6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-13 04:30:23 +00:00
Code Issues Projects Releases Wiki Activity

AArch64/ARM64: mark fmul intrinsic as commutative.

Browse Source 
This gives DAG patterns matching indexed patterns where either side is an
indexed vector.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206875 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tim Northover 2014-04-22 10:10:14 +00:00
parent 74bd57b16b
commit 85974bc77e
3 changed files with 128 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
include/llvm/IR/IntrinsicsARM64.td
View File

@ -189,7 +189,9 @@ let Properties = [IntrNoMem] in {
Intrinsic<[llvm_v16i8_ty], [llvm_i64_ty, llvm_i64_ty], [IntrNoMem]>;
// Vector Extending Multiply
def int_arm64_neon_fmulx : AdvSIMD_2FloatArg_Intrinsic;
def int_arm64_neon_fmulx : AdvSIMD_2FloatArg_Intrinsic {
let Properties = [IntrNoMem, Commutative];
}
// Vector Saturating Doubling Long Multiply
def int_arm64_neon_sqdmull : AdvSIMD_2VectorArg_Long_Intrinsic;

2
test/CodeGen/AArch64/neon-scalar-by-elem-mul.ll
View File

@ -1,5 +1,5 @@
; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon -fp-contract=fast | FileCheck %s
; arm64 has separate copy due to intrinsics (aarch64-neon-scalar-by-elem-mul.ll)
define float @test_fmul_lane_ss2S(float %a, <2 x float> %v) {
; CHECK: test_fmul_lane_ss2S
; CHECK: fmul {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[1]

124
test/CodeGen/ARM64/aarch64-neon-scalar-by-elem-mul.ll Normal file
View File

@ -0,0 +1,124 @@
; RUN: llc < %s -verify-machineinstrs -mtriple=arm64-none-linux-gnu -mattr=+neon -fp-contract=fast | FileCheck %s
define float @test_fmul_lane_ss2S(float %a, <2 x float> %v) {
; CHECK-LABEL: test_fmul_lane_ss2S
; CHECK: fmul {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[1]
%tmp1 = extractelement <2 x float> %v, i32 1
%tmp2 = fmul float %a, %tmp1;
ret float %tmp2;
}
define float @test_fmul_lane_ss2S_swap(float %a, <2 x float> %v) {
; CHECK-LABEL: test_fmul_lane_ss2S_swap
; CHECK: fmul {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[1]
%tmp1 = extractelement <2 x float> %v, i32 1
%tmp2 = fmul float %tmp1, %a;
ret float %tmp2;
}
define float @test_fmul_lane_ss4S(float %a, <4 x float> %v) {
; CHECK-LABEL: test_fmul_lane_ss4S
; CHECK: fmul {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = fmul float %a, %tmp1;
ret float %tmp2;
}
define float @test_fmul_lane_ss4S_swap(float %a, <4 x float> %v) {
; CHECK-LABEL: test_fmul_lane_ss4S_swap
; CHECK: fmul {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = fmul float %tmp1, %a;
ret float %tmp2;
}
define double @test_fmul_lane_ddD(double %a, <1 x double> %v) {
; CHECK-LABEL: test_fmul_lane_ddD
; CHECK: fmul {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+.d\[0]|d[0-9]+}}
%tmp1 = extractelement <1 x double> %v, i32 0
%tmp2 = fmul double %a, %tmp1;
ret double %tmp2;
}
define double @test_fmul_lane_dd2D(double %a, <2 x double> %v) {
; CHECK-LABEL: test_fmul_lane_dd2D
; CHECK: fmul {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = fmul double %a, %tmp1;
ret double %tmp2;
}
define double @test_fmul_lane_dd2D_swap(double %a, <2 x double> %v) {
; CHECK-LABEL: test_fmul_lane_dd2D_swap
; CHECK: fmul {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = fmul double %tmp1, %a;
ret double %tmp2;
}
declare float @llvm.arm64.neon.fmulx.f32(float, float)
define float @test_fmulx_lane_f32(float %a, <2 x float> %v) {
; CHECK-LABEL: test_fmulx_lane_f32
; CHECK: fmulx {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[1]
%tmp1 = extractelement <2 x float> %v, i32 1
%tmp2 = call float @llvm.arm64.neon.fmulx.f32(float %a, float %tmp1)
ret float %tmp2;
}
define float @test_fmulx_laneq_f32(float %a, <4 x float> %v) {
; CHECK-LABEL: test_fmulx_laneq_f32
; CHECK: fmulx {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = call float @llvm.arm64.neon.fmulx.f32(float %a, float %tmp1)
ret float %tmp2;
}
define float @test_fmulx_laneq_f32_swap(float %a, <4 x float> %v) {
; CHECK-LABEL: test_fmulx_laneq_f32_swap
; CHECK: fmulx {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = call float @llvm.arm64.neon.fmulx.f32(float %tmp1, float %a)
ret float %tmp2;
}
declare double @llvm.arm64.neon.fmulx.f64(double, double)
define double @test_fmulx_lane_f64(double %a, <1 x double> %v) {
; CHECK-LABEL: test_fmulx_lane_f64
; CHECK: fmulx {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+.d\[0]|d[0-9]+}}
%tmp1 = extractelement <1 x double> %v, i32 0
%tmp2 = call double @llvm.arm64.neon.fmulx.f64(double %a, double %tmp1)
ret double %tmp2;
}
define double @test_fmulx_laneq_f64_0(double %a, <2 x double> %v) {
; CHECK-LABEL: test_fmulx_laneq_f64_0
; CHECK: fmulx {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+}}.d[0]
%tmp1 = extractelement <2 x double> %v, i32 0
%tmp2 = call double @llvm.arm64.neon.fmulx.f64(double %a, double %tmp1)
ret double %tmp2;
}
define double @test_fmulx_laneq_f64_1(double %a, <2 x double> %v) {
; CHECK-LABEL: test_fmulx_laneq_f64_1
; CHECK: fmulx {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = call double @llvm.arm64.neon.fmulx.f64(double %a, double %tmp1)
ret double %tmp2;
}
define double @test_fmulx_laneq_f64_1_swap(double %a, <2 x double> %v) {
; CHECK-LABEL: test_fmulx_laneq_f64_1_swap
; CHECK: fmulx {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-9]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = call double @llvm.arm64.neon.fmulx.f64(double %tmp1, double %a)
ret double %tmp2;
}