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
```
29 lines
1.4 KiB
LLVM
29 lines
1.4 KiB
LLVM
; RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx906 -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefixes=GFX906 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx908 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX908 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX90A %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX940 %s
|
|
; RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx1030 -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefixes=GFX1030 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX1100 %s
|
|
|
|
; GFX906: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.global.atomic.fadd
|
|
|
|
; GFX908-LABEL: fadd_test:
|
|
; GFX908: global_atomic_add_f32
|
|
|
|
; GFX90A-LABEL: fadd_test:
|
|
; GFX90A: global_atomic_add_f32
|
|
|
|
; GFX940-LABEL: fadd_test:
|
|
; GFX940: global_atomic_add_f32
|
|
|
|
; GFX1030: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.global.atomic.fadd
|
|
|
|
; GFX1100-LABEL: fadd_test:
|
|
; GFX1100: global_atomic_add_f32
|
|
|
|
define fastcc void @fadd_test(ptr addrspace(1) nocapture noundef %0, float noundef %1) unnamed_addr {
|
|
%3 = tail call float @llvm.amdgcn.global.atomic.fadd.f32.p1.f32(ptr addrspace(1) noundef %0, float noundef %1)
|
|
ret void
|
|
}
|
|
declare float @llvm.amdgcn.global.atomic.fadd.f32.p1.f32(ptr addrspace(1) nocapture, float)
|