maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.memtime.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

27 lines
1.2 KiB
LLVM
Raw Normal View History

[AMDGPU] Fix some tests that did not specify -mcpu Summary: This fixes some tests that did not specify -mcpu. Doing that disables all subtarget features, which gives behavior that (a) does not necessarily correspond to any actual target, and (b) can change as we add new subtarget features. Also added gfx1010 to memtime test. Differential Revision: https://reviews.llvm.org/D74594 Change-Id: I8c0fe4fa03e9a93ef8bb722cd42d22e064526309
2020-02-13 19:44:52 +08:00
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=SIVI -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=SIVI -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
[AMDGPU] Add gfx1030 target Differential Revision: https://reviews.llvm.org/D81886
2020-06-16 05:10:39 +08:00
; RUN: not --crash llc -march=amdgcn -mcpu=gfx1030 -mattr=-flat-for-global -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=GFX1030-ERR %s
AMDGPU: Implement readcyclecounter This matches the behavior of the HSAIL clock instruction. s_realmemtime is used if the subtarget supports it, and falls back to s_memtime if not. Also introduces new intrinsics for each of s_memtime / s_memrealtime. llvm-svn: 262119
2016-02-27 16:53:46 +08:00
declare i64 @llvm.amdgcn.s.memtime() #0
; GCN-LABEL: {{^}}test_s_memtime:
; GCN-DAG: s_memtime s{{\[[0-9]+:[0-9]+\]}}
; GCN-DAG: s_load_dwordx2
; GCN: lgkmcnt
[AMDGPU] Fix some tests that did not specify -mcpu Summary: This fixes some tests that did not specify -mcpu. Doing that disables all subtarget features, which gives behavior that (a) does not necessarily correspond to any actual target, and (b) can change as we add new subtarget features. Also added gfx1010 to memtime test. Differential Revision: https://reviews.llvm.org/D74594 Change-Id: I8c0fe4fa03e9a93ef8bb722cd42d22e064526309
2020-02-13 19:44:52 +08:00
; GCN: {{buffer|global}}_store_dwordx2
; SIVI-NOT: lgkmcnt
AMDGPU: Implement readcyclecounter This matches the behavior of the HSAIL clock instruction. s_realmemtime is used if the subtarget supports it, and falls back to s_memtime if not. Also introduces new intrinsics for each of s_memtime / s_memrealtime. llvm-svn: 262119
2016-02-27 16:53:46 +08:00
; GCN: s_memtime s{{\[[0-9]+:[0-9]+\]}}
[AMDGPU] Fix some tests that did not specify -mcpu Summary: This fixes some tests that did not specify -mcpu. Doing that disables all subtarget features, which gives behavior that (a) does not necessarily correspond to any actual target, and (b) can change as we add new subtarget features. Also added gfx1010 to memtime test. Differential Revision: https://reviews.llvm.org/D74594 Change-Id: I8c0fe4fa03e9a93ef8bb722cd42d22e064526309
2020-02-13 19:44:52 +08:00
; GCN: {{buffer|global}}_store_dwordx2
[AMDGPU] Add gfx1030 target Differential Revision: https://reviews.llvm.org/D81886
2020-06-16 05:10:39 +08:00
; GFX1030-ERR: ERROR
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_s_memtime(i64 addrspace(1)* %out) #0 {
AMDGPU: Implement readcyclecounter