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
63 lines
2.4 KiB
ArmAsm
63 lines
2.4 KiB
ArmAsm
// COM: Scale16 prefix operands always address bank-zero VGPRs, even when the
|
|
// COM: matrix SRC0/SRC1 roles select nonzero banks through VGPR-MSB. Generated
|
|
// COM: scale values must therefore be produced in the same low-bank registers
|
|
// COM: consumed by each replacement WMMA.
|
|
|
|
// 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 | %FileCheck --check-prefix=RESULT %s
|
|
// RESULT: RESULT: SUCCESS
|
|
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
|
|
// DISASM-LABEL: <test_wmma_scale16_scale_bank_zero>:
|
|
// DISASM-NOT: v_wmma_scale16
|
|
// COM: The gather reads the original scale tuples in bank zero and writes
|
|
// COM: directly addressable low-bank results. Each WMMA consumes those exact
|
|
// COM: result registers rather than their nonzero-bank aliases.
|
|
// DISASM: v_and_b32_e32 [[SCALE_A_LO:v[0-9]+]], 0xff, v48{{[[:space:]]+//}}
|
|
// DISASM: v_and_b32_e32 [[SCALE_B_LO:v[0-9]+]], 0xff, v50{{[[:space:]]+//}}
|
|
// DISASM: v_wmma_scale_f32_16x16x128_f8f6f4 {{.*}}, [[SCALE_A_LO]], [[SCALE_B_LO]]
|
|
|
|
// RUN: hotswap-rewrite %t.out.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --check-idempotent | %FileCheck --check-prefix=IDEM %s
|
|
// IDEM: IDEMPOTENT: YES
|
|
|
|
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
|
|
.text
|
|
.globl test_wmma_scale16_scale_bank_zero
|
|
.p2align 8
|
|
.type test_wmma_scale16_scale_bank_zero,@function
|
|
test_wmma_scale16_scale_bank_zero:
|
|
s_set_vgpr_msb 0x5
|
|
v_wmma_scale16_f32_16x16x128_f8f6f4 v[0:7], v[16:23], v[32:39], v[0:7], v[48:49], v[50:51] matrix_a_fmt:MATRIX_FMT_FP4 matrix_b_fmt:MATRIX_FMT_FP4
|
|
s_endpgm
|
|
.Ltest_wmma_scale16_scale_bank_zero_end:
|
|
.size test_wmma_scale16_scale_bank_zero, .Ltest_wmma_scale16_scale_bank_zero_end-test_wmma_scale16_scale_bank_zero
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel test_wmma_scale16_scale_bank_zero
|
|
.amdhsa_next_free_vgpr 304
|
|
.amdhsa_next_free_sgpr 2
|
|
.amdhsa_wavefront_size32 1
|
|
.end_amdhsa_kernel
|
|
|
|
.amdgpu_metadata
|
|
amdhsa.version:
|
|
- 3
|
|
- 0
|
|
amdhsa.kernels:
|
|
- .name: test_wmma_scale16_scale_bank_zero
|
|
.symbol: test_wmma_scale16_scale_bank_zero.kd
|
|
.sgpr_count: 2
|
|
.vgpr_count: 304
|
|
.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
|