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
65 lines
2.8 KiB
LLVM
65 lines
2.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -check-prefix=GFX942 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -O0 < %s | FileCheck -check-prefix=GFX90A %s
|
|
|
|
@G = addrspace(1) global <2 x i32> splat (i32 5)
|
|
|
|
define amdgpu_ps void @global_load_lds_dword_saddr(ptr addrspace(1) inreg nocapture %gptr, ptr addrspace(3) nocapture %lptr) {
|
|
; GFX942-LABEL: global_load_lds_dword_saddr:
|
|
; GFX942: ; %bb.0: ; %main_body
|
|
; GFX942-NEXT: v_readfirstlane_b32 s2, v0
|
|
; GFX942-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX942-NEXT: s_mov_b32 m0, s2
|
|
; GFX942-NEXT: s_nop 0
|
|
; GFX942-NEXT: global_load_lds_dword v1, s[0:1] offset:32 nt
|
|
; GFX942-NEXT: s_getpc_b64 s[0:1]
|
|
; GFX942-NEXT: s_add_u32 s0, s0, G@gotpcrel32@lo+4
|
|
; GFX942-NEXT: s_addc_u32 s1, s1, G@gotpcrel32@hi+12
|
|
; GFX942-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; GFX942-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX942-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX942-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX942-NEXT: s_mul_i32 s3, s3, 10
|
|
; GFX942-NEXT: s_mul_i32 s2, s2, 10
|
|
; GFX942-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX942-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX942-NEXT: global_store_dwordx2 v1, v[2:3], s[0:1]
|
|
; GFX942-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-LABEL: global_load_lds_dword_saddr:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX90A-NEXT: s_mov_b32 s2, s0
|
|
; GFX90A-NEXT: ; kill: def $sgpr2 killed $sgpr2 def $sgpr2_sgpr3
|
|
; GFX90A-NEXT: s_mov_b32 s3, s1
|
|
; GFX90A-NEXT: s_getpc_b64 s[0:1]
|
|
; GFX90A-NEXT: s_add_u32 s0, s0, G@gotpcrel32@lo+4
|
|
; GFX90A-NEXT: s_addc_u32 s1, s1, G@gotpcrel32@hi+12
|
|
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x0
|
|
; GFX90A-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: s_mov_b32 s4, s9
|
|
; GFX90A-NEXT: s_mov_b32 s6, 10
|
|
; GFX90A-NEXT: s_mul_i32 s4, s4, s6
|
|
; GFX90A-NEXT: s_mov_b32 s5, s8
|
|
; GFX90A-NEXT: s_mul_i32 s5, s5, s6
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s5
|
|
; GFX90A-NEXT: v_mov_b32_e32 v4, s4
|
|
; GFX90A-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
|
|
; GFX90A-NEXT: v_mov_b32_e32 v3, v4
|
|
; GFX90A-NEXT: v_readfirstlane_b32 s4, v1
|
|
; GFX90A-NEXT: s_mov_b32 m0, s4
|
|
; GFX90A-NEXT: s_nop 0
|
|
; GFX90A-NEXT: global_load_dword v0, s[2:3] offset:32 slc lds
|
|
; GFX90A-NEXT: global_store_dwordx2 v0, v[2:3], s[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%LGV = load <2 x i32>, ptr addrspace(1) @G, align 8
|
|
%B = mul <2 x i32> %LGV, splat (i32 10)
|
|
call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) %gptr, ptr addrspace(3) %lptr, i32 4, i32 32, i32 2)
|
|
store <2 x i32> %B, ptr addrspace(1) @G, align 8
|
|
ret void
|
|
}
|