Files
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

88 lines
3.6 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s
; Check that invariant global loads are treated like constant
; loads. The optnone disables the annotation of of amdgpu.noclobber.
define amdgpu_kernel void @load_constant_v3i64(ptr addrspace(1) %dst, ptr addrspace(4) %src) #0 {
; CHECK-LABEL: load_constant_v3i64:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x8
; CHECK-NEXT: v_mov_b32_e32 v4, 0
; CHECK-NEXT: s_load_dwordx2 s[4:5], s[8:9], 0x0
; CHECK-NEXT: s_load_dwordx2 s[6:7], s[8:9], 0x8
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_load_dwordx4 s[0:3], s[6:7], 0x0
; CHECK-NEXT: s_nop 0
; CHECK-NEXT: s_load_dwordx2 s[6:7], s[6:7], 0x10
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: v_mov_b32_e32 v0, s6
; CHECK-NEXT: v_mov_b32_e32 v1, s7
; CHECK-NEXT: global_store_dwordx2 v4, v[0:1], s[4:5] offset:16
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: v_mov_b32_e32 v1, s1
; CHECK-NEXT: v_mov_b32_e32 v2, s2
; CHECK-NEXT: v_mov_b32_e32 v3, s3
; CHECK-NEXT: global_store_dwordx4 v4, v[0:3], s[4:5]
; CHECK-NEXT: s_endpgm
%ld = load <3 x i64>, ptr addrspace(4) %src, align 32
store <3 x i64> %ld, ptr addrspace(1) %dst, align 32
ret void
}
define amdgpu_kernel void @load_global_v3i64(ptr addrspace(1) %dst, ptr addrspace(1) %src) #0 {
; CHECK-LABEL: load_global_v3i64:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x8
; CHECK-NEXT: v_mov_b32_e32 v6, 0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x0
; CHECK-NEXT: s_load_dwordx2 s[2:3], s[8:9], 0x8
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: global_load_dwordx4 v[0:3], v6, s[2:3]
; CHECK-NEXT: global_load_dwordx2 v[4:5], v6, s[2:3] offset:16
; CHECK-NEXT: s_waitcnt vmcnt(0)
; CHECK-NEXT: global_store_dwordx2 v6, v[4:5], s[0:1] offset:16
; CHECK-NEXT: global_store_dwordx4 v6, v[0:3], s[0:1]
; CHECK-NEXT: s_endpgm
%ld = load <3 x i64>, ptr addrspace(1) %src, align 32
store <3 x i64> %ld, ptr addrspace(1) %dst, align 32
ret void
}
define amdgpu_kernel void @load_global_v3i64_invariant(ptr addrspace(1) %dst, ptr addrspace(1) %src) #0 {
; CHECK-LABEL: load_global_v3i64_invariant:
; CHECK: ; %bb.0:
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_load_dwordx2 s[0:1], s[8:9], 0x8
; CHECK-NEXT: v_mov_b32_e32 v4, 0
; CHECK-NEXT: s_load_dwordx2 s[4:5], s[8:9], 0x0
; CHECK-NEXT: s_load_dwordx2 s[6:7], s[8:9], 0x8
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: s_load_dwordx4 s[0:3], s[6:7], 0x0
; CHECK-NEXT: s_nop 0
; CHECK-NEXT: s_load_dwordx2 s[6:7], s[6:7], 0x10
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: v_mov_b32_e32 v0, s6
; CHECK-NEXT: v_mov_b32_e32 v1, s7
; CHECK-NEXT: global_store_dwordx2 v4, v[0:1], s[4:5] offset:16
; CHECK-NEXT: v_mov_b32_e32 v0, s0
; CHECK-NEXT: v_mov_b32_e32 v1, s1
; CHECK-NEXT: v_mov_b32_e32 v2, s2
; CHECK-NEXT: v_mov_b32_e32 v3, s3
; CHECK-NEXT: global_store_dwordx4 v4, v[0:3], s[4:5]
; CHECK-NEXT: s_endpgm
%ld = load <3 x i64>, ptr addrspace(1) %src, align 32, !invariant.load !0
store <3 x i64> %ld, ptr addrspace(1) %dst, align 32
ret void
}
attributes #0 = { noinline nounwind optnone }
!0 = !{}