b6b703b2df
SIMachineFunctionInfo has a scan of the function body for inline asm
which may use AGPRs, or callees in SIMachineFunctionInfo. Move this
into the attributor, so it actually works interprocedurally.
Could probably avoid most of the test churn if this bothered to avoid
adding this on subtargets without AGPRs. We should also probably
try to delete the MIR scan in usesAGPRs but it seems to be trickier
to eliminate.
48 lines
2.4 KiB
LLVM
48 lines
2.4 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 -passes=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 ptr, align 8, addrspace(5)
|
|
; AKF_GCN-NEXT: store ptr @indirect, ptr addrspace(5) [[FPTR]], align 8
|
|
; AKF_GCN-NEXT: [[FP:%.*]] = load ptr, ptr addrspace(5) [[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 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 [[FP]]()
|
|
; 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" }
|
|
|
|
;.
|
|
; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-no-dispatch-id" "amdgpu-stack-objects" }
|
|
;.
|
|
; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "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" "amdgpu-waves-per-eu"="4,10" "uniform-work-group-size"="false" }
|
|
; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "uniform-work-group-size"="false" }
|
|
;.
|