Files
TheRock/compiler/amd-llvm/amd/comgr/test-lit/hotswap/rewriter/hotswap-wmma-scale16-32x16-refuse.s
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

58 lines
1.9 KiB
ArmAsm

// COM: Fail-closed gate for the 32x16 FP4 block-16 scaled WMMA. The M=32 form
// COM: needs an M-split on top of the K-split and has no exact lowering yet,
// COM: so the rewrite refuses it: any unlowerable v_wmma_scale16_f32_* makes the
// COM: rewrite return an error instead of emitting a wrong code object.
// RUN: %clang -target amdgcn-amd-amdhsa -mcpu=gfx1250 -nostdlib %s -o %t.elf
// COM: Default mode: presence of the unlowerable form fails the rewrite.
// RUN: hotswap-rewrite %t.elf \
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
// RUN: --expect-status ERROR \
// RUN: | %FileCheck --check-prefix=REFUSE %s
// REFUSE: RESULT: ERROR
// COM: Strict mode: same fail-closed result.
// RUN: hotswap-rewrite %t.elf \
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
// RUN: --strict-mode --expect-status ERROR \
// RUN: | %FileCheck --check-prefix=REFUSE %s
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
.text
// --- Scale16 32x16 FP4 (block-16) -> refuse (fail closed) ---
.globl test_wmma_scale16_32x16
.p2align 8
.type test_wmma_scale16_32x16,@function
test_wmma_scale16_32x16:
v_wmma_scale16_f32_32x16x128_f4 v[0:15], v[16:31], v[32:39], v[0:15], v[40:41], v[42:43]
s_endpgm
.Ltest_wmma_scale16_32x16_end:
.size test_wmma_scale16_32x16, .Ltest_wmma_scale16_32x16_end-test_wmma_scale16_32x16
.rodata
.p2align 8
.amdhsa_kernel test_wmma_scale16_32x16
.amdhsa_next_free_vgpr 44
.amdhsa_next_free_sgpr 2
.amdhsa_wavefront_size32 1
.end_amdhsa_kernel
.amdgpu_metadata
amdhsa.version:
- 3
- 0
amdhsa.kernels:
- .name: test_wmma_scale16_32x16
.symbol: test_wmma_scale16_32x16.kd
.sgpr_count: 2
.vgpr_count: 44
.kernarg_segment_size: 0
.group_segment_fixed_size: 0
.private_segment_fixed_size: 0
.kernarg_segment_align: 8
.wavefront_size: 32
.max_flat_workgroup_size: 256
.end_amdgpu_metadata