1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 04:22:57 +02:00
llvm-mirror/test/CodeGen/AMDGPU/lower-range-metadata-intrinsic-call.ll
Matt Arsenault 34d57039a9 SelectionDAG: Lower some range metadata to AssertZext
If a range has a lower bound of 0, add an AssertZext from the
nearest floor power of two.

This allows operations with some workitem intrinsics with known
maximum ranges to use fast 24-bit multiplies.

llvm-svn: 260109
2016-02-08 16:28:19 +00:00

47 lines
1.5 KiB
LLVM

; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-unknown < %s | FileCheck %s
; and can be eliminated
; CHECK-LABEL: {{^}}test_workitem_id_x_known_max_range:
; CHECK-NOT: v0
; CHECK: {{flat|buffer}}_store_dword v0
define void @test_workitem_id_x_known_max_range(i32 addrspace(1)* nocapture %out) #0 {
entry:
%id = tail call i32 @llvm.amdgcn.workitem.id.x(), !range !0
%and = and i32 %id, 1023
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_workitem_id_x_known_trunc_1_bit_range:
; CHECK: v_and_b32_e32 [[MASKED:v[0-9]+]], 0x1ff, v0
; CHECK: {{flat|buffer}}_store_dword [[MASKED]]
define void @test_workitem_id_x_known_trunc_1_bit_range(i32 addrspace(1)* nocapture %out) #0 {
entry:
%id = tail call i32 @llvm.amdgcn.workitem.id.x(), !range !0
%and = and i32 %id, 511
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_workitem_id_x_known_max_range_m1:
; CHECK-NOT: v0
; CHECK: v_and_b32_e32 [[MASKED:v[0-9]+]], 0xff, v0
; CHECK: {{flat|buffer}}_store_dword [[MASKED]]
define void @test_workitem_id_x_known_max_range_m1(i32 addrspace(1)* nocapture %out) #0 {
entry:
%id = tail call i32 @llvm.amdgcn.workitem.id.x(), !range !1
%and = and i32 %id, 255
store i32 %and, i32 addrspace(1)* %out, align 4
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { norecurse nounwind }
attributes #1 = { nounwind readnone }
!0 = !{i32 0, i32 1024}
!1 = !{i32 0, i32 1023}