Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/flat-for-global-subtarget-feature.ll
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

60 lines
2.2 KiB
LLVM

; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=+flat-for-global | FileCheck -check-prefix=HSA -check-prefix=HSA-DEFAULT -check-prefix=ALL %s
; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global | FileCheck -check-prefix=HSA -check-prefix=HSA-NODEFAULT -check-prefix=ALL %s
; RUN: llc < %s -mtriple=amdgcn-- -mcpu=tonga | FileCheck -check-prefix=HSA-NOADDR64 -check-prefix=ALL %s
; RUN: llc < %s -mtriple=amdgcn-- -mcpu=kaveri -mattr=-flat-for-global | FileCheck -check-prefix=NOHSA-DEFAULT -check-prefix=ALL %s
; RUN: llc < %s -mtriple=amdgcn-- -mcpu=kaveri -mattr=+flat-for-global | FileCheck -check-prefix=NOHSA-NODEFAULT -check-prefix=ALL %s
; RUN: llc < %s -mtriple=amdgcn-- -mcpu=tonga | FileCheck -check-prefix=NOHSA-NOADDR64 -check-prefix=ALL %s
; There are no stack objects even though flat is used by default, so
; flat_scratch_init should be disabled.
; ALL-LABEL: {{^}}test:
; ALL-NOT: flat_scr
; HSA-DEFAULT: flat_store_dword
; HSA-NODEFAULT: buffer_store_dword
; HSA-NOADDR64: flat_store_dword
; HSA: .amdhsa_user_sgpr_flat_scratch_init 0
; NOHSA-DEFAULT: buffer_store_dword
; NOHSA-NODEFAULT: flat_store_dword
; NOHSA-NOADDR64: flat_store_dword
define amdgpu_kernel void @test(ptr addrspace(1) %out) #0 {
entry:
store i32 0, ptr addrspace(1) %out
ret void
}
; ALL-LABEL: {{^}}test_addr64:
; HSA-DEFAULT: flat_store_dword
; HSA-NODEFAULT: buffer_store_dword
; HSA-NOADDR64: flat_store_dword
; NOHSA-DEFAULT: buffer_store_dword
; NOHSA-NODEFAULT: flat_store_dword
; NOHSA-NOADDR64: flat_store_dword
define amdgpu_kernel void @test_addr64(ptr addrspace(1) %out) #0 {
entry:
%out.addr = alloca ptr addrspace(1), align 4, addrspace(5)
store ptr addrspace(1) %out, ptr addrspace(5) %out.addr, align 4
%ld0 = load ptr addrspace(1), ptr addrspace(5) %out.addr, align 4
store i32 1, ptr addrspace(1) %ld0, align 4
%ld1 = load ptr addrspace(1), ptr addrspace(5) %out.addr, align 4
%arrayidx1 = getelementptr inbounds i32, ptr addrspace(1) %ld1, i32 1
store i32 2, ptr addrspace(1) %arrayidx1, align 4
ret void
}
attributes #0 = { "amdgpu-no-flat-scratch-init" }
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"amdhsa_code_object_version", i32 400}