Files
TheRock/compiler/amd-llvm/llvm/test/CodeGen/AMDGPU/hsa-metadata-resource-usage-function-ordering.ll
T
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

142 lines
4.5 KiB
LLVM

; Note: uses a randomly selected assumed external call stack size so that the
; test assertions are unlikely to succeed by accident.
; RUN: llc -amdgpu-assume-external-call-stack-size=5310 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -enable-misched=0 -filetype=asm -o - < %s | FileCheck --check-prefixes CHECK,GFX7 %s
; RUN: llc -amdgpu-assume-external-call-stack-size=5310 -mattr=-xnack -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -enable-misched=0 -filetype=asm -o - < %s | FileCheck --check-prefixes CHECK,GFX8 %s
; RUN: llc -amdgpu-assume-external-call-stack-size=5310 -mattr=-xnack -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -enable-misched=0 -filetype=asm -o - < %s | FileCheck --check-prefixes CHECK,GFX9 %s
; RUN: llc -amdgpu-assume-external-call-stack-size=5310 -mattr=-xnack -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -enable-misched=0 -filetype=asm -o - < %s | FileCheck --check-prefixes CHECK,GFX10 %s
; CHECK-LABEL: amdhsa.kernels
; test a kernel without an external call that occurs before its callee in the module
; CHECK-LABEL: test1
; CHECK: .private_segment_fixed_size: 20
; GFX7: .sgpr_count: 37
; GFX7: .sgpr_spill_count: 0
; GFX7: .vgpr_count: 4
; GFX7: .vgpr_spill_count: 0
; GFX8: .sgpr_count: 39
; GFX8: .sgpr_spill_count: 0
; GFX8: .vgpr_count: 4
; GFX8: .vgpr_spill_count: 0
; GFX9: .sgpr_count: 39
; GFX9: .sgpr_spill_count: 0
; GFX9: .vgpr_count: 4
; GFX9: .vgpr_spill_count: 0
; GFX10: .sgpr_count: 33
; GFX10: .sgpr_spill_count: 0
; GFX10: .vgpr_count: 4
; GFX10: .vgpr_spill_count: 0
define amdgpu_kernel void @test1(ptr %x) #1 {
%1 = load volatile float, ptr %x
%2 = call float @f(float %1)
store volatile float %2, ptr %x
ret void
}
define internal float @f(float %arg0) #1 {
%stack = alloca float, i32 4, align 4, addrspace(5)
store volatile float 3.0, ptr addrspace(5) %stack
%val = load volatile float, ptr addrspace(5) %stack
%add = fadd float %arg0, %val
ret float %add
}
; test a kernel without an external call that occurs after its callee in the module
; CHECK-LABEL: test2
; CHECK: .private_segment_fixed_size: 20
; GFX7: .sgpr_count: 37
; GFX7: .sgpr_spill_count: 0
; GFX7: .vgpr_count: 4
; GFX7: .vgpr_spill_count: 0
; GFX8: .sgpr_count: 39
; GFX8: .sgpr_spill_count: 0
; GFX8: .vgpr_count: 4
; GFX8: .vgpr_spill_count: 0
; GFX9: .sgpr_count: 39
; GFX9: .sgpr_spill_count: 0
; GFX9: .vgpr_count: 4
; GFX9: .vgpr_spill_count: 0
; GFX10: .sgpr_count: 33
; GFX10: .sgpr_spill_count: 0
; GFX10: .vgpr_count: 4
; GFX10: .vgpr_spill_count: 0
define amdgpu_kernel void @test2(ptr %x) {
%1 = load volatile float, ptr %x
%2 = call float @f(float %1)
store volatile float %2, ptr %x
ret void
}
; test a kernel with an external call that occurs before its callee in the module
; CHECK-LABEL: test3
; CHECK: .private_segment_fixed_size: 5310
; GFX7: .sgpr_count: 37
; GFX7: .sgpr_spill_count: 0
; GFX7: .vgpr_count: 32
; GFX7: .vgpr_spill_count: 0
; GFX8: .sgpr_count: 39
; GFX8: .sgpr_spill_count: 0
; GFX8: .vgpr_count: 32
; GFX8: .vgpr_spill_count: 0
; GFX9: .sgpr_count: 39
; GFX9: .sgpr_spill_count: 0
; GFX9: .vgpr_count: 32
; GFX9: .vgpr_spill_count: 0
; GFX10: .sgpr_count: 35
; GFX10: .sgpr_spill_count: 0
; GFX10: .vgpr_count: 32
; GFX10: .vgpr_spill_count: 0
define amdgpu_kernel void @test3() {
call void @g()
ret void
}
declare void @g() #0
; test a kernel without an external call that occurs after its callee in the module
; CHECK-LABEL: test4
; CHECK: .private_segment_fixed_size: 5310
; GFX7: .sgpr_count: 37
; GFX7: .sgpr_spill_count: 0
; GFX7: .vgpr_count: 32
; GFX7: .vgpr_spill_count: 0
; GFX8: .sgpr_count: 39
; GFX8: .sgpr_spill_count: 0
; GFX8: .vgpr_count: 32
; GFX8: .vgpr_spill_count: 0
; GFX9: .sgpr_count: 39
; GFX9: .sgpr_spill_count: 0
; GFX9: .vgpr_count: 32
; GFX9: .vgpr_spill_count: 0
; GFX10: .sgpr_count: 35
; GFX10: .sgpr_spill_count: 0
; GFX10: .vgpr_count: 32
; GFX10: .vgpr_spill_count: 0
define amdgpu_kernel void @test4() {
call void @g()
ret void
}
attributes #0 = { norecurse }
attributes #1 = { norecurse "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" }
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"amdhsa_code_object_version", i32 400}