088cc63640
Switch to using BitIntegerState for each of the inputs, and invert their meanings. This now diverges more from the old AMDGPUAnnotateKernelFeatures, but this isn't used yet anyway.
131 lines
4.5 KiB
LLVM
131 lines
4.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-globals
|
|
; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-annotate-kernel-features < %s | FileCheck -check-prefixes=CHECK,AKF_CHECK %s
|
|
; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-attributor < %s | FileCheck -check-prefixes=CHECK,ATTRIBUTOR_CHECK %s
|
|
|
|
;.
|
|
; CHECK: @[[G1:[a-zA-Z0-9_$"\\.-]+]] = global i32* null
|
|
; CHECK: @[[G2:[a-zA-Z0-9_$"\\.-]+]] = global i32 0
|
|
;.
|
|
define weak void @weak() {
|
|
; CHECK-LABEL: define {{[^@]+}}@weak
|
|
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: call void @internal1()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @internal1()
|
|
ret void
|
|
}
|
|
|
|
@G1 = global i32* null
|
|
|
|
define internal void @internal1() {
|
|
; CHECK-LABEL: define {{[^@]+}}@internal1
|
|
; CHECK-SAME: () #[[ATTR0]] {
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load i32*, i32** @G1, align 8
|
|
; CHECK-NEXT: store i32 0, i32* [[TMP1]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%1 = load i32*, i32** @G1
|
|
store i32 0, i32* %1
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel1() #0 {
|
|
; CHECK-LABEL: define {{[^@]+}}@kernel1
|
|
; CHECK-SAME: () #[[ATTR1:[0-9]+]] {
|
|
; CHECK-NEXT: call void @weak()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @weak()
|
|
ret void
|
|
}
|
|
|
|
@G2 = global i32 0
|
|
|
|
define internal void @internal3() {
|
|
; AKF_CHECK-LABEL: define {{[^@]+}}@internal3
|
|
; AKF_CHECK-SAME: () #[[ATTR2:[0-9]+]] {
|
|
; AKF_CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* @G2, align 4
|
|
; AKF_CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[TMP1]], 0
|
|
; AKF_CHECK-NEXT: br i1 [[TMP2]], label [[TMP3:%.*]], label [[TMP4:%.*]]
|
|
; AKF_CHECK: 3:
|
|
; AKF_CHECK-NEXT: call void @internal4()
|
|
; AKF_CHECK-NEXT: call void @internal3()
|
|
; AKF_CHECK-NEXT: br label [[TMP4]]
|
|
; AKF_CHECK: 4:
|
|
; AKF_CHECK-NEXT: ret void
|
|
;
|
|
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@internal3
|
|
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR1]] {
|
|
; ATTRIBUTOR_CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* @G2, align 4
|
|
; ATTRIBUTOR_CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[TMP1]], 0
|
|
; ATTRIBUTOR_CHECK-NEXT: br i1 [[TMP2]], label [[TMP3:%.*]], label [[TMP4:%.*]]
|
|
; ATTRIBUTOR_CHECK: 3:
|
|
; ATTRIBUTOR_CHECK-NEXT: call void @internal4()
|
|
; ATTRIBUTOR_CHECK-NEXT: call void @internal3()
|
|
; ATTRIBUTOR_CHECK-NEXT: br label [[TMP4]]
|
|
; ATTRIBUTOR_CHECK: 4:
|
|
; ATTRIBUTOR_CHECK-NEXT: ret void
|
|
;
|
|
%1 = load i32, i32* @G2, align 4
|
|
%2 = icmp eq i32 %1, 0
|
|
br i1 %2, label %3, label %4
|
|
3:
|
|
call void @internal4()
|
|
call void @internal3()
|
|
br label %4
|
|
4:
|
|
ret void
|
|
}
|
|
|
|
define internal void @internal4() {
|
|
; AKF_CHECK-LABEL: define {{[^@]+}}@internal4
|
|
; AKF_CHECK-SAME: () #[[ATTR2]] {
|
|
; AKF_CHECK-NEXT: store i32 1, i32* @G2, align 4
|
|
; AKF_CHECK-NEXT: ret void
|
|
;
|
|
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@internal4
|
|
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR1]] {
|
|
; ATTRIBUTOR_CHECK-NEXT: store i32 1, i32* @G2, align 4
|
|
; ATTRIBUTOR_CHECK-NEXT: ret void
|
|
;
|
|
store i32 1, i32* @G2, align 4
|
|
ret void
|
|
}
|
|
|
|
define internal void @internal2() {
|
|
; AKF_CHECK-LABEL: define {{[^@]+}}@internal2
|
|
; AKF_CHECK-SAME: () #[[ATTR2]] {
|
|
; AKF_CHECK-NEXT: call void @internal3()
|
|
; AKF_CHECK-NEXT: ret void
|
|
;
|
|
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@internal2
|
|
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR1]] {
|
|
; ATTRIBUTOR_CHECK-NEXT: call void @internal3()
|
|
; ATTRIBUTOR_CHECK-NEXT: ret void
|
|
;
|
|
call void @internal3()
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel2() #0 {
|
|
; CHECK-LABEL: define {{[^@]+}}@kernel2
|
|
; CHECK-SAME: () #[[ATTR1]] {
|
|
; CHECK-NEXT: call void @internal2()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @internal2()
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "uniform-work-group-size"="true" }
|
|
|
|
;.
|
|
; AKF_CHECK: attributes #[[ATTR0]] = { "uniform-work-group-size"="false" }
|
|
; AKF_CHECK: attributes #[[ATTR1]] = { "amdgpu-calls" "uniform-work-group-size"="true" }
|
|
; AKF_CHECK: attributes #[[ATTR2]] = { "uniform-work-group-size"="true" }
|
|
;.
|
|
; ATTRIBUTOR_CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-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_CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-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" }
|
|
;.
|