9e9907f1cf
Similar to 806761a7629df268c8aed49657aeccffa6bca449. For IR files without a target triple, -mtriple= specifies the full target triple while -march= merely sets the architecture part of the default target triple, leaving a target triple which may not make sense, e.g. amdgpu-apple-darwin. Therefore, -march= is error-prone and not recommended for tests without a target triple. The issue has been benign as we recognize $unknown-apple-darwin as ELF instead of rejecting it outrightly. This patch changes AMDGPU tests to not rely on the default OS/environment components. Tests that need fixes are not changed: ``` LLVM :: CodeGen/AMDGPU/fabs.f64.ll LLVM :: CodeGen/AMDGPU/fabs.ll LLVM :: CodeGen/AMDGPU/floor.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.f64.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.ll LLVM :: CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll LLVM :: CodeGen/AMDGPU/schedule-if-2.ll ```
108 lines
3.8 KiB
LLVM
108 lines
3.8 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -enable-var-scope -check-prefixes=GCN,O2 %s
|
|
; RUN: llc -O0 -mtriple=amdgcn < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}zext_grp_size_128:
|
|
; GCN-NOT: and_b32
|
|
define amdgpu_kernel void @zext_grp_size_128(ptr addrspace(1) nocapture %arg) #0 {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp1 = and i32 %tmp, 127
|
|
store i32 %tmp1, ptr addrspace(1) %arg, align 4
|
|
%tmp2 = tail call i32 @llvm.amdgcn.workitem.id.y()
|
|
%tmp3 = and i32 %tmp2, 127
|
|
%tmp4 = getelementptr inbounds i32, ptr addrspace(1) %arg, i64 1
|
|
store i32 %tmp3, ptr addrspace(1) %tmp4, align 4
|
|
%tmp5 = tail call i32 @llvm.amdgcn.workitem.id.z()
|
|
%tmp6 = and i32 %tmp5, 127
|
|
%tmp7 = getelementptr inbounds i32, ptr addrspace(1) %arg, i64 2
|
|
store i32 %tmp6, ptr addrspace(1) %tmp7, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}zext_grp_size_32x4x1:
|
|
; GCN-NOT: and_b32
|
|
define amdgpu_kernel void @zext_grp_size_32x4x1(ptr addrspace(1) nocapture %arg) #0 !reqd_work_group_size !0 {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp1 = and i32 %tmp, 31
|
|
store i32 %tmp1, ptr addrspace(1) %arg, align 4
|
|
%tmp2 = tail call i32 @llvm.amdgcn.workitem.id.y()
|
|
%tmp3 = and i32 %tmp2, 3
|
|
%tmp4 = getelementptr inbounds i32, ptr addrspace(1) %arg, i64 1
|
|
store i32 %tmp3, ptr addrspace(1) %tmp4, align 4
|
|
%tmp5 = tail call i32 @llvm.amdgcn.workitem.id.z()
|
|
%tmp6 = and i32 %tmp5, 1
|
|
%tmp7 = getelementptr inbounds i32, ptr addrspace(1) %arg, i64 2
|
|
store i32 %tmp6, ptr addrspace(1) %tmp7, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}zext_grp_size_1x1x1:
|
|
; GCN-NOT: and_b32
|
|
|
|
; When EarlyCSE is not run this call produces a range max with 0 active bits,
|
|
; which is a special case as an AssertZext from width 0 is invalid.
|
|
define amdgpu_kernel void @zext_grp_size_1x1x1(ptr addrspace(1) nocapture %arg) #0 !reqd_work_group_size !1 {
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp1 = and i32 %tmp, 1
|
|
store i32 %tmp1, ptr addrspace(1) %arg, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}zext_grp_size_512:
|
|
; GCN-NOT: and_b32
|
|
define amdgpu_kernel void @zext_grp_size_512(ptr addrspace(1) nocapture %arg) #1 {
|
|
bb:
|
|
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tmp1 = and i32 %tmp, 65535
|
|
store i32 %tmp1, ptr addrspace(1) %arg, align 4
|
|
%tmp2 = tail call i32 @llvm.amdgcn.workitem.id.y()
|
|
%tmp3 = and i32 %tmp2, 65535
|
|
%tmp4 = getelementptr inbounds i32, ptr addrspace(1) %arg, i64 1
|
|
store i32 %tmp3, ptr addrspace(1) %tmp4, align 4
|
|
%tmp5 = tail call i32 @llvm.amdgcn.workitem.id.z()
|
|
%tmp6 = and i32 %tmp5, 65535
|
|
%tmp7 = getelementptr inbounds i32, ptr addrspace(1) %arg, i64 2
|
|
store i32 %tmp6, ptr addrspace(1) %tmp7, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}func_test_workitem_id_x_known_max_range:
|
|
; O2-NOT: and_b32
|
|
; O2: v_and_b32_e32 v{{[0-9]+}}, 0x3ff,
|
|
; O2-NOT: and_b32
|
|
define void @func_test_workitem_id_x_known_max_range(ptr addrspace(1) nocapture %out) #0 {
|
|
entry:
|
|
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%and = and i32 %id, 1023
|
|
store i32 %and, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}func_test_workitem_id_x_default_range:
|
|
; O2-NOT: and_b32
|
|
; O2: v_and_b32_e32 v{{[0-9]+}}, 0x3ff,
|
|
; O2-NOT: and_b32
|
|
define void @func_test_workitem_id_x_default_range(ptr addrspace(1) nocapture %out) #4 {
|
|
entry:
|
|
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
%and = and i32 %id, 1023
|
|
store i32 %and, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #2
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.y() #2
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.z() #2
|
|
|
|
attributes #0 = { nounwind "amdgpu-flat-work-group-size"="64,128" }
|
|
attributes #1 = { nounwind "amdgpu-flat-work-group-size"="512,512" }
|
|
attributes #2 = { nounwind readnone speculatable }
|
|
attributes #3 = { nounwind readnone }
|
|
attributes #4 = { nounwind }
|
|
|
|
!0 = !{i32 32, i32 4, i32 1}
|
|
!1 = !{i32 1, i32 1, i32 1}
|