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
83 lines
3.3 KiB
C
83 lines
3.3 KiB
C
// RUN: %clang_cc1 %s -flax-vector-conversions=none -ffreestanding -triple=x86_64-unknown-unknown -target-feature +avx512f -target-feature +amx-int8 \
|
|
// RUN: -target-feature +amx-bf16 -target-feature +amx-fp16 -emit-llvm -o - -Werror -pedantic | FileCheck %s --check-prefixes=CHECK
|
|
|
|
#include <immintrin.h>
|
|
|
|
char buf[1024];
|
|
#define STRIDE 32
|
|
|
|
char buf2[1024];
|
|
|
|
// This is an example code and integration test.
|
|
void test_api(int cond, short row, short col) {
|
|
//CHECK-LABEL: @test_api
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tileloadd64.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpbssd.internal
|
|
//CHECK-DAG: call void @llvm.x86.tilestored64.internal
|
|
__tile1024i a = {row, 8};
|
|
__tile1024i b = {8, col};
|
|
__tile1024i c = {row, col};
|
|
|
|
if (cond) {
|
|
__tile_loadd(&a, buf, STRIDE);
|
|
__tile_loadd(&b, buf, STRIDE);
|
|
__tile_loadd(&c, buf, STRIDE);
|
|
} else {
|
|
__tile_loadd(&a, buf2, STRIDE);
|
|
__tile_loadd(&b, buf2, STRIDE);
|
|
__tile_loadd(&c, buf2, STRIDE);
|
|
}
|
|
__tile_dpbssd(&c, a, b);
|
|
__tile_stored(buf, STRIDE, c);
|
|
}
|
|
|
|
void test_tile_dpbssd(__tile1024i a, __tile1024i b, __tile1024i c) {
|
|
//CHECK-LABEL: @test_tile_dpbssd
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpbssd.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
__tile_dpbssd(&c, a, b);
|
|
}
|
|
|
|
void test_tile_dpbsud(__tile1024i a, __tile1024i b, __tile1024i c) {
|
|
//CHECK-LABEL: @test_tile_dpbsud
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpbsud.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
__tile_dpbsud(&c, a, b);
|
|
}
|
|
|
|
void test_tile_dpbusd(__tile1024i a, __tile1024i b, __tile1024i c) {
|
|
//CHECK-LABEL: @test_tile_dpbusd
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpbusd.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
__tile_dpbusd(&c, a, b);
|
|
}
|
|
|
|
void test_tile_dpbuud(__tile1024i a, __tile1024i b, __tile1024i c) {
|
|
//CHECK-LABEL: @test_tile_dpbuud
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpbuud.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
__tile_dpbuud(&c, a, b);
|
|
}
|
|
|
|
void test_tile_dpbf16ps(__tile1024i a, __tile1024i b, __tile1024i c) {
|
|
//CHECK-LABEL: @test_tile_dpbf16ps
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpbf16ps.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
__tile_dpbf16ps(&a, b, c);
|
|
}
|
|
|
|
void test_tile_dpfp16ps(__tile1024i a, __tile1024i b, __tile1024i c) {
|
|
//CHECK-LABEL: @test_tile_dpfp16ps
|
|
//CHECK-DAG: call x86_amx @llvm.x86.cast.vector.to.tile.v256i32(<256 x i32> {{%.*}})
|
|
//CHECK-DAG: call x86_amx @llvm.x86.tdpfp16ps.internal
|
|
//CHECK-DAG: call <256 x i32> @llvm.x86.cast.tile.to.vector.v256i32(x86_amx {{%.*}})
|
|
__tile_dpfp16ps(&a, b, c);
|
|
}
|