d8f99bb6e0
The module flag to indicate use of hostcall is insufficient to catch all cases where hostcall might be in use by a kernel. This is now replaced by a function attribute that gets propagated to top-level kernel functions via their respective call-graph. If the attribute "amdgpu-no-hostcall-ptr" is absent on a kernel, the default behaviour is to emit kernel metadata indicating that the kernel uses the hostcall buffer pointer passed as an implicit argument. The attribute may be placed explicitly by the user, or inferred by the AMDGPU attributor by examining the call-graph. The attribute is inferred only if the function is not being sanitized, and the implictarg_ptr does not result in a load of any byte in the hostcall pointer argument. Reviewed By: jdoerfert, arsenm, kpyzhov Differential Revision: https://reviews.llvm.org/D119216
47 lines
1.8 KiB
LLVM
47 lines
1.8 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- -amdgpu-attributor < %s | FileCheck %s
|
|
|
|
; Test to verify if the attribute gets propagated across nested function calls
|
|
|
|
; Added to prevent Attributor from deleting calls.
|
|
@x = global i32 0
|
|
|
|
;.
|
|
; CHECK: @[[X:[a-zA-Z0-9_$"\\.-]+]] = global i32 0
|
|
;.
|
|
define void @func1() #0 {
|
|
; CHECK-LABEL: define {{[^@]+}}@func1
|
|
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: store i32 0, i32* @x, align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
store i32 0, i32* @x
|
|
ret void
|
|
}
|
|
|
|
define void @func2() #1 {
|
|
; CHECK-LABEL: define {{[^@]+}}@func2
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @func1()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @func1()
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel3() #2 {
|
|
; CHECK-LABEL: define {{[^@]+}}@kernel3
|
|
; CHECK-SAME: () #[[ATTR1:[0-9]+]] {
|
|
; CHECK-NEXT: call void @func2()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @func2()
|
|
ret void
|
|
}
|
|
|
|
attributes #2 = { "uniform-work-group-size"="true" }
|
|
;.
|
|
; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "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" }
|
|
; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "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"="true" }
|
|
;.
|