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
45 lines
1.9 KiB
LLVM
45 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck %s -check-prefix=GFX11
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 < %s | FileCheck %s -check-prefix=GFX12
|
|
|
|
define amdgpu_cs void @test_uniform_load_b96(ptr addrspace(1) %ptr, i32 %arg) "amdgpu-flat-work-group-size"="1,1" {
|
|
; GFX11-LABEL: test_uniform_load_b96:
|
|
; GFX11: ; %bb.0: ; %bb
|
|
; GFX11-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
|
|
; GFX11-NEXT: v_lshlrev_b64 v[2:3], 2, v[2:3]
|
|
; GFX11-NEXT: v_add_co_u32 v2, vcc_lo, v0, v2
|
|
; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX11-NEXT: v_add_co_ci_u32_e64 v3, null, v1, v3, vcc_lo
|
|
; GFX11-NEXT: global_load_b96 v[2:4], v[2:3], off
|
|
; GFX11-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-NEXT: v_or3_b32 v2, v2, v3, v4
|
|
; GFX11-NEXT: global_store_b32 v[0:1], v2, off
|
|
; GFX11-NEXT: s_endpgm
|
|
;
|
|
; GFX12-LABEL: test_uniform_load_b96:
|
|
; GFX12: ; %bb.0: ; %bb
|
|
; GFX12-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
|
|
; GFX12-NEXT: v_lshlrev_b64_e32 v[2:3], 2, v[2:3]
|
|
; GFX12-NEXT: v_add_co_u32 v2, vcc_lo, v0, v2
|
|
; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX12-NEXT: v_add_co_ci_u32_e64 v3, null, v1, v3, vcc_lo
|
|
; GFX12-NEXT: global_load_b96 v[2:4], v[2:3], off
|
|
; GFX12-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-NEXT: v_or3_b32 v2, v2, v3, v4
|
|
; GFX12-NEXT: global_store_b32 v[0:1], v2, off
|
|
; GFX12-NEXT: s_endpgm
|
|
bb:
|
|
%i = zext i32 %arg to i64
|
|
%i1 = getelementptr i32, ptr addrspace(1) %ptr, i64 %i
|
|
%i2 = load <3 x i32>, ptr addrspace(1) %i1, align 4
|
|
%i3 = extractelement <3 x i32> %i2, i32 0
|
|
%i4 = extractelement <3 x i32> %i2, i32 1
|
|
%i5 = extractelement <3 x i32> %i2, i32 2
|
|
%i6 = or i32 %i3, %i4
|
|
%i7 = or i32 %i5, %i6
|
|
store i32 %i7, ptr addrspace(1) %ptr, align 4
|
|
ret void
|
|
}
|