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
72 lines
2.4 KiB
ArmAsm
72 lines
2.4 KiB
ArmAsm
// COM: The motivating case: the SGPR budget is saturated to s106 and the
|
|
// COM: descriptor feeds two tensors, so the at-site fallback cannot safely
|
|
// COM: modify the first use without a scratch register. The definition-time
|
|
// COM: clear applies because both consumers require the cleared descriptor.
|
|
// COM: There is no NOP sled or spare SGPR.
|
|
|
|
// RUN: %clang -target amdgcn-amd-amdhsa -mcpu=gfx1250 -nostdlib %s -o %t.elf
|
|
|
|
// RUN: env AMD_COMGR_EMIT_VERBOSE_LOGS=1 hotswap-rewrite %t.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --output %t.out.elf \
|
|
// RUN: 2>&1 \
|
|
// RUN: | %FileCheck --check-prefix=API %s
|
|
// API: hotswap: tensor_load_to_lds: cleared workgroup_mask at descriptor definition 0x{{[0-9A-F]+}} (s4)
|
|
// API-NOT: no scratch SGPR available
|
|
// API: RESULT: SUCCESS
|
|
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM %s
|
|
// DISASM-LABEL: <test_tensor_mask_saturated>:
|
|
// DISASM: s_and_b32 s4, s4, 0xfff70000
|
|
// DISASM-NOT: s_pack_hh_b32_b16
|
|
// DISASM: tensor_load_to_lds s[0:3], s[4:11]
|
|
// DISASM-NEXT: tensor_load_to_lds s[0:3], s[4:11]
|
|
|
|
// COM: Idempotency: a second rewrite of the shared saturated descriptor makes
|
|
// COM: no further change.
|
|
// RUN: hotswap-rewrite %t.out.elf \
|
|
// RUN: amdgcn-amd-amdhsa--gfx1250 amdgcn-amd-amdhsa--gfx1250 \
|
|
// RUN: --check-idempotent \
|
|
// RUN: | %FileCheck --check-prefix=IDEM %s
|
|
// IDEM: IDEMPOTENT: YES
|
|
|
|
.amdgcn_target "amdgcn-amd-amdhsa--gfx1250"
|
|
.text
|
|
.globl test_tensor_mask_saturated
|
|
.p2align 8
|
|
.type test_tensor_mask_saturated,@function
|
|
test_tensor_mask_saturated:
|
|
s_mov_b32 s4, 0
|
|
s_and_b32 s4, s4, 0xfffcffff
|
|
s_or_b32 s4, s4, s5
|
|
s_and_b32 s4, s4, 0xfff7ffff
|
|
tensor_load_to_lds s[0:3], s[4:11]
|
|
tensor_load_to_lds s[0:3], s[4:11]
|
|
s_endpgm
|
|
.Ltest_tensor_mask_saturated_end:
|
|
.size test_tensor_mask_saturated, .Ltest_tensor_mask_saturated_end-test_tensor_mask_saturated
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel test_tensor_mask_saturated
|
|
.amdhsa_next_free_vgpr 1
|
|
.amdhsa_next_free_sgpr 106
|
|
.end_amdhsa_kernel
|
|
|
|
.amdgpu_metadata
|
|
amdhsa.version:
|
|
- 3
|
|
- 0
|
|
amdhsa.kernels:
|
|
- .name: test_tensor_mask_saturated
|
|
.symbol: test_tensor_mask_saturated.kd
|
|
.sgpr_count: 106
|
|
.vgpr_count: 1
|
|
.kernarg_segment_size: 0
|
|
.group_segment_fixed_size: 0
|
|
.private_segment_fixed_size: 0
|
|
.kernarg_segment_align: 8
|
|
.wavefront_size: 64
|
|
.max_flat_workgroup_size: 256
|
|
.end_amdgpu_metadata
|