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
75 lines
2.2 KiB
Python
75 lines
2.2 KiB
Python
# RUN: %PYTHON %s | FileCheck %s
|
|
|
|
from mlir.ir import *
|
|
import mlir.dialects.builtin as builtin
|
|
import mlir.dialects.func as func
|
|
import mlir.dialects.x86 as x86
|
|
|
|
|
|
def run(f):
|
|
print("\nTEST:", f.__name__)
|
|
with Context(), Location.unknown():
|
|
f()
|
|
return f
|
|
|
|
|
|
# CHECK-LABEL: TEST: testAvxOp
|
|
@run
|
|
def testAvxOp():
|
|
module = Module.create()
|
|
with InsertionPoint(module.body):
|
|
|
|
@func.FuncOp.from_py_func(MemRefType.get((1,), BF16Type.get()))
|
|
def avx_op(arg):
|
|
return x86.BcstToPackedF32Op(a=arg, dst=VectorType.get((8,), F32Type.get()))
|
|
|
|
# CHECK-LABEL: func @avx_op(
|
|
# CHECK-SAME: %[[ARG:.+]]: memref<1xbf16>) -> vector<8xf32> {
|
|
# CHECK: %[[VAL:.+]] = x86.avx.bcst_to_f32.packed %[[ARG]]
|
|
# CHECK: return %[[VAL]] : vector<8xf32>
|
|
# CHECK: }
|
|
print(module)
|
|
|
|
|
|
# CHECK-LABEL: TEST: testAvx512Op
|
|
@run
|
|
def testAvx512Op():
|
|
module = Module.create()
|
|
with InsertionPoint(module.body):
|
|
|
|
@func.FuncOp.from_py_func(VectorType.get((8,), F32Type.get()))
|
|
def avx512_op(arg):
|
|
return x86.CvtPackedF32ToBF16Op(
|
|
a=arg, dst=VectorType.get((8,), BF16Type.get())
|
|
)
|
|
|
|
# CHECK-LABEL: func @avx512_op(
|
|
# CHECK-SAME: %[[ARG:.+]]: vector<8xf32>) -> vector<8xbf16> {
|
|
# CHECK: %[[VAL:.+]] = x86.avx512.cvt.packed.f32_to_bf16 %[[ARG]]
|
|
# CHECK: return %[[VAL]] : vector<8xbf16>
|
|
# CHECK: }
|
|
print(module)
|
|
|
|
|
|
# CHECK-LABEL: TEST: testAvx10Op
|
|
@run
|
|
def testAvx10Op():
|
|
module = Module.create()
|
|
with InsertionPoint(module.body):
|
|
|
|
@func.FuncOp.from_py_func(
|
|
VectorType.get((16,), IntegerType.get(32)),
|
|
VectorType.get((64,), IntegerType.get(8)),
|
|
VectorType.get((64,), IntegerType.get(8)),
|
|
)
|
|
def avx10_op(*args):
|
|
return x86.AVX10DotInt8Op(w=args[0], a=args[1], b=args[2])
|
|
|
|
# CHECK-LABEL: func @avx10_op(
|
|
# CHECK-SAME: %[[W:.+]]: vector<16xi32>, %[[A:.+]]: vector<64xi8>,
|
|
# CHECK-SAME: %[[B:.+]]: vector<64xi8>) -> vector<16xi32> {
|
|
# CHECK: %[[VAL:.+]] = x86.avx10.dot.i8 %[[W]], %[[A]], %[[B]]
|
|
# CHECK: return %[[VAL]] : vector<16xi32>
|
|
# CHECK: }
|
|
print(module)
|