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
```
45 lines
2.0 KiB
LLVM
45 lines
2.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=module | FileCheck -check-prefix=OPT %s
|
|
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=module | FileCheck -check-prefix=OPT %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s --amdgpu-lower-module-lds-strategy=module | FileCheck -check-prefix=GCN %s
|
|
|
|
; Check that module LDS is allocated at address 0 and kernel starts its
|
|
; allocation past module LDS when a call is present.
|
|
|
|
@lds.size.1.align.1 = internal unnamed_addr addrspace(3) global [1 x i8] undef, align 1
|
|
@lds.size.16.align.16 = internal unnamed_addr addrspace(3) global [16 x i8] undef, align 16
|
|
|
|
; GCN-LABEL: {{^}}k0:
|
|
; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0
|
|
; GCN-DAG: v_mov_b32_e32 [[ONE:v[0-9]+]], 1
|
|
; GCN: ds_write_b8 [[NULL]], [[ONE]]
|
|
; GCN: v_mov_b32_e32 [[TWO:v[0-9]+]], 2
|
|
; GCN: ds_write_b8 [[NULL]], [[TWO]] offset:16
|
|
define amdgpu_kernel void @k0() {
|
|
; OPT-LABEL: @k0(
|
|
; OPT-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds) ]
|
|
; OPT-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
|
|
; OPT-NEXT: store i8 1, ptr addrspace(3) @llvm.amdgcn.module.lds, align 1
|
|
; OPT-NEXT: store i8 2, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 16
|
|
; OPT-NEXT: call void @f0()
|
|
; OPT-NEXT: ret void
|
|
;
|
|
store i8 1, ptr addrspace(3) @lds.size.1.align.1, align 1
|
|
store i8 2, ptr addrspace(3) @lds.size.16.align.16, align 16
|
|
call void @f0()
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}f0:
|
|
; GCN-DAG: v_mov_b32_e32 [[NULL:v[0-9]+]], 0
|
|
; GCN-DAG: v_mov_b32_e32 [[TREE:v[0-9]+]], 3
|
|
; GCN: ds_write_b8 [[NULL]], [[TREE]]
|
|
define void @f0() {
|
|
; OPT-LABEL: @f0() {
|
|
; OPT-NEXT: store i8 3, ptr addrspace(3) @llvm.amdgcn.module.lds, align 1
|
|
; OPT-NEXT: ret void
|
|
;
|
|
store i8 3, ptr addrspace(3) @lds.size.1.align.1, align 1
|
|
ret void
|
|
}
|