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
2.3 KiB
MLIR
52 lines
2.3 KiB
MLIR
// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
|
|
|
|
// CHECK-LABEL: @convert_f32x2_to_f4x2_e2m1
|
|
llvm.func @convert_f32x2_to_f4x2_e2m1(%srcA : f32, %srcB : f32) {
|
|
// CHECK: %[[res1:.*]] = call i16 @llvm.nvvm.ff.to.e2m1x2.rn.satfinite(float %{{.*}}, float %{{.*}})
|
|
// CHECK-NEXT: %{{.*}} = trunc i16 %[[res1]] to i8
|
|
%res1 = nvvm.convert.f32x2.to.f4x2 %srcA, %srcB : i8 (f4E2M1FN)
|
|
// CHECK: %[[res2:.*]] = call i16 @llvm.nvvm.ff.to.e2m1x2.rn.relu.satfinite(float %{{.*}}, float %{{.*}})
|
|
// CHECK-NEXT: %{{.*}} = trunc i16 %[[res2]] to i8
|
|
%res2 = nvvm.convert.f32x2.to.f4x2 %srcA, %srcB {relu = true} : i8 (f4E2M1FN)
|
|
llvm.return
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: @convert_f16x2_to_f4x2
|
|
llvm.func @convert_f16x2_to_f4x2(%srcA : vector<2xf16>) {
|
|
// CHECK: %[[res1:.*]] = call i16 @llvm.nvvm.f16x2.to.e2m1x2.rn.satfinite(<2 x half> %{{.*}})
|
|
// CHECK-NEXT: %{{.*}} = trunc i16 %[[res1]] to i8
|
|
%res1 = nvvm.convert.f16x2.to.f4x2 %srcA : vector<2xf16> -> i8 (f4E2M1FN)
|
|
// CHECK: %[[res2:.*]] = call i16 @llvm.nvvm.f16x2.to.e2m1x2.rn.relu.satfinite(<2 x half> %{{.*}})
|
|
// CHECK-NEXT: %{{.*}} = trunc i16 %[[res2]] to i8
|
|
%res2 = nvvm.convert.f16x2.to.f4x2 %srcA {relu = true} : vector<2xf16> -> i8 (f4E2M1FN)
|
|
llvm.return
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: @convert_bf16x2_to_f4x2
|
|
llvm.func @convert_bf16x2_to_f4x2(%srcA : vector<2xbf16>) {
|
|
// CHECK: %[[res1:.*]] = call i16 @llvm.nvvm.bf16x2.to.e2m1x2.rn.satfinite(<2 x bfloat> %{{.*}})
|
|
// CHECK-NEXT: %{{.*}} = trunc i16 %[[res1]] to i8
|
|
%res1 = nvvm.convert.bf16x2.to.f4x2 %srcA : vector<2xbf16> -> i8 (f4E2M1FN)
|
|
// CHECK: %[[res2:.*]] = call i16 @llvm.nvvm.bf16x2.to.e2m1x2.rn.relu.satfinite(<2 x bfloat> %{{.*}})
|
|
// CHECK-NEXT: %{{.*}} = trunc i16 %[[res2]] to i8
|
|
%res2 = nvvm.convert.bf16x2.to.f4x2 %srcA {relu = true} : vector<2xbf16> -> i8 (f4E2M1FN)
|
|
llvm.return
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: @convert_f4x2_to_f16x2
|
|
llvm.func @convert_f4x2_to_f16x2(%src : i8) {
|
|
// CHECK: %[[res1:.*]] = zext i8 %{{.*}} to i16
|
|
// CHECK-NEXT: %{{.*}} = call <2 x half> @llvm.nvvm.e2m1x2.to.f16x2.rn(i16 %[[res1]])
|
|
%res1 = nvvm.convert.f4x2.to.f16x2 %src : i8 (f4E2M1FN)-> vector<2xf16>
|
|
// CHECK: %[[res2:.*]] = zext i8 %{{.*}} to i16
|
|
// CHECK-NEXT: %{{.*}} = call <2 x half> @llvm.nvvm.e2m1x2.to.f16x2.rn.relu(i16 %[[res2]])
|
|
%res2 = nvvm.convert.f4x2.to.f16x2 %src {relu = true} : i8 (f4E2M1FN)-> vector<2xf16>
|
|
llvm.return
|
|
}
|