1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll
Kuter Dinel a502a514d2 [AMDGPU] Deduce attributes with the Attributor
This patch introduces a pass that uses the Attributor to deduce AMDGPU specific attributes.

Reviewed By: jdoerfert, arsenm

Differential Revision: https://reviews.llvm.org/D104997
2021-07-24 06:07:15 +03:00

158 lines
5.5 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() {
; AKF_CHECK-LABEL: define {{[^@]+}}@weak
; AKF_CHECK-SAME: () #[[ATTR0:[0-9]+]] {
; AKF_CHECK-NEXT: call void @internal1()
; AKF_CHECK-NEXT: ret void
;
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@weak
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR0:[0-9]+]] {
; ATTRIBUTOR_CHECK-NEXT: call void @internal1() #[[ATTR5:[0-9]+]]
; ATTRIBUTOR_CHECK-NEXT: ret void
;
call void @internal1()
ret void
}
@G1 = global i32* null
define internal void @internal1() {
; AKF_CHECK-LABEL: define {{[^@]+}}@internal1
; AKF_CHECK-SAME: () #[[ATTR0]] {
; AKF_CHECK-NEXT: [[TMP1:%.*]] = load i32*, i32** @G1, align 8
; AKF_CHECK-NEXT: store i32 0, i32* [[TMP1]], align 4
; AKF_CHECK-NEXT: ret void
;
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@internal1
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR1:[0-9]+]] {
; ATTRIBUTOR_CHECK-NEXT: [[TMP1:%.*]] = load i32*, i32** @G1, align 8
; ATTRIBUTOR_CHECK-NEXT: store i32 0, i32* [[TMP1]], align 4
; ATTRIBUTOR_CHECK-NEXT: ret void
;
%1 = load i32*, i32** @G1
store i32 0, i32* %1
ret void
}
define amdgpu_kernel void @kernel1() #0 {
; AKF_CHECK-LABEL: define {{[^@]+}}@kernel1
; AKF_CHECK-SAME: () #[[ATTR1:[0-9]+]] {
; AKF_CHECK-NEXT: call void @weak()
; AKF_CHECK-NEXT: ret void
;
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@kernel1
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR2:[0-9]+]] {
; ATTRIBUTOR_CHECK-NEXT: call void @weak()
; ATTRIBUTOR_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: () #[[ATTR3:[0-9]+]] {
; 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() #[[ATTR6:[0-9]+]]
; ATTRIBUTOR_CHECK-NEXT: call void @internal3() #[[ATTR7:[0-9]+]]
; 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: () #[[ATTR4:[0-9]+]] {
; 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: () #[[ATTR3]] {
; ATTRIBUTOR_CHECK-NEXT: call void @internal3() #[[ATTR7]]
; ATTRIBUTOR_CHECK-NEXT: ret void
;
call void @internal3()
ret void
}
define amdgpu_kernel void @kernel2() #0 {
; AKF_CHECK-LABEL: define {{[^@]+}}@kernel2
; AKF_CHECK-SAME: () #[[ATTR1]] {
; AKF_CHECK-NEXT: call void @internal2()
; AKF_CHECK-NEXT: ret void
;
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@kernel2
; ATTRIBUTOR_CHECK-SAME: () #[[ATTR2]] {
; ATTRIBUTOR_CHECK-NEXT: call void @internal2() #[[ATTR5]]
; ATTRIBUTOR_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]] = { "uniform-work-group-size"="false" }
; ATTRIBUTOR_CHECK: attributes #[[ATTR1]] = { nofree nosync nounwind willreturn "uniform-work-group-size"="false" }
; ATTRIBUTOR_CHECK: attributes #[[ATTR2]] = { "amdgpu-calls" "uniform-work-group-size"="true" }
; ATTRIBUTOR_CHECK: attributes #[[ATTR3]] = { nofree nosync nounwind "uniform-work-group-size"="true" }
; ATTRIBUTOR_CHECK: attributes #[[ATTR4]] = { nofree nosync nounwind willreturn writeonly "uniform-work-group-size"="true" }
; ATTRIBUTOR_CHECK: attributes #[[ATTR5]] = { nounwind }
; ATTRIBUTOR_CHECK: attributes #[[ATTR6]] = { nofree nosync nounwind willreturn writeonly }
; ATTRIBUTOR_CHECK: attributes #[[ATTR7]] = { nofree nosync nounwind }
;.