31f39c8325
Previously the AnnotateKernelFeatures pass infers two attributes: amdgpu-calls and amdgpu-stack-objects, which are used to help determine if flat scratch init is allowed. PR #118907 created the amdgpu-no-flat-scratch-init attribute. Continuing with that work, this patch makes use of this attribute to determine flat scratch init, replacing amdgpu-calls and amdgpu-stack-objects. This also leads to the removal of the AnnotateKernelFeatures pass.
35 lines
2.2 KiB
LLVM
35 lines
2.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-globals
|
|
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-attributor %s | FileCheck -check-prefix=ATTRIBUTOR_GCN %s
|
|
|
|
define internal void @indirect() {
|
|
; ATTRIBUTOR_GCN-LABEL: define {{[^@]+}}@indirect
|
|
; ATTRIBUTOR_GCN-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; ATTRIBUTOR_GCN-NEXT: ret void
|
|
;
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @test_simple_indirect_call() #0 {
|
|
; ATTRIBUTOR_GCN-LABEL: define {{[^@]+}}@test_simple_indirect_call
|
|
; ATTRIBUTOR_GCN-SAME: () #[[ATTR1:[0-9]+]] {
|
|
; ATTRIBUTOR_GCN-NEXT: [[FPTR:%.*]] = alloca ptr, align 8, addrspace(5)
|
|
; ATTRIBUTOR_GCN-NEXT: store ptr @indirect, ptr addrspace(5) [[FPTR]], align 8
|
|
; ATTRIBUTOR_GCN-NEXT: [[FP:%.*]] = load ptr, ptr addrspace(5) [[FPTR]], align 8
|
|
; ATTRIBUTOR_GCN-NEXT: call void @indirect()
|
|
; ATTRIBUTOR_GCN-NEXT: ret void
|
|
;
|
|
%fptr = alloca ptr, addrspace(5)
|
|
store ptr @indirect, ptr addrspace(5) %fptr
|
|
%fp = load ptr, ptr addrspace(5) %fptr
|
|
call void %fp()
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-no-dispatch-id" }
|
|
|
|
;.
|
|
;.
|
|
; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-agpr-alloc"="0" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
|
|
; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-flat-scratch-init" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
|
|
;.
|