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
43 lines
1.6 KiB
ArmAsm
43 lines
1.6 KiB
ArmAsm
// Test M-split with neg_lo:[0,0,1] on src2.
|
|
//
|
|
// Differs from K-split: M-split has no carry, so the original src2's
|
|
// modifier applies to BOTH halves (each half has its own M-slice of
|
|
// src2). The MATRIX_FMT_FP4 modifiers added by the splitter come BEFORE
|
|
// the preserved neg_lo, mirroring how the printer orders them.
|
|
|
|
// RUN: %clang -target amdgcn-amd-amdhsa -mcpu=gfx1250 -nostdlib %s -o %t.elf
|
|
|
|
// RUN: hotswap-rewrite %t.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --output %t.out.elf \
|
|
// RUN: | %FileCheck --check-prefix=API %s
|
|
// API: RESULT: SUCCESS
|
|
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
|
|
|
|
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
|
|
|
|
// DISASM-LABEL: <kernel>:
|
|
// DISASM-NOT: v_wmma_f32_32x16x128_f4
|
|
// DISASM: s_branch
|
|
// DISASM: s_endpgm
|
|
|
|
// DISASM: v_wmma_f32_16x16x128_f8f6f4 v[80:87], v[0:7], v[2:9], v[80:87] matrix_a_fmt:MATRIX_FMT_FP4 matrix_b_fmt:MATRIX_FMT_FP4 neg_lo:[0,0,1]
|
|
// DISASM-NEXT: v_wmma_f32_16x16x128_f8f6f4 v[88:95], v[8:15], v[2:9], v[88:95] matrix_a_fmt:MATRIX_FMT_FP4 matrix_b_fmt:MATRIX_FMT_FP4 neg_lo:[0,0,1]
|
|
// DISASM-NEXT: s_branch
|
|
.globl kernel
|
|
.p2align 8
|
|
.type kernel,@function
|
|
kernel:
|
|
v_wmma_f32_32x16x128_f4 v[80:95], v[0:15], v[2:9], v[80:95] neg_lo:[0,0,1]
|
|
s_endpgm
|
|
.size kernel, .-kernel
|
|
|
|
// Idempotency.
|
|
// RUN: hotswap-rewrite %t.out.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --output %t.out2.elf \
|
|
// RUN: | %FileCheck --check-prefix=API2 %s
|
|
// API2: RESULT: SUCCESS
|
|
// RUN: cmp %t.out.elf %t.out2.elf
|