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
53 lines
2.4 KiB
LLVM
53 lines
2.4 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefixes=GCN,GFX11 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefixes=GCN,GFX11 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GCN,GFX12 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GCN,GFX12 %s
|
|
|
|
; GCN-LABEL: {{^}}lds_direct_load:
|
|
; GCN: s_mov_b32 m0
|
|
; GFX11: lds_direct_load v{{[0-9]+}}
|
|
; GFX12: ds_direct_load v{{[0-9]+}}
|
|
; GCN: s_mov_b32 m0
|
|
; GFX11: lds_direct_load v{{[0-9]+}}
|
|
; GFX12: ds_direct_load v{{[0-9]+}}
|
|
; GCN: s_mov_b32 m0
|
|
; GFX11: lds_direct_load v{{[0-9]+}}
|
|
; GFX11: s_waitcnt expcnt(2)
|
|
; GFX12: ds_direct_load v{{[0-9]+}}
|
|
; GFX12: s_wait_expcnt 0x2
|
|
; GCN: v_add_f32
|
|
; GCN: buffer_store_b32
|
|
; GFX11: s_waitcnt expcnt(1)
|
|
; GFX12: s_wait_expcnt 0x1
|
|
; GCN: buffer_store_b32
|
|
; GFX11: s_waitcnt expcnt(0)
|
|
; GFX12: s_wait_expcnt 0x0
|
|
; GCN: buffer_store_b32
|
|
; GCN: buffer_store_b32
|
|
; GCN: buffer_store_b32
|
|
; GCN: buffer_store_b32
|
|
define amdgpu_ps void @lds_direct_load(ptr addrspace(8) inreg %buf, i32 inreg %arg0,
|
|
i32 inreg %arg1, i32 inreg %arg2) #0 {
|
|
main_body:
|
|
%p0 = call float @llvm.amdgcn.lds.direct.load(i32 %arg0)
|
|
; Ensure memory clustering is occuring for lds_direct_load
|
|
%p5 = fadd float %p0, 1.0
|
|
%p1 = call float @llvm.amdgcn.lds.direct.load(i32 %arg1)
|
|
%p2 = call float @llvm.amdgcn.lds.direct.load(i32 %arg2)
|
|
%p3 = call float @llvm.amdgcn.lds.direct.load(i32 %arg1)
|
|
%p4 = call float @llvm.amdgcn.lds.direct.load(i32 %arg2)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.f32(float %p5, ptr addrspace(8) %buf, i32 4, i32 0, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.f32(float %p1, ptr addrspace(8) %buf, i32 4, i32 1, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.f32(float %p2, ptr addrspace(8) %buf, i32 4, i32 2, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.f32(float %p3, ptr addrspace(8) %buf, i32 4, i32 3, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.f32(float %p4, ptr addrspace(8) %buf, i32 4, i32 4, i32 0)
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.f32(float %p0, ptr addrspace(8) %buf, i32 4, i32 5, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.amdgcn.lds.direct.load(i32) #1
|
|
declare void @llvm.amdgcn.raw.ptr.buffer.store.f32(float, ptr addrspace(8), i32, i32, i32)
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readonly }
|