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
55 lines
2.1 KiB
LLVM
55 lines
2.1 KiB
LLVM
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -amdgpu-enable-object-linking < %s | FileCheck %s --implicit-check-not=.amdgpu_num_agpr
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -amdgpu-enable-object-linking -filetype=obj < %s | llvm-readobj -r --sections - | FileCheck %s --check-prefix=ELF
|
|
|
|
; Verify object linking codegen for named barriers on GFX1250:
|
|
; 1. Barrier instructions use M0-based forms with relocation references
|
|
; 2. .amdgpu.info section records the barrier as an LDS use edge
|
|
; 3. group_segment_fixed_size = 0 (linker patches it)
|
|
; 4. Named barrier is emitted as an SHN_AMDGPU_LDS symbol (.amdgpu_lds)
|
|
|
|
@bar = internal addrspace(3) global [2 x target("amdgcn.named.barrier", 0)] poison
|
|
|
|
; CHECK-LABEL: kernel:
|
|
; CHECK: s_lshr_b32 s{{[0-9]+}}, __amdgpu_named_barrier.bar{{[^ @]*}}@abs32@lo, 4
|
|
; CHECK: s_barrier_join m0
|
|
; CHECK: s_barrier_signal m0
|
|
; CHECK: s_barrier_wait 1
|
|
|
|
; CHECK: .amdhsa_group_segment_fixed_size 0
|
|
|
|
; CHECK: .amdgpu_info kernel
|
|
; CHECK: .amdgpu_flags {{[0-9]+}}
|
|
; CHECK: .amdgpu_num_sgpr {{[0-9]+}}
|
|
; CHECK: .amdgpu_num_vgpr {{[0-9]+}}
|
|
; CHECK: .amdgpu_private_segment_size {{[0-9]+}}
|
|
; CHECK: .amdgpu_use __amdgpu_named_barrier.bar{{[^ ,]*}}
|
|
; CHECK: .amdgpu_call helper
|
|
; CHECK: .end_amdgpu_info
|
|
|
|
; CHECK: .amdgpu_lds __amdgpu_named_barrier.bar{{[^ ,]*}}, 32, 4
|
|
|
|
; ELF: Section {
|
|
; ELF: Name: .amdgpu.info
|
|
; ELF: Type: SHT_PROGBITS
|
|
; ELF: Flags [
|
|
; ELF: SHF_EXCLUDE
|
|
|
|
; ELF-DAG: R_AMDGPU_ABS64 kernel
|
|
; ELF-DAG: R_AMDGPU_ABS64 __amdgpu_named_barrier.bar{{[^ ]*}}
|
|
; ELF-DAG: R_AMDGPU_ABS64 helper
|
|
|
|
define amdgpu_kernel void @kernel() {
|
|
call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar)
|
|
call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar, i32 3)
|
|
call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
call void @helper()
|
|
ret void
|
|
}
|
|
|
|
declare void @helper()
|
|
declare void @llvm.amdgcn.s.barrier.join(ptr addrspace(3)) #0
|
|
declare void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3), i32) #0
|
|
declare void @llvm.amdgcn.s.barrier.wait(i16) #0
|
|
|
|
attributes #0 = { convergent nounwind }
|