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
52 lines
1.6 KiB
C
52 lines
1.6 KiB
C
// RUN: %clang -emit-llvm -S -fenable-matrix -mllvm -disable-llvm-optzns %s -o - | FileCheck %s
|
|
// UNSUPPORTED: target={{.*}}-zos{{.*}}
|
|
|
|
typedef float fx2x2_t __attribute__((matrix_type(2, 2)));
|
|
typedef int ix2x2_t __attribute__((matrix_type(2, 2)));
|
|
|
|
fx2x2_t fp_matrix_contract(fx2x2_t a, fx2x2_t b, float c, float d) {
|
|
// CHECK: call contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
|
|
// CHECK: fdiv contract <4 x float>
|
|
// CHECK: fmul contract <4 x float>
|
|
#pragma clang fp contract(fast)
|
|
return (a * b / c) * d;
|
|
}
|
|
|
|
fx2x2_t fp_matrix_reassoc(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
|
|
// CHECK: fadd reassoc <4 x float>
|
|
// CHECK: fsub reassoc <4 x float>
|
|
#pragma clang fp reassociate(on)
|
|
return a + b - c;
|
|
}
|
|
|
|
fx2x2_t fp_matrix_ops(fx2x2_t a, fx2x2_t b, fx2x2_t c) {
|
|
// CHECK: call reassoc contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
|
|
// CHECK: fadd reassoc contract <4 x float>
|
|
#pragma clang fp contract(fast) reassociate(on)
|
|
return a * b + c;
|
|
}
|
|
|
|
fx2x2_t fp_matrix_compound_ops(fx2x2_t a, fx2x2_t b, fx2x2_t c, fx2x2_t d,
|
|
float e, float f) {
|
|
// CHECK: call reassoc contract <4 x float> @llvm.matrix.multiply.v4f32.v4f32.v4f32
|
|
// CHECK: fadd reassoc contract <4 x float>
|
|
// CHECK: fsub reassoc contract <4 x float>
|
|
// CHECK: fmul reassoc contract <4 x float>
|
|
// CHECK: fdiv reassoc contract <4 x float>
|
|
#pragma clang fp contract(fast) reassociate(on)
|
|
a *= b;
|
|
a += c;
|
|
a -= d;
|
|
a *= e;
|
|
a /= f;
|
|
|
|
return a;
|
|
}
|
|
|
|
ix2x2_t int_matrix_ops(ix2x2_t a, ix2x2_t b, ix2x2_t c) {
|
|
// CHECK: call <4 x i32> @llvm.matrix.multiply.v4i32.v4i32.v4i32
|
|
// CHECK: add <4 x i32>
|
|
#pragma clang fp contract(fast) reassociate(on)
|
|
return a * b + c;
|
|
}
|