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
128 lines
4.9 KiB
LLVM
128 lines
4.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 < %s | FileCheck --check-prefix=GFX12 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefix=GFX12 %s
|
|
|
|
|
|
define amdgpu_kernel void @buffer_last_use_load_0(ptr addrspace(7) %in, ptr addrspace(7) %out) {
|
|
; GFX12-LABEL: buffer_last_use_load_0:
|
|
; GFX12: ; %bb.0: ; %entry
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x0
|
|
; GFX12-NEXT: s_load_b32 s11, s[4:5], 0x10
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX12-NEXT: s_mov_b32 s8, s1
|
|
; GFX12-NEXT: s_mov_b32 s9, s2
|
|
; GFX12-NEXT: s_mov_b32 s10, s3
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x20
|
|
; GFX12-NEXT: s_load_b32 s7, s[4:5], 0x30
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v1, s0
|
|
; GFX12-NEXT: buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_LU
|
|
; GFX12-NEXT: s_mov_b32 s4, s1
|
|
; GFX12-NEXT: s_mov_b32 s5, s2
|
|
; GFX12-NEXT: s_mov_b32 s6, s3
|
|
; GFX12-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-NEXT: buffer_store_b32 v0, v1, s[4:7], null offen
|
|
; GFX12-NEXT: s_endpgm
|
|
entry:
|
|
%val = load i32, ptr addrspace(7) %in, !amdgpu.last.use !{}
|
|
store i32 %val, ptr addrspace(7) %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @buffer_last_use_load_1(ptr addrspace(7) %in, ptr addrspace(7) %out) {
|
|
; GFX12-LABEL: buffer_last_use_load_1:
|
|
; GFX12: ; %bb.0: ; %entry
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x0
|
|
; GFX12-NEXT: s_load_b32 s11, s[4:5], 0x10
|
|
; GFX12-NEXT: v_and_b32_e32 v0, 0x3ff, v0
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1)
|
|
; GFX12-NEXT: v_lshl_add_u32 v0, v0, 2, s0
|
|
; GFX12-NEXT: s_mov_b32 s8, s1
|
|
; GFX12-NEXT: s_mov_b32 s9, s2
|
|
; GFX12-NEXT: s_mov_b32 s10, s3
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x20
|
|
; GFX12-NEXT: s_load_b32 s7, s[4:5], 0x30
|
|
; GFX12-NEXT: buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_LU
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v1, s0
|
|
; GFX12-NEXT: s_mov_b32 s4, s1
|
|
; GFX12-NEXT: s_mov_b32 s5, s2
|
|
; GFX12-NEXT: s_mov_b32 s6, s3
|
|
; GFX12-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-NEXT: buffer_store_b32 v0, v1, s[4:7], null offen
|
|
; GFX12-NEXT: s_endpgm
|
|
entry:
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%val.gep = getelementptr inbounds i32, ptr addrspace(7) %in, i32 %tid
|
|
%val = load i32, ptr addrspace(7) %val.gep, align 4, !amdgpu.last.use !{}
|
|
store i32 %val, ptr addrspace(7) %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @buffer_last_use_and_volatile_load(ptr addrspace(7) %in, ptr addrspace(7) %out) {
|
|
; GFX12-LABEL: buffer_last_use_and_volatile_load:
|
|
; GFX12: ; %bb.0: ; %entry
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x0
|
|
; GFX12-NEXT: s_load_b32 s11, s[4:5], 0x10
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX12-NEXT: s_mov_b32 s8, s1
|
|
; GFX12-NEXT: s_mov_b32 s9, s2
|
|
; GFX12-NEXT: s_mov_b32 s10, s3
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x20
|
|
; GFX12-NEXT: s_load_b32 s7, s[4:5], 0x30
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v1, s0
|
|
; GFX12-NEXT: buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_BYPASS scope:SCOPE_SYS
|
|
; GFX12-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-NEXT: s_mov_b32 s4, s1
|
|
; GFX12-NEXT: s_mov_b32 s5, s2
|
|
; GFX12-NEXT: s_mov_b32 s6, s3
|
|
; GFX12-NEXT: buffer_store_b32 v0, v1, s[4:7], null offen
|
|
; GFX12-NEXT: s_endpgm
|
|
entry:
|
|
%val = load volatile i32, ptr addrspace(7) %in, !amdgpu.last.use !{}
|
|
store i32 %val, ptr addrspace(7) %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @buffer_last_use_and_nontemporal_load(ptr addrspace(7) %in, ptr addrspace(7) %out) {
|
|
; GFX12-LABEL: buffer_last_use_and_nontemporal_load:
|
|
; GFX12: ; %bb.0: ; %entry
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x0
|
|
; GFX12-NEXT: s_load_b32 s11, s[4:5], 0x10
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX12-NEXT: s_mov_b32 s8, s1
|
|
; GFX12-NEXT: s_mov_b32 s9, s2
|
|
; GFX12-NEXT: s_mov_b32 s10, s3
|
|
; GFX12-NEXT: s_clause 0x1
|
|
; GFX12-NEXT: s_load_b128 s[0:3], s[4:5], 0x20
|
|
; GFX12-NEXT: s_load_b32 s7, s[4:5], 0x30
|
|
; GFX12-NEXT: s_wait_kmcnt 0x0
|
|
; GFX12-NEXT: v_mov_b32_e32 v1, s0
|
|
; GFX12-NEXT: buffer_load_b32 v0, v0, s[8:11], null offen th:TH_LOAD_LU
|
|
; GFX12-NEXT: s_mov_b32 s4, s1
|
|
; GFX12-NEXT: s_mov_b32 s5, s2
|
|
; GFX12-NEXT: s_mov_b32 s6, s3
|
|
; GFX12-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-NEXT: buffer_store_b32 v0, v1, s[4:7], null offen
|
|
; GFX12-NEXT: s_endpgm
|
|
entry:
|
|
%val = load i32, ptr addrspace(7) %in, !amdgpu.last.use !{}, !nontemporal !0
|
|
store i32 %val, ptr addrspace(7) %out
|
|
ret void
|
|
}
|
|
|
|
!0 = !{i32 1}
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|