f05d2e8a39
The "uniform-work-group-size" function attribute previously took a string value of "true" or "false". Since presence alone can convey the "true" semantics and absence can convey "false", the value is unnecessary. This patch converts it to a valueless string attribute: presence indicates true, absence indicates false. For backward compatibility, auto-upgrade logic is added in both UpgradeAttributes (bitcode) and UpgradeFunctionAttributes: if the old value is "true", the attribute is kept without a value; if "false", the attribute is removed.
59 lines
2.5 KiB
LLVM
59 lines
2.5 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- -passes=amdgpu-attributor %s | FileCheck %s
|
|
|
|
@x = global i32 0
|
|
|
|
; Propagate the uniform-work-group-attribute from the kernel to callee if it doesn't have it
|
|
;.
|
|
; CHECK: @x = global i32 0
|
|
;.
|
|
define void @func() #0 {
|
|
; CHECK-LABEL: define {{[^@]+}}@func
|
|
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: store i32 0, ptr @x, align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
store i32 0, ptr @x
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel1() {
|
|
; CHECK-LABEL: define {{[^@]+}}@kernel1
|
|
; CHECK-SAME: () #[[ATTR1:[0-9]+]] {
|
|
; CHECK-NEXT: call void @func()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @func()
|
|
ret void
|
|
}
|
|
|
|
; External declaration of a function
|
|
define weak_odr void @weak_func() #0 {
|
|
; CHECK-LABEL: define {{[^@]+}}@weak_func
|
|
; CHECK-SAME: () #[[ATTR2:[0-9]+]] {
|
|
; CHECK-NEXT: store i32 0, ptr @x, align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
store i32 0, ptr @x
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel2() #1 {
|
|
; CHECK-LABEL: define {{[^@]+}}@kernel2
|
|
; CHECK-SAME: () #[[ATTR3:[0-9]+]] {
|
|
; CHECK-NEXT: call void @weak_func()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @weak_func()
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { "uniform-work-group-size" }
|
|
;.
|
|
; CHECK: attributes #[[ATTR0]] = { nounwind "amdgpu-no-cluster-id-x" "amdgpu-no-cluster-id-y" "amdgpu-no-cluster-id-z" "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" }
|
|
; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-cluster-id-x" "amdgpu-no-cluster-id-y" "amdgpu-no-cluster-id-z" "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" }
|
|
; CHECK: attributes #[[ATTR2]] = { nounwind }
|
|
; CHECK: attributes #[[ATTR3]] = { "uniform-work-group-size" }
|
|
;.
|