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
2.9 KiB
LLVM
72 lines
2.9 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck --check-prefix=SI --check-prefix=CHECK %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck --check-prefix=CI --check-prefix=CHECK %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck --check-prefix=CI --check-prefix=CHECK %s
|
|
|
|
define amdgpu_kernel void @use_gep_address_space(ptr addrspace(3) %array) nounwind {
|
|
; CHECK-LABEL: {{^}}use_gep_address_space:
|
|
; CHECK: v_mov_b32_e32 [[PTR:v[0-9]+]], s{{[0-9]+}}
|
|
; CHECK: ds_write_b32 [[PTR]], v{{[0-9]+}} offset:64
|
|
%p = getelementptr [1024 x i32], ptr addrspace(3) %array, i16 0, i16 16
|
|
store i32 99, ptr addrspace(3) %p
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}use_gep_address_space_large_offset:
|
|
; The LDS offset will be 65536 bytes, which is larger than the size of LDS on
|
|
; SI, which is why it is being OR'd with the base pointer.
|
|
; SI: s_bitset1_b32
|
|
; CI: s_add_i32
|
|
; CHECK: ds_write_b32
|
|
define amdgpu_kernel void @use_gep_address_space_large_offset(ptr addrspace(3) %array) nounwind {
|
|
%p = getelementptr [1024 x i32], ptr addrspace(3) %array, i16 0, i16 16384
|
|
store i32 99, ptr addrspace(3) %p
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v4:
|
|
; SI: s_add_i32
|
|
; SI: s_add_i32
|
|
; SI: s_add_i32
|
|
; SI: s_add_i32
|
|
|
|
; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
|
|
; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
|
|
; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
|
|
; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
|
|
|
|
; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
|
|
; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
|
|
; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
|
|
; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
|
|
; CHECK: s_endpgm
|
|
define amdgpu_kernel void @gep_as_vector_v4(<4 x ptr addrspace(3)> %array) nounwind {
|
|
%p = getelementptr [1024 x i32], <4 x ptr addrspace(3)> %array, <4 x i16> zeroinitializer, <4 x i16> <i16 16, i16 16, i16 16, i16 16>
|
|
%p0 = extractelement <4 x ptr addrspace(3)> %p, i32 0
|
|
%p1 = extractelement <4 x ptr addrspace(3)> %p, i32 1
|
|
%p2 = extractelement <4 x ptr addrspace(3)> %p, i32 2
|
|
%p3 = extractelement <4 x ptr addrspace(3)> %p, i32 3
|
|
store i32 99, ptr addrspace(3) %p0
|
|
store i32 99, ptr addrspace(3) %p1
|
|
store i32 99, ptr addrspace(3) %p2
|
|
store i32 99, ptr addrspace(3) %p3
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}gep_as_vector_v2:
|
|
; SI: s_add_i32
|
|
; SI: s_add_i32
|
|
; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
|
|
; CHECK-DAG: v_mov_b32_e32 {{v[0-9]+}}, {{s[0-9]+}}
|
|
; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
|
|
; CI-DAG: ds_write_b32 v{{[0-9]+}}, v{{[0-9]+}} offset:64
|
|
; CHECK: s_endpgm
|
|
define amdgpu_kernel void @gep_as_vector_v2(<2 x ptr addrspace(3)> %array) nounwind {
|
|
%p = getelementptr [1024 x i32], <2 x ptr addrspace(3)> %array, <2 x i16> zeroinitializer, <2 x i16> <i16 16, i16 16>
|
|
%p0 = extractelement <2 x ptr addrspace(3)> %p, i32 0
|
|
%p1 = extractelement <2 x ptr addrspace(3)> %p, i32 1
|
|
store i32 99, ptr addrspace(3) %p0
|
|
store i32 99, ptr addrspace(3) %p1
|
|
ret void
|
|
}
|
|
|