mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
bf9d9a1180
Previously this would default to 256, not the maximum supported size of 1024. Using a maximum lower than the hardware maximum requires language runtimes to enforce this limit for correctness, which no language has correctly done. Switch the default to the conservatively correct maximum, and force frontends to opt-in to the more optimal 256 default maximum. I don't really understand why the changes in occupancy-levels.ll increased the computed occupancy, which I expected to decrease. I'm not sure if these tests should be forcing the old maximum.
47 lines
1.5 KiB
LLVM
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 amdgpu_kernel 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-NOT: v_and_b32
|
|
; CHECK: {{flat|buffer}}_store_dword {{.*}}v0
|
|
define amdgpu_kernel 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-NOT: v_and_b32
|
|
; CHECK: {{flat|buffer}}_store_dword {{.*}}v0
|
|
define amdgpu_kernel 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 "amdgpu-flat-work-group-size"="1,256" }
|
|
attributes #1 = { nounwind readnone }
|
|
|
|
!0 = !{i32 0, i32 1024}
|
|
!1 = !{i32 0, i32 1023}
|