9e9907f1cf
Similar to 806761a762.
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
```
57 lines
2.1 KiB
LLVM
57 lines
2.1 KiB
LLVM
; RUN: llc -O0 -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCNNOOPT -check-prefix=GCN %s
|
|
; RUN: llc -O0 -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCNNOOPT -check-prefix=GCN %s
|
|
; RUN: llc -O0 -mtriple=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global,-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCNNOOPT -check-prefix=GCN %s
|
|
; RUN: llc -O0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=-flat-for-global,-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCNNOOPT -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCNOPT -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCNOPT -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}test_branch:
|
|
; GCNNOOPT: v_writelane_b32
|
|
; GCNNOOPT: v_writelane_b32
|
|
; GCN: s_cbranch_scc1 [[END:.LBB[0-9]+_[0-9]+]]
|
|
|
|
; GCNNOOPT: v_readlane_b32
|
|
; GCNNOOPT: v_readlane_b32
|
|
; GCN: buffer_store_{{dword|b32}}
|
|
; GCNNOOPT: s_endpgm
|
|
|
|
; GCN: {{^}}[[END]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @test_branch(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in, i32 %val) #0 {
|
|
%cmp = icmp ne i32 %val, 0
|
|
br i1 %cmp, label %store, label %end
|
|
|
|
store:
|
|
store i32 222, ptr addrspace(1) %out
|
|
ret void
|
|
|
|
end:
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_brcc_i1:
|
|
; GCN: s_load_{{dword|b32}} [[VAL:s[0-9]+]]
|
|
; GCNNOOPT: s_mov_b32 [[ONE:s[0-9]+]], 1{{$}}
|
|
; GCNNOOPT: s_and_b32 s{{[0-9]+}}, [[VAL]], [[ONE]]
|
|
; GCNOPT: s_bitcmp0_b32 [[VAL]], 0
|
|
; GCNNOOPT: s_cmp_eq_u32
|
|
; GCN: s_cbranch_scc1 [[END:.LBB[0-9]+_[0-9]+]]
|
|
|
|
; GCN: buffer_store_{{dword|b32}}
|
|
|
|
; GCN: {{^}}[[END]]:
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @test_brcc_i1(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %in, i1 %val) #0 {
|
|
%cmp0 = icmp ne i1 %val, 0
|
|
br i1 %cmp0, label %store, label %end
|
|
|
|
store:
|
|
store i32 222, ptr addrspace(1) %out
|
|
ret void
|
|
|
|
end:
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|