ee13638362
Since e39f6c1844fab59c638d8059a6cf139adb42279a opt will infer the correct datalayout when given a triple. Avoid explicitly specifying it in tests that depend on the AMDGPU target being present to avoid the string becoming out of sync with the TargetInfo value. Only tests with REQUIRES: amdgpu-registered-target or a local lit.cfg were updated to ensure that tests for non-target-specific passes that happen to use the AMDGPU layout still pass when building with a limited set of targets. Reviewed By: shiltian, arsenm Pull Request: https://github.com/llvm/llvm-project/pull/137921
21 lines
727 B
LLVM
21 lines
727 B
LLVM
; RUN: llc -mtriple=amdgcn-- -mcpu=unknown -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR -check-prefix=GCN %s
|
|
; RUN: llc -mtriple=r600-- -mcpu=unknown -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR -check-prefix=R600 %s
|
|
|
|
; Should not crash when the processor is not recognized and the
|
|
; wavefront size feature not set.
|
|
|
|
; Should also not have fragments of r600 and gcn isa mixed.
|
|
|
|
; ERROR: 'unknown' is not a recognized processor for this target (ignoring processor)
|
|
|
|
; GCN-NOT: MOV
|
|
; GCN: buffer_store_dword
|
|
; GCN: ScratchSize: 8{{$}}
|
|
|
|
; R600: MOV
|
|
define amdgpu_kernel void @foo() {
|
|
%alloca = alloca i32, align 4, addrspace(5)
|
|
store volatile i32 0, ptr addrspace(5) %alloca
|
|
ret void
|
|
}
|