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.
138 lines
6.1 KiB
LLVM
138 lines
6.1 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-annotate-kernel-features %s | FileCheck --allow-unused-prefixes -check-prefixes=CHECK,AKF_CHECK %s
|
|
; RUN: opt -S -mtriple=amdgcn-amd- -amdgpu-attributor %s | FileCheck --allow-unused-prefixes -check-prefixes=CHECK,ATTRIBUTOR_CHECK %s
|
|
|
|
; Test to ensure recursive functions exhibit proper behaviour
|
|
; Test to generate fibonacci numbers
|
|
|
|
define i32 @fib(i32 %n) #0 {
|
|
; CHECK-LABEL: define {{[^@]+}}@fib
|
|
; CHECK-SAME: (i32 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i32 [[N]], 0
|
|
; CHECK-NEXT: br i1 [[CMP1]], label [[EXIT:%.*]], label [[CONT1:%.*]]
|
|
; CHECK: cont1:
|
|
; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i32 [[N]], 1
|
|
; CHECK-NEXT: br i1 [[CMP2]], label [[EXIT]], label [[CONT2:%.*]]
|
|
; CHECK: cont2:
|
|
; CHECK-NEXT: [[NM1:%.*]] = sub i32 [[N]], 1
|
|
; CHECK-NEXT: [[FIBM1:%.*]] = call i32 @fib(i32 [[NM1]])
|
|
; CHECK-NEXT: [[NM2:%.*]] = sub i32 [[N]], 2
|
|
; CHECK-NEXT: [[FIBM2:%.*]] = call i32 @fib(i32 [[NM2]])
|
|
; CHECK-NEXT: [[RETVAL:%.*]] = add i32 [[FIBM1]], [[FIBM2]]
|
|
; CHECK-NEXT: ret i32 [[RETVAL]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: ret i32 1
|
|
;
|
|
%cmp1 = icmp eq i32 %n, 0
|
|
br i1 %cmp1, label %exit, label %cont1
|
|
|
|
cont1:
|
|
%cmp2 = icmp eq i32 %n, 1
|
|
br i1 %cmp2, label %exit, label %cont2
|
|
|
|
cont2:
|
|
%nm1 = sub i32 %n, 1
|
|
%fibm1 = call i32 @fib(i32 %nm1)
|
|
%nm2 = sub i32 %n, 2
|
|
%fibm2 = call i32 @fib(i32 %nm2)
|
|
%retval = add i32 %fibm1, %fibm2
|
|
|
|
ret i32 %retval
|
|
|
|
exit:
|
|
ret i32 1
|
|
}
|
|
|
|
define internal i32 @fib_internal(i32 %n) #0 {
|
|
; AKF_CHECK-LABEL: define {{[^@]+}}@fib_internal
|
|
; AKF_CHECK-SAME: (i32 [[N:%.*]]) #[[ATTR0]] {
|
|
; AKF_CHECK-NEXT: [[CMP1:%.*]] = icmp eq i32 [[N]], 0
|
|
; AKF_CHECK-NEXT: br i1 [[CMP1]], label [[EXIT:%.*]], label [[CONT1:%.*]]
|
|
; AKF_CHECK: cont1:
|
|
; AKF_CHECK-NEXT: [[CMP2:%.*]] = icmp eq i32 [[N]], 1
|
|
; AKF_CHECK-NEXT: br i1 [[CMP2]], label [[EXIT]], label [[CONT2:%.*]]
|
|
; AKF_CHECK: cont2:
|
|
; AKF_CHECK-NEXT: [[NM1:%.*]] = sub i32 [[N]], 1
|
|
; AKF_CHECK-NEXT: [[FIBM1:%.*]] = call i32 @fib_internal(i32 [[NM1]])
|
|
; AKF_CHECK-NEXT: [[NM2:%.*]] = sub i32 [[N]], 2
|
|
; AKF_CHECK-NEXT: [[FIBM2:%.*]] = call i32 @fib_internal(i32 [[NM2]])
|
|
; AKF_CHECK-NEXT: [[RETVAL:%.*]] = add i32 [[FIBM1]], [[FIBM2]]
|
|
; AKF_CHECK-NEXT: ret i32 [[RETVAL]]
|
|
; AKF_CHECK: exit:
|
|
; AKF_CHECK-NEXT: ret i32 1
|
|
;
|
|
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@fib_internal
|
|
; ATTRIBUTOR_CHECK-SAME: (i32 [[N:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
; ATTRIBUTOR_CHECK-NEXT: [[CMP1:%.*]] = icmp eq i32 [[N]], 0
|
|
; ATTRIBUTOR_CHECK-NEXT: br i1 [[CMP1]], label [[EXIT:%.*]], label [[CONT1:%.*]]
|
|
; ATTRIBUTOR_CHECK: cont1:
