4 x double> %2
}
declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>) #1
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) #1
declare float @llvm.fma.f32(float, float, float) #1
declare double @llvm.fma.f64(double, double, double) #1
declare <8 x float> @llvm.fma.v8f32(<8 x float>, <8 x float>, <8 x float>) #1
declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>) #1