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
48 lines
2.2 KiB
LLVM
48 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 -amdgpu-annotate-kernel-features %s | FileCheck -check-prefix=AKF_GCN %s
|
|
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-attributor %s | FileCheck -check-prefix=ATTRIBUTOR_GCN %s
|
|
|
|
define internal void @indirect() {
|
|
; AKF_GCN-LABEL: define {{[^@]+}}@indirect() {
|
|
; AKF_GCN-NEXT: ret void
|
|
;
|
|
; 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 {
|
|
; AKF_GCN-LABEL: define {{[^@]+}}@test_simple_indirect_call
|
|
; AKF_GCN-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; AKF_GCN-NEXT: [[FPTR:%.*]] = alloca void ()*, align 8
|
|
; AKF_GCN-NEXT: store void ()* @indirect, void ()** [[FPTR]], align 8
|
|
; AKF_GCN-NEXT: [[FP:%.*]] = load void ()*, void ()** [[FPTR]], align 8
|
|
; AKF_GCN-NEXT: call void [[FP]]()
|
|
; AKF_GCN-NEXT: ret void
|
|
;
|
|
; ATTRIBUTOR_GCN-LABEL: define {{[^@]+}}@test_simple_indirect_call
|
|
; ATTRIBUTOR_GCN-SAME: () #[[ATTR1:[0-9]+]] {
|
|
; ATTRIBUTOR_GCN-NEXT: [[FPTR:%.*]] = alloca void ()*, align 8
|
|
; ATTRIBUTOR_GCN-NEXT: store void ()* @indirect, void ()** [[FPTR]], align 8
|
|
; ATTRIBUTOR_GCN-NEXT: [[FP:%.*]] = load void ()*, void ()** [[FPTR]], align 8
|
|
; ATTRIBUTOR_GCN-NEXT: call void [[FP]]()
|
|
; ATTRIBUTOR_GCN-NEXT: ret void
|
|
;
|
|
%fptr = alloca void()*
|
|
store void()* @indirect, void()** %fptr
|
|
%fp = load void()*, void()** %fptr
|
|
call void %fp()
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "amdgpu-no-dispatch-id" }
|
|
|
|
;.
|
|
; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-no-dispatch-id" "amdgpu-stack-objects" }
|
|
;.
|
|
; ATTRIBUTOR_GCN: 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" }
|
|
; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "uniform-work-group-size"="false" }
|
|
;.
|