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
74 lines
2.1 KiB
LLVM
74 lines
2.1 KiB
LLVM
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -stop-after=prologepilog < %s | FileCheck -check-prefix=CHECK %s
|
|
|
|
; Make sure we use a stack pointer and allocate 112 * 4 bytes at the beginning of the stack.
|
|
|
|
define amdgpu_cs void @amdgpu_cs() #0 {
|
|
; CHECK-LABEL: {{^}}name: amdgpu_cs
|
|
; CHECK: scratchReservedForDynamicVGPRs: 448
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel() #0 {
|
|
; CHECK-LABEL: {{^}}name: kernel
|
|
; CHECK: scratchReservedForDynamicVGPRs: 448
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_cs void @with_local() #0 {
|
|
; CHECK-LABEL: {{^}}name: with_local
|
|
; CHECK: scratchReservedForDynamicVGPRs: 448
|
|
%local = alloca i32, addrspace(5)
|
|
store volatile i8 13, ptr addrspace(5) %local
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_cs void @with_calls() #0 {
|
|
; CHECK-LABEL: {{^}}name: with_calls
|
|
; CHECK: scratchReservedForDynamicVGPRs: 448
|
|
%local = alloca i32, addrspace(5)
|
|
store volatile i8 15, ptr addrspace(5) %local
|
|
call amdgpu_gfx void @callee(i32 71)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_cs void @realign_stack(<32 x i32> %x) #0 {
|
|
; CHECK-LABEL: {{^}}name: realign_stack
|
|
; CHECK: scratchReservedForDynamicVGPRs: 512
|
|
%v = alloca <32 x i32>, align 128, addrspace(5)
|
|
; use volatile store to avoid promotion of alloca to registers
|
|
store volatile <32 x i32> %x, ptr addrspace(5) %v
|
|
call amdgpu_gfx void @callee(i32 71)
|
|
ret void
|
|
}
|
|
|
|
; Non-entry functions and graphics shaders can't run on a compute queue,
|
|
; so they don't need to worry about CWSR.
|
|
define amdgpu_gs void @amdgpu_gs() #0 {
|
|
; CHECK-LABEL: {{^}}name: amdgpu_gs
|
|
; CHECK: scratchReservedForDynamicVGPRs: 0
|
|
%local = alloca i32, addrspace(5)
|
|
store volatile i8 15, ptr addrspace(5) %local
|
|
call amdgpu_gfx void @callee(i32 71)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_gfx void @amdgpu_gfx() #0 {
|
|
; CHECK-LABEL: {{^}}name: amdgpu_gfx
|
|
; CHECK: scratchReservedForDynamicVGPRs: 0
|
|
%local = alloca i32, addrspace(5)
|
|
store volatile i8 15, ptr addrspace(5) %local
|
|
call amdgpu_gfx void @callee(i32 71)
|
|
ret void
|
|
}
|
|
|
|
define void @default() #0 {
|
|
; CHECK-LABEL: {{^}}name: default
|
|
; CHECK: scratchReservedForDynamicVGPRs: 0
|
|
ret void
|
|
}
|
|
|
|
declare amdgpu_gfx void @callee(i32) #0
|
|
|
|
attributes #0 = { nounwind "amdgpu-dynamic-vgpr-block-size" = "16" }
|
|
|