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 ```
51 lines
1.8 KiB
LLVM
51 lines
1.8 KiB
LLVM
; RUN: llc < %s -mtriple=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s --check-prefix=GCN
|
|
|
|
; GCN-LABEL: and_zext:
|
|
; GCN: v_and_b32_e32 [[VAL16:v[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}}
|
|
; GCN: v_and_b32_e32 v{{[0-9]+}}, 0xffff, [[VAL16]]
|
|
define amdgpu_kernel void @and_zext(ptr addrspace(1) %out, ptr addrspace(1) %in) {
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x() #1
|
|
%ptr = getelementptr i16, ptr addrspace(1) %in, i32 %id
|
|
%a = load i16, ptr addrspace(1) %in
|
|
%b = load i16, ptr addrspace(1) %ptr
|
|
%c = add i16 %a, %b
|
|
%val16 = and i16 %c, %a
|
|
%val32 = zext i16 %val16 to i32
|
|
store i32 %val32, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: or_zext:
|
|
; GCN: v_or_b32_e32 [[VAL16:v[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}}
|
|
; GCN: v_and_b32_e32 v{{[0-9]+}}, 0xffff, [[VAL16]]
|
|
define amdgpu_kernel void @or_zext(ptr addrspace(1) %out, ptr addrspace(1) %in) {
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x() #1
|
|
%ptr = getelementptr i16, ptr addrspace(1) %in, i32 %id
|
|
%a = load i16, ptr addrspace(1) %in
|
|
%b = load i16, ptr addrspace(1) %ptr
|
|
%c = add i16 %a, %b
|
|
%val16 = or i16 %c, %a
|
|
%val32 = zext i16 %val16 to i32
|
|
store i32 %val32, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: xor_zext:
|
|
; GCN: v_xor_b32_e32 [[VAL16:v[0-9]+]], v{{[0-9]+}}, v{{[0-9]+}}
|
|
; GCN: v_and_b32_e32 v{{[0-9]+}}, 0xffff, [[VAL16]]
|
|
define amdgpu_kernel void @xor_zext(ptr addrspace(1) %out, ptr addrspace(1) %in) {
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x() #1
|
|
%ptr = getelementptr i16, ptr addrspace(1) %in, i32 %id
|
|
%a = load i16, ptr addrspace(1) %in
|
|
%b = load i16, ptr addrspace(1) %ptr
|
|
%c = add i16 %a, %b
|
|
%val16 = xor i16 %c, %a
|
|
%val32 = zext i16 %val16 to i32
|
|
store i32 %val32, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #1 = { nounwind readnone }
|