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
```
130 lines
2.6 KiB
LLVM
130 lines
2.6 KiB
LLVM
;RUN: llc -mtriple=r600 -mcpu=redwood -amdgpu-bypass-slow-div=0 < %s | FileCheck -check-prefix=EG %s
|
|
|
|
;EG-LABEL: {{^}}s_test_sdiv:
|
|
;EG: RECIP_UINT
|
|
;EG: LSHL {{.*}}, 1,
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
define amdgpu_kernel void @s_test_sdiv(ptr addrspace(1) %out, i64 %x, i64 %y) {
|
|
%result = sdiv i64 %x, %y
|
|
store i64 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
;EG-LABEL: {{^}}s_test_srem:
|
|
;EG: RECIP_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: BFE_UINT
|
|
;EG: AND_INT {{.*}}, 1,
|
|
define amdgpu_kernel void @s_test_srem(ptr addrspace(1) %out, i64 %x, i64 %y) {
|
|
%result = urem i64 %x, %y
|
|
store i64 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
;EG-LABEL: {{^}}test_sdiv3264:
|
|
;EG: RECIP_UINT
|
|
;EG-NOT: BFE_UINT
|
|
define amdgpu_kernel void @test_sdiv3264(ptr addrspace(1) %out, i64 %x, i64 %y) {
|
|
%1 = ashr i64 %x, 33
|
|
%2 = ashr i64 %y, 33
|
|
%result = sdiv i64 %1, %2
|
|
store i64 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
;EG-LABEL: {{^}}test_srem3264:
|
|
;EG: RECIP_UINT
|
|
;EG-NOT: BFE_UINT
|
|
define amdgpu_kernel void @test_srem3264(ptr addrspace(1) %out, i64 %x, i64 %y) {
|
|
%1 = ashr i64 %x, 33
|
|
%2 = ashr i64 %y, 33
|
|
%result = srem i64 %1, %2
|
|
store i64 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
;EG-LABEL: {{^}}test_sdiv2464:
|
|
;EG: INT_TO_FLT
|
|
;EG: INT_TO_FLT
|
|
;EG: FLT_TO_INT
|
|
;EG-NOT: RECIP_UINT
|
|
;EG-NOT: BFE_UINT
|
|
define amdgpu_kernel void @test_sdiv2464(ptr addrspace(1) %out, i64 %x, i64 %y) {
|
|
%1 = ashr i64 %x, 40
|
|
%2 = ashr i64 %y, 40
|
|
%result = sdiv i64 %1, %2
|
|
store i64 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
;EG-LABEL: {{^}}test_srem2464:
|
|
;EG: INT_TO_FLT
|
|
;EG: INT_TO_FLT
|
|
;EG: FLT_TO_INT
|
|
;EG-NOT: RECIP_UINT
|
|
;EG-NOT: BFE_UINT
|
|
define amdgpu_kernel void @test_srem2464(ptr addrspace(1) %out, i64 %x, i64 %y) {
|
|
%1 = ashr i64 %x, 40
|
|
%2 = ashr i64 %y, 40
|
|
%result = srem i64 %1, %2
|
|
store i64 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|