forked from OSchip/llvm-project
152 lines
5.4 KiB
C
152 lines
5.4 KiB
C
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
|
|
// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature +neon -target-feature +bf16 \
|
|
// RUN: -disable-O0-optnone -emit-llvm %s -o - | opt -S -mem2reg -instcombine | FileCheck %s
|
|
|
|
#include <arm_neon.h>
|
|
|
|
// CHECK-LABEL: @test_vcreate_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = bitcast i64 [[A:%.*]] to <4 x bfloat>
|
|
// CHECK-NEXT: ret <4 x bfloat> [[TMP0]]
|
|
//
|
|
bfloat16x4_t test_vcreate_bf16(uint64_t a) {
|
|
return vcreate_bf16(a);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vdup_n_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[VECINIT_I:%.*]] = insertelement <4 x bfloat> undef, bfloat [[V:%.*]], i32 0
|
|
// CHECK-NEXT: [[VECINIT3_I:%.*]] = shufflevector <4 x bfloat> [[VECINIT_I]], <4 x bfloat> undef, <4 x i32> zeroinitializer
|
|
// CHECK-NEXT: ret <4 x bfloat> [[VECINIT3_I]]
|
|
//
|
|
bfloat16x4_t test_vdup_n_bf16(bfloat16_t v) {
|
|
return vdup_n_bf16(v);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vdupq_n_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[VECINIT_I:%.*]] = insertelement <8 x bfloat> undef, bfloat [[V:%.*]], i32 0
|
|
// CHECK-NEXT: [[VECINIT7_I:%.*]] = shufflevector <8 x bfloat> [[VECINIT_I]], <8 x bfloat> undef, <8 x i32> zeroinitializer
|
|
// CHECK-NEXT: ret <8 x bfloat> [[VECINIT7_I]]
|
|
//
|
|
bfloat16x8_t test_vdupq_n_bf16(bfloat16_t v) {
|
|
return vdupq_n_bf16(v);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vdup_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[LANE:%.*]] = shufflevector <4 x bfloat> [[V:%.*]], <4 x bfloat> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
|
|
// CHECK-NEXT: ret <4 x bfloat> [[LANE]]
|
|
//
|
|
bfloat16x4_t test_vdup_lane_bf16(bfloat16x4_t v) {
|
|
return vdup_lane_bf16(v, 1);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vdupq_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[LANE:%.*]] = shufflevector <4 x bfloat> [[V:%.*]], <4 x bfloat> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
|
|
// CHECK-NEXT: ret <8 x bfloat> [[LANE]]
|
|
//
|
|
bfloat16x8_t test_vdupq_lane_bf16(bfloat16x4_t v) {
|
|
return vdupq_lane_bf16(v, 1);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vdup_laneq_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[LANE:%.*]] = shufflevector <8 x bfloat> [[V:%.*]], <8 x bfloat> undef, <4 x i32> <i32 7, i32 7, i32 7, i32 7>
|
|
// CHECK-NEXT: ret <4 x bfloat> [[LANE]]
|
|
//
|
|
bfloat16x4_t test_vdup_laneq_bf16(bfloat16x8_t v) {
|
|
return vdup_laneq_bf16(v, 7);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vdupq_laneq_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[LANE:%.*]] = shufflevector <8 x bfloat> [[V:%.*]], <8 x bfloat> undef, <8 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
|
|
// CHECK-NEXT: ret <8 x bfloat> [[LANE]]
|
|
//
|
|
bfloat16x8_t test_vdupq_laneq_bf16(bfloat16x8_t v) {
|
|
return vdupq_laneq_bf16(v, 7);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vcombine_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[SHUFFLE_I:%.*]] = shufflevector <4 x bfloat> [[LOW:%.*]], <4 x bfloat> [[HIGH:%.*]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
// CHECK-NEXT: ret <8 x bfloat> [[SHUFFLE_I]]
|
|
//
|
|
bfloat16x8_t test_vcombine_bf16(bfloat16x4_t low, bfloat16x4_t high) {
|
|
return vcombine_bf16(low, high);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vget_high_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[SHUFFLE_I:%.*]] = shufflevector <8 x bfloat> [[A:%.*]], <8 x bfloat> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
// CHECK-NEXT: ret <4 x bfloat> [[SHUFFLE_I]]
|
|
//
|
|
bfloat16x4_t test_vget_high_bf16(bfloat16x8_t a) {
|
|
return vget_high_bf16(a);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vget_low_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[SHUFFLE_I:%.*]] = shufflevector <8 x bfloat> [[A:%.*]], <8 x bfloat> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
// CHECK-NEXT: ret <4 x bfloat> [[SHUFFLE_I]]
|
|
//
|
|
bfloat16x4_t test_vget_low_bf16(bfloat16x8_t a) {
|
|
return vget_low_bf16(a);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vget_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[DOTCAST1:%.*]] = extractelement <4 x bfloat> [[V:%.*]], i32 1
|
|
// CHECK-NEXT: ret bfloat [[DOTCAST1]]
|
|
//
|
|
bfloat16_t test_vget_lane_bf16(bfloat16x4_t v) {
|
|
return vget_lane_bf16(v, 1);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vgetq_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[DOTCAST1:%.*]] = extractelement <8 x bfloat> [[V:%.*]], i32 7
|
|
// CHECK-NEXT: ret bfloat [[DOTCAST1]]
|
|
//
|
|
bfloat16_t test_vgetq_lane_bf16(bfloat16x8_t v) {
|
|
return vgetq_lane_bf16(v, 7);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vset_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x bfloat> [[V:%.*]], bfloat [[A:%.*]], i32 1
|
|
// CHECK-NEXT: ret <4 x bfloat> [[TMP0]]
|
|
//
|
|
bfloat16x4_t test_vset_lane_bf16(bfloat16_t a, bfloat16x4_t v) {
|
|
return vset_lane_bf16(a, v, 1);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vsetq_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = insertelement <8 x bfloat> [[V:%.*]], bfloat [[A:%.*]], i32 7
|
|
// CHECK-NEXT: ret <8 x bfloat> [[TMP0]]
|
|
//
|
|
bfloat16x8_t test_vsetq_lane_bf16(bfloat16_t a, bfloat16x8_t v) {
|
|
return vsetq_lane_bf16(a, v, 7);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vduph_lane_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[VGET_LANE:%.*]] = extractelement <4 x bfloat> [[V:%.*]], i32 1
|
|
// CHECK-NEXT: ret bfloat [[VGET_LANE]]
|
|
//
|
|
bfloat16_t test_vduph_lane_bf16(bfloat16x4_t v) {
|
|
return vduph_lane_bf16(v, 1);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_vduph_laneq_bf16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[VGETQ_LANE:%.*]] = extractelement <8 x bfloat> [[V:%.*]], i32 7
|
|
// CHECK-NEXT: ret bfloat [[VGETQ_LANE]]
|
|
//
|
|
bfloat16_t test_vduph_laneq_bf16(bfloat16x8_t v) {
|
|
return vduph_laneq_bf16(v, 7);
|
|
}
|