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
```
85 lines
3.9 KiB
LLVM
85 lines
3.9 KiB
LLVM
;RUN: llc < %s -mtriple=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK
|
|
|
|
;CHECK-LABEL: {{^}}buffer_store_format_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_format_xyz v[0:2], off, s[0:3], 0 offset:42
|
|
define amdgpu_ps void @buffer_store_format_immoffs_x3(<4 x i32> inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.buffer.store.format.v3f32(<3 x float> %1, <4 x i32> %0, i32 0, i32 42, i1 0, i1 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}buffer_store_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_dwordx3 v[0:2], off, s[0:3], 0 offset:42
|
|
define amdgpu_ps void @buffer_store_immoffs_x3(<4 x i32> inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.buffer.store.v3f32(<3 x float> %1, <4 x i32> %0, i32 0, i32 42, i1 0, i1 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}raw_buffer_store_format_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_format_xyz v[0:2], off, s[0:3], 0 offset:42
|
|
define amdgpu_ps void @raw_buffer_store_format_immoffs_x3(<4 x i32> inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.raw.buffer.store.format.v3f32(<3 x float> %1, <4 x i32> %0, i32 42, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}raw_buffer_store_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_dwordx3 v[0:2], off, s[0:3], 0 offset:42
|
|
define amdgpu_ps void @raw_buffer_store_immoffs_x3(<4 x i32> inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.raw.buffer.store.v3f32(<3 x float> %1, <4 x i32> %0, i32 42, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}struct_buffer_store_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
|
|
define amdgpu_ps void @struct_buffer_store_immoffs_x3(<4 x i32> inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.struct.buffer.store.v3f32(<3 x float> %1, <4 x i32> %0, i32 0, i32 42, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}raw_ptr_buffer_store_format_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_format_xyz v[0:2], off, s[0:3], 0 offset:42
|
|
define amdgpu_ps void @raw_ptr_buffer_store_format_immoffs_x3(ptr addrspace(8) inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.format.v3f32(<3 x float> %1, ptr addrspace(8) %0, i32 42, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}raw_ptr_buffer_store_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_dwordx3 v[0:2], off, s[0:3], 0 offset:42
|
|
define amdgpu_ps void @raw_ptr_buffer_store_immoffs_x3(ptr addrspace(8) inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.raw.ptr.buffer.store.v3f32(<3 x float> %1, ptr addrspace(8) %0, i32 42, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}struct_ptr_buffer_store_immoffs_x3:
|
|
;CHECK-NOT: s_waitcnt
|
|
;CHECK: buffer_store_dwordx3 v[0:2], {{v[0-9]+}}, s[0:3], 0 idxen offset:42
|
|
define amdgpu_ps void @struct_ptr_buffer_store_immoffs_x3(ptr addrspace(8) inreg, <3 x float>) {
|
|
main_body:
|
|
call void @llvm.amdgcn.struct.ptr.buffer.store.v3f32(<3 x float> %1, ptr addrspace(8) %0, i32 0, i32 42, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.amdgcn.buffer.store.v3f32(<3 x float>, <4 x i32>, i32, i32, i1, i1) #0
|
|
declare void @llvm.amdgcn.buffer.store.format.v3f32(<3 x float>, <4 x i32>, i32, i32, i1, i1) #0
|
|
declare void @llvm.amdgcn.raw.buffer.store.format.v3f32(<3 x float>, <4 x i32>, i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.raw.buffer.store.v3f32(<3 x float>, <4 x i32>, i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.struct.buffer.store.format.v3f32(<3 x float>, <4 x i32>, i32, i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.struct.buffer.store.v3f32(<3 x float>, <4 x i32>, i32, i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.raw.ptr.buffer.store.format.v3f32(<3 x float>, ptr addrspace(8), i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.raw.ptr.buffer.store.v3f32(<3 x float>, ptr addrspace(8), i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.struct.ptr.buffer.store.format.v3f32(<3 x float>, ptr addrspace(8), i32, i32, i32, i32) #0
|
|
declare void @llvm.amdgcn.struct.ptr.buffer.store.v3f32(<3 x float>, ptr addrspace(8), i32, i32, i32, i32) #0
|