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
73 lines
3.5 KiB
LLVM
73 lines
3.5 KiB
LLVM
;RUN: llc < %s -mtriple=amdgcn -mcpu=gfx600 | FileCheck %s -check-prefixes=CHECK,SI
|
|
;RUN: llc < %s -mtriple=amdgcn -mcpu=gfx700 | FileCheck %s -check-prefixes=CHECK,GCNX3
|
|
|
|
;CHECK-LABEL: {{^}}buffer_raw_load_immoffs_x3:
|
|
;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40
|
|
;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40
|
|
;CHECK: s_waitcnt
|
|
define amdgpu_ps <3 x float> @buffer_raw_load_immoffs_x3(<4 x i32> inreg) {
|
|
main_body:
|
|
%data = call <3 x float> @llvm.amdgcn.raw.buffer.load.v3f32(<4 x i32> %0, i32 40, i32 0, i32 0)
|
|
ret <3 x float> %data
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}buffer_struct_load_format_immoffs_x3:
|
|
;SI: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
|
|
;GCNX3: buffer_load_format_xyz v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
|
|
;CHECK: s_waitcnt
|
|
define amdgpu_ps <3 x float> @buffer_struct_load_format_immoffs_x3(<4 x i32> inreg) {
|
|
main_body:
|
|
%data = call <3 x float> @llvm.amdgcn.struct.buffer.load.format.v3f32(<4 x i32> %0, i32 0, i32 42, i32 0, i32 0)
|
|
ret <3 x float> %data
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}struct_buffer_load_immoffs_x3:
|
|
;SI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
|
|
;GCNX3: buffer_load_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
|
|
;CHECK: s_waitcnt
|
|
define amdgpu_ps <3 x float> @struct_buffer_load_immoffs_x3(<4 x i32> inreg) {
|
|
main_body:
|
|
%data = call <3 x float> @llvm.amdgcn.struct.buffer.load.v3f32(<4 x i32> %0, i32 0, i32 40, i32 0, i32 0)
|
|
ret <3 x float> %data
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}buffer_raw_ptr_load_immoffs_x3:
|
|
;SI: buffer_load_dwordx4 v[0:3], off, s[0:3], 0 offset:40
|
|
;GCNX3: buffer_load_dwordx3 v[0:2], off, s[0:3], 0 offset:40
|
|
;CHECK: s_waitcnt
|
|
define amdgpu_ps <3 x float> @buffer_raw_ptr_load_immoffs_x3(ptr addrspace(8) inreg) {
|
|
main_body:
|
|
%data = call <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.v3f32(ptr addrspace(8) %0, i32 40, i32 0, i32 0)
|
|
ret <3 x float> %data
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}buffer_struct_ptr_load_format_immoffs_x3:
|
|
;SI: buffer_load_format_xyzw v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
|
|
;GCNX3: buffer_load_format_xyz v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
|
|
;CHECK: s_waitcnt
|
|
define amdgpu_ps <3 x float> @buffer_struct_ptr_load_format_immoffs_x3(ptr addrspace(8) inreg) {
|
|
main_body:
|
|
%data = call <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.format.v3f32(ptr addrspace(8) %0, i32 0, i32 42, i32 0, i32 0)
|
|
ret <3 x float> %data
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}struct_ptr_buffer_load_immoffs_x3:
|
|
;SI: buffer_load_dwordx4 v[0:3], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
|
|
;GCNX3: buffer_load_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:40
|
|
;CHECK: s_waitcnt
|
|
define amdgpu_ps <3 x float> @struct_ptr_buffer_load_immoffs_x3(ptr addrspace(8) inreg) {
|
|
main_body:
|
|
%data = call <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.v3f32(ptr addrspace(8) %0, i32 0, i32 40, i32 0, i32 0)
|
|
ret <3 x float> %data
|
|
}
|
|
|
|
declare <3 x float> @llvm.amdgcn.raw.buffer.load.format.v3f32(<4 x i32>, i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.raw.buffer.load.v3f32(<4 x i32>, i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.struct.buffer.load.format.v3f32(<4 x i32>, i32, i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.struct.buffer.load.v3f32(<4 x i32>, i32, i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.format.v3f32(ptr addrspace(8), i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.raw.ptr.buffer.load.v3f32(ptr addrspace(8), i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.format.v3f32(ptr addrspace(8), i32, i32, i32, i32) #0
|
|
declare <3 x float> @llvm.amdgcn.struct.ptr.buffer.load.v3f32(ptr addrspace(8), i32, i32, i32, i32) #0
|
|
|