|
|
; ATTRIBUTOR_CHECK-NEXT: [[CMP2:%.*]] = icmp eq i32 [[N]], 1
|
|
; ATTRIBUTOR_CHECK-NEXT: br i1 [[CMP2]], label [[EXIT]], label [[CONT2:%.*]]
|
|
; ATTRIBUTOR_CHECK: cont2:
|
|
; ATTRIBUTOR_CHECK-NEXT: [[NM1:%.*]] = sub i32 [[N]], 1
|
|
; ATTRIBUTOR_CHECK-NEXT: [[FIBM1:%.*]] = call i32 @fib_internal(i32 [[NM1]])
|
|
; ATTRIBUTOR_CHECK-NEXT: [[NM2:%.*]] = sub i32 [[N]], 2
|
|
; ATTRIBUTOR_CHECK-NEXT: [[FIBM2:%.*]] = call i32 @fib_internal(i32 [[NM2]])
|
|
; ATTRIBUTOR_CHECK-NEXT: [[RETVAL:%.*]] = add i32 [[FIBM1]], [[FIBM2]]
|
|
; ATTRIBUTOR_CHECK-NEXT: ret i32 [[RETVAL]]
|
|
; ATTRIBUTOR_CHECK: exit:
|
|
; ATTRIBUTOR_CHECK-NEXT: ret i32 1
|
|
;
|
|
%cmp1 = icmp eq i32 %n, 0
|
|
br i1 %cmp1, label %exit, label %cont1
|
|
|
|
cont1:
|
|
%cmp2 = icmp eq i32 %n, 1
|
|
br i1 %cmp2, label %exit, label %cont2
|
|
|
|
cont2:
|
|
%nm1 = sub i32 %n, 1
|
|
%fibm1 = call i32 @fib_internal(i32 %nm1)
|
|
%nm2 = sub i32 %n, 2
|
|
%fibm2 = call i32 @fib_internal(i32 %nm2)
|
|
%retval = add i32 %fibm1, %fibm2
|
|
|
|
ret i32 %retval
|
|
|
|
exit:
|
|
ret i32 1
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel(i32 addrspace(1)* %m) #1 {
|
|
; AKF_CHECK-LABEL: define {{[^@]+}}@kernel
|
|
; AKF_CHECK-SAME: (i32 addrspace(1)* [[M:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
; AKF_CHECK-NEXT: [[R:%.*]] = call i32 @fib(i32 5)
|
|
; AKF_CHECK-NEXT: [[R2:%.*]] = call i32 @fib_internal(i32 5)
|
|
; AKF_CHECK-NEXT: store i32 [[R]], i32 addrspace(1)* [[M]], align 4
|
|
; AKF_CHECK-NEXT: store i32 [[R2]], i32 addrspace(1)* [[M]], align 4
|
|
; AKF_CHECK-NEXT: ret void
|
|
;
|
|
; ATTRIBUTOR_CHECK-LABEL: define {{[^@]+}}@kernel
|
|
; ATTRIBUTOR_CHECK-SAME: (i32 addrspace(1)* [[M:%.*]]) #[[ATTR2:[0-9]+]] {
|
|
; ATTRIBUTOR_CHECK-NEXT: [[R:%.*]] = call i32 @fib(i32 5)
|
|
; ATTRIBUTOR_CHECK-NEXT: [[R2:%.*]] = call i32 @fib_internal(i32 5)
|
|
; ATTRIBUTOR_CHECK-NEXT: store i32 [[R]], i32 addrspace(1)* [[M]], align 4
|
|
; ATTRIBUTOR_CHECK-NEXT: store i32 [[R2]], i32 addrspace(1)* [[M]], align 4
|
|
; ATTRIBUTOR_CHECK-NEXT: ret void
|
|
;
|
|
%r = call i32 @fib(i32 5)
|
|
%r2 = call i32 @fib_internal(i32 5)
|
|
|
|
store i32 %r, i32 addrspace(1)* %m
|
|
store i32 %r2, i32 addrspace(1)* %m
|
|
ret void
|
|
}
|
|
|
|
; nounwind and readnone are added to match attributor results.
|
|
attributes #0 = { nounwind readnone }
|
|
attributes #1 = { "uniform-work-group-size"="true" }
|
|
|
|
;.
|
|
; AKF_CHECK: attributes #[[ATTR0]] = { nounwind readnone "uniform-work-group-size"="true" }
|
|
; AKF_CHECK: attributes #[[ATTR1]] = { "amdgpu-calls" "uniform-work-group-size"="true" }
|
|
;.
|
|
; ATTRIBUTOR_CHECK: attributes #[[ATTR0]] = { nounwind readnone "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]] = { nounwind readnone "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" }
|
|
; ATTRIBUTOR_CHECK: attributes #[[ATTR2]] = { "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" }
|
|
;.
|