54cf69c9d5
Summary: This patch introduces a mechanism to check the code object version from the module flag, This avoids checking from command line. In case the module flag is missing, we use the current default code object version supported in the compiler. For tools whose inputs are not IR, we may need other approach (directive, for example) to check the code object version, That will be in a separate patch later. For LIT tests update, we directly add module flag if there is only a single code object version associated with all checks in one file. In cause of multiple code object version in one file, we use the "sed" method to "clone" the checks to achieve the goal. Reviewer: arsenm Differential Revision: https://reviews.llvm.org/D14313
40 lines
1.1 KiB
LLVM
40 lines
1.1 KiB
LLVM
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=ALL -check-prefix=HSA %s
|
|
; RUN: llc -global-isel=1 -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=ALL -check-prefix=HSA %s
|
|
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=ALL -check-prefix=EG %s
|
|
|
|
; This test makes sure we do not double count global values when they are
|
|
; used in different basic blocks.
|
|
|
|
; GCN: .long 47180
|
|
; GCN-NEXT: .long 32900
|
|
|
|
; EG: .long 166120
|
|
; EG-NEXT: .long 1
|
|
; ALL: {{^}}test:
|
|
|
|
; HSA: granulated_lds_size = 0
|
|
; HSA: workgroup_group_segment_byte_size = 4
|
|
|
|
; GCN: ; LDSByteSize: 4 bytes/workgroup (compile time only)
|
|
@lds = internal unnamed_addr addrspace(3) global i32 undef, align 4
|
|
|
|
define amdgpu_kernel void @test(ptr addrspace(1) %out, i32 %cond) {
|
|
entry:
|
|
%0 = icmp eq i32 %cond, 0
|
|
br i1 %0, label %if, label %else
|
|
|
|
if:
|
|
store i32 1, ptr addrspace(3) @lds
|
|
br label %endif
|
|
|
|
else:
|
|
store i32 2, ptr addrspace(3) @lds
|
|
br label %endif
|
|
|
|
endif:
|
|
ret void
|
|
}
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
|