maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[NEON] Support vfma_n and vfms_n intrinsics 

Differential Revision: https://reviews.llvm.org/D45483

llvm-svn: 329814
This commit is contained in:
Ivan A. Kosarev 2018-04-11 14:43:11 +00:00
parent 7c3e14b63b
commit 2f326d453f
2 changed files with 25 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
clang/include/clang/Basic/arm_neon.td
View File

@ -621,8 +621,8 @@ def FMLS : SOpInst<"vfms", "dddd", "dQd", OP_FMLS>;
// MUL, MLA, MLS, FMA, FMS definitions with scalar argument
def VMUL_N_A64 : IOpInst<"vmul_n", "dds", "Qd", OP_MUL_N>;
def FMLA_N : SOpInst<"vfma_n", "ddds", "fQfQd", OP_FMLA_N>;
def FMLS_N : SOpInst<"vfms_n", "ddds", "fQfQd", OP_FMLS_N>;
def FMLA_N : SOpInst<"vfma_n", "ddds", "fdQfQd", OP_FMLA_N>;
def FMLS_N : SOpInst<"vfms_n", "ddds", "fdQfQd", OP_FMLS_N>;
def MLA_N : SOpInst<"vmla_n", "ddds", "Qd", OP_MLA_N>;
def MLS_N : SOpInst<"vmls_n", "ddds", "Qd", OP_MLS_N>;

23
clang/test/CodeGen/aarch64-neon-2velem.c
View File

@ -3083,6 +3083,17 @@ float32x2_t test_vfma_n_f32(float32x2_t a, float32x2_t b, float32_t n) {
return vfma_n_f32(a, b, n);
}
// CHECK-LABEL: @test_vfma_n_f64(
// CHECK: [[VECINIT_I:%.*]] = insertelement <1 x double> undef, double %n, i32 0
// CHECK: [[TMP0:%.*]] = bitcast <1 x double> %a to <8 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <1 x double> %b to <8 x i8>
// CHECK: [[TMP2:%.*]] = bitcast <1 x double> [[VECINIT_I]] to <8 x i8>
// CHECK: [[TMP3:%.*]] = call <1 x double> @llvm.fma.v1f64(<1 x double> %b, <1 x double> [[VECINIT_I]], <1 x double> %a)
// CHECK: ret <1 x double> [[TMP3]]
float64x1_t test_vfma_n_f64(float64x1_t a, float64x1_t b, float64_t n) {
return vfma_n_f64(a, b, n);
}
// CHECK-LABEL: @test_vfmaq_n_f32(
// CHECK: [[VECINIT_I:%.*]] = insertelement <4 x float> undef, float %n, i32 0
// CHECK: [[VECINIT1_I:%.*]] = insertelement <4 x float> [[VECINIT_I]], float %n, i32 1
@ -3110,6 +3121,18 @@ float32x2_t test_vfms_n_f32(float32x2_t a, float32x2_t b, float32_t n) {
return vfms_n_f32(a, b, n);
}
// CHECK-LABEL: @test_vfms_n_f64(
// CHECK: [[SUB_I:%.*]] = fsub <1 x double> <double -0.000000e+00>, %b
// CHECK: [[VECINIT_I:%.*]] = insertelement <1 x double> undef, double %n, i32 0
// CHECK: [[TMP0:%.*]] = bitcast <1 x double> %a to <8 x i8>
// CHECK: [[TMP1:%.*]] = bitcast <1 x double> [[SUB_I]] to <8 x i8>
// CHECK: [[TMP2:%.*]] = bitcast <1 x double> [[VECINIT_I]] to <8 x i8>
// CHECK: [[TMP3:%.*]] = call <1 x double> @llvm.fma.v1f64(<1 x double> [[SUB_I]], <1 x double> [[VECINIT_I]], <1 x double> %a)
// CHECK: ret <1 x double> [[TMP3]]
float64x1_t test_vfms_n_f64(float64x1_t a, float64x1_t b, float64_t n) {
return vfms_n_f64(a, b, n);
}
// CHECK-LABEL: @test_vfmsq_n_f32(
// CHECK: [[SUB_I:%.*]] = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
// CHECK: [[VECINIT_I:%.*]] = insertelement <4 x float> undef, float %n, i32 0