derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
77 lines
3.1 KiB
C
77 lines
3.1 KiB
C
// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs \
|
|
// RUN: -mfloat-abi soft -target-feature +neon -emit-llvm -o - -O1 %s \
|
|
// RUN: | FileCheck %s --check-prefix=CHECK-SOFT
|
|
// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs \
|
|
// RUN: -mfloat-abi hard -target-feature +neon -emit-llvm -o - -O1 %s \
|
|
// RUN: | FileCheck %s --check-prefix=CHECK-HARD
|
|
// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs \
|
|
// RUN: -mfloat-abi hard -target-feature +neon -target-feature +fullfp16 \
|
|
// RUN: -emit-llvm -o - -O1 %s \
|
|
// RUN: | FileCheck %s --check-prefix=CHECK-FULL
|
|
|
|
typedef __attribute__((neon_vector_type(4))) __fp16 float16x4_t;
|
|
typedef __attribute__((neon_vector_type(8))) __fp16 float16x8_t;
|
|
|
|
typedef struct { float16x4_t x[2]; } hfa_t;
|
|
// CHECK-FULL: %struct.hfa_t = type { [2 x <4 x half>] }
|
|
|
|
float16x4_t g4;
|
|
float16x8_t g8;
|
|
|
|
void st4(float16x4_t a) { g4 = a; }
|
|
// CHECK-SOFT: define{{.*}} void @st4(<2 x i32> noundef %a.coerce)
|
|
// CHECK-SOFT: store <2 x i32> %a.coerce, ptr @g4
|
|
//
|
|
// CHECK-HARD: define{{.*}} arm_aapcs_vfpcc void @st4(<2 x i32> noundef %a.coerce)
|
|
// CHECK-HARD: store <2 x i32> %a.coerce, ptr @g4
|
|
//
|
|
// CHECK-FULL: define{{.*}} arm_aapcs_vfpcc void @st4(<4 x half> noundef %a)
|
|
// CHECK-FULL: store <4 x half> %a, ptr @g4
|
|
|
|
float16x4_t ld4(void) { return g4; }
|
|
// CHECK-SOFT: define{{.*}} <2 x i32> @ld4()
|
|
// CHECK-SOFT: %0 = load <2 x i32>, ptr @g4
|
|
// CHECK-SOFT: ret <2 x i32> %0
|
|
//
|
|
// CHECK-HARD: define{{.*}} arm_aapcs_vfpcc <2 x i32> @ld4()
|
|
// CHECK-HARD: %0 = load <2 x i32>, ptr @g4
|
|
// CHECK-HARD: ret <2 x i32> %0
|
|
//
|
|
// CHECK-FULL: define{{.*}} arm_aapcs_vfpcc <4 x half> @ld4()
|
|
// CHECK-FULL: %0 = load <4 x half>, ptr @g4
|
|
// CHECK-FULL: ret <4 x half> %0
|
|
|
|
void st8(float16x8_t a) { g8 = a; }
|
|
// CHECK-SOFT: define{{.*}} void @st8(<4 x i32> noundef %a.coerce)
|
|
// CHECK-SOFT: store <4 x i32> %a.coerce, ptr @g8
|
|
//
|
|
// CHECK-HARD: define{{.*}} arm_aapcs_vfpcc void @st8(<4 x i32> noundef %a.coerce)
|
|
// CHECK-HARD: store <4 x i32> %a.coerce, ptr @g8
|
|
//
|
|
// CHECK-FULL: define{{.*}} arm_aapcs_vfpcc void @st8(<8 x half> noundef %a)
|
|
// CHECK-FULL: store <8 x half> %a, ptr @g8
|
|
|
|
float16x8_t ld8(void) { return g8; }
|
|
// CHECK-SOFT: define{{.*}} <4 x i32> @ld8()
|
|
// CHECK-SOFT: %0 = load <4 x i32>, ptr @g8
|
|
// CHECK-SOFT: ret <4 x i32> %0
|
|
//
|
|
// CHECK-HARD: define{{.*}} arm_aapcs_vfpcc <4 x i32> @ld8()
|
|
// CHECK-HARD: %0 = load <4 x i32>, ptr @g8
|
|
// CHECK-HARD: ret <4 x i32> %0
|
|
//
|
|
// CHECK-FULL: define{{.*}} arm_aapcs_vfpcc <8 x half> @ld8()
|
|
// CHECK-FULL: %0 = load <8 x half>, ptr @g8
|
|
// CHECK-FULL: ret <8 x half> %0
|
|
|
|
void test_hfa(hfa_t a) {}
|
|
// CHECK-SOFT: define{{.*}} void @test_hfa([2 x i64] %a.coerce)
|
|
// CHECK-HARD: define{{.*}} arm_aapcs_vfpcc void @test_hfa([2 x <2 x i32>] %a.coerce)
|
|
// CHECK-FULL: define{{.*}} arm_aapcs_vfpcc void @test_hfa(%struct.hfa_t %a.coerce)
|
|
|
|
hfa_t ghfa;
|
|
hfa_t test_ret_hfa(void) { return ghfa; }
|
|
// CHECK-SOFT: define{{.*}} void @test_ret_hfa(ptr dead_on_unwind noalias writable writeonly sret(%struct.hfa_t) align 8 captures(none) initializes((0, 16)) %agg.result)
|
|
// CHECK-HARD: define{{.*}} arm_aapcs_vfpcc [2 x <2 x i32>] @test_ret_hfa()
|
|
// CHECK-FULL: define{{.*}} arm_aapcs_vfpcc %struct.hfa_t @test_ret_hfa()
|