Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/sdwa-op64-test.ll
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

75 lines
3.9 KiB
LLVM

; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9,GCN %s
; RUN: llc -mtriple=amdgcn -mcpu=fiji < %s | FileCheck -check-prefixes=FIJI,GCN %s
; GCN-LABEL: {{^}}test_add_co_sdwa:
; GFX9: v_add_co_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; GFX9: v_addc_co_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
; FIJI: v_add_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; FIJI: v_addc_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
define void @test_add_co_sdwa(ptr addrspace(1) %arg, ptr addrspace(1) %arg1) #0 {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp3 = getelementptr inbounds i32, ptr addrspace(1) %arg1, i32 %tmp
%tmp4 = load i32, ptr addrspace(1) %tmp3, align 4
%tmp5 = and i32 %tmp4, 255
%tmp6 = zext i32 %tmp5 to i64
%tmp7 = getelementptr inbounds i64, ptr addrspace(1) %arg, i32 %tmp
%tmp8 = load i64, ptr addrspace(1) %tmp7, align 8
%tmp9 = add nsw i64 %tmp8, %tmp6
store i64 %tmp9, ptr addrspace(1) %tmp7, align 8
ret void
}
; GCN-LABEL: {{^}}test_sub_co_sdwa:
; GFX9: v_sub_co_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; GFX9: v_subbrev_co_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
; FIJI: v_sub_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; FIJI: v_subbrev_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
define void @test_sub_co_sdwa(ptr addrspace(1) %arg, ptr addrspace(1) %arg1) #0 {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp3 = getelementptr inbounds i32, ptr addrspace(1) %arg1, i32 %tmp
%tmp4 = load i32, ptr addrspace(1) %tmp3, align 4
%tmp5 = and i32 %tmp4, 255
%tmp6 = zext i32 %tmp5 to i64
%tmp7 = getelementptr inbounds i64, ptr addrspace(1) %arg, i32 %tmp
%tmp8 = load i64, ptr addrspace(1) %tmp7, align 8
%tmp9 = sub nsw i64 %tmp8, %tmp6
store i64 %tmp9, ptr addrspace(1) %tmp7, align 8
ret void
}
; GCN-LABEL: {{^}}test1_add_co_sdwa:
; GFX9: v_add_co_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; GFX9: v_addc_co_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
; GFX9: v_add_co_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; GFX9: v_addc_co_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
; FIJI: v_add_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; FIJI: v_addc_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
; FIJI: v_add_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; FIJI: v_addc_u32_e32 v{{[0-9]+}}, vcc, 0, v{{[0-9]+}}, vcc{{$}}
define amdgpu_kernel void @test1_add_co_sdwa(ptr addrspace(1) %arg, ptr addrspace(1) %arg1, ptr addrspace(1) %arg2) #0 {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp3 = getelementptr inbounds i32, ptr addrspace(1) %arg1, i32 %tmp
%tmp4 = load i32, ptr addrspace(1) %tmp3, align 4
%tmp5 = and i32 %tmp4, 255
%tmp6 = zext i32 %tmp5 to i64
%tmp7 = getelementptr inbounds i64, ptr addrspace(1) %arg, i32 %tmp
%tmp8 = load i64, ptr addrspace(1) %tmp7, align 8
%tmp9 = add nsw i64 %tmp8, %tmp6
store i64 %tmp9, ptr addrspace(1) %tmp7, align 8
%tmp13 = getelementptr inbounds i32, ptr addrspace(1) %arg1, i32 %tmp
%tmp14 = load i32, ptr addrspace(1) %tmp13, align 4
%tmp15 = and i32 %tmp14, 255
%tmp16 = zext i32 %tmp15 to i64
%tmp17 = getelementptr inbounds i64, ptr addrspace(1) %arg2, i32 %tmp
%tmp18 = load i64, ptr addrspace(1) %tmp17, align 8
%tmp19 = add nsw i64 %tmp18, %tmp16
store i64 %tmp19, ptr addrspace(1) %tmp17, align 8
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()