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
118 lines
3.3 KiB
ArmAsm
118 lines
3.3 KiB
ArmAsm
// COM: A far patch can live in a zero-size ordinary device function shared by
|
|
// COM: multiple kernels. The tensor descriptor save and set-PC return safely
|
|
// COM: reuse one global scratch block, charged to both possible callers. The
|
|
// COM: missing .size directive exercises zero-size function-range inference on
|
|
// COM: the far path.
|
|
|
|
// 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=API %s
|
|
// API: RESULT: SUCCESS
|
|
|
|
// RUN: %llvm-objdump -d %t.out.elf | %FileCheck --check-prefix=DISASM \
|
|
// RUN: --implicit-check-not=s_add_pc_i64 %s
|
|
// RUN: %llvm-readelf --notes %t.out.elf | %FileCheck --check-prefix=META %s
|
|
|
|
// DISASM-LABEL: <device_tensor>:
|
|
// DISASM-NEXT: s_branch
|
|
// DISASM-NEXT: s_nop
|
|
// DISASM-NEXT: s_nop
|
|
// DISASM-LABEL: <kernel_b>:
|
|
// DISASM: s_endpgm
|
|
// DISASM-NEXT: s_get_pc_i64 s[66:67]
|
|
// DISASM-NEXT: s_add_nc_u64 s[66:67], s[66:67],
|
|
// DISASM-NEXT: s_set_pc_i64 s[66:67]
|
|
// DISASM: s_mov_b32 s66, s4
|
|
// DISASM-NEXT: s_pack_hh_b32_b16 s4, 0, s4
|
|
// DISASM-NEXT: tensor_load_to_lds s[0:3], s[4:11]
|
|
// DISASM-NEXT: s_mov_b32 s4, s66
|
|
// DISASM-NEXT: s_get_pc_i64 s[66:67]
|
|
// DISASM-NEXT: s_add_nc_u64 s[66:67], s[66:67],
|
|
// DISASM-NEXT: s_set_pc_i64 s[66:67]
|
|
|
|
// META: .name: kernel_a
|
|
// META: .sgpr_count: 70
|
|
// META: .name: kernel_b
|
|
// META: .sgpr_count: 70
|
|
|
|
// 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
|
|
.local device_tensor
|
|
.type device_tensor,@function
|
|
device_tensor:
|
|
tensor_load_to_lds s[0:3], s[4:11]
|
|
s_set_pc_i64 s[30:31]
|
|
|
|
.globl kernel_a
|
|
.type kernel_a,@function
|
|
kernel_a:
|
|
s_call_i64 s[30:31], device_tensor
|
|
s_endpgm
|
|
.Lkernel_a_end:
|
|
.size kernel_a, .Lkernel_a_end-kernel_a
|
|
|
|
.globl kernel_b
|
|
.type kernel_b,@function
|
|
kernel_b:
|
|
s_call_i64 s[30:31], device_tensor
|
|
s_endpgm
|
|
.Lkernel_b_end:
|
|
.size kernel_b, .Lkernel_b_end-kernel_b
|
|
|
|
// Safe external gateway space: it follows a no-fallthrough instruction and is
|
|
// outside every function range, so it cannot be executed by fallthrough.
|
|
.rept 8
|
|
s_nop 0
|
|
.endr
|
|
|
|
// Push the appended trampoline pool beyond s_branch reach without extending
|
|
// any function symbol range.
|
|
.rept 40000
|
|
s_mov_b32 s64, s65
|
|
.endr
|
|
|
|
.rodata
|
|
.p2align 8
|
|
.amdhsa_kernel kernel_a
|
|
.amdhsa_next_free_vgpr 1
|
|
.amdhsa_next_free_sgpr 48
|
|
.end_amdhsa_kernel
|
|
|
|
.amdhsa_kernel kernel_b
|
|
.amdhsa_next_free_vgpr 1
|
|
.amdhsa_next_free_sgpr 48
|
|
.end_amdhsa_kernel
|
|
|
|
.amdgpu_metadata
|
|
amdhsa.version:
|
|
- 3
|
|
- 0
|
|
amdhsa.kernels:
|
|
- .name: kernel_a
|
|
.symbol: kernel_a.kd
|
|
.sgpr_count: 48
|
|
.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
|
|
- .name: kernel_b
|
|
.symbol: kernel_b.kd
|
|
.sgpr_count: 48
|
|
.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
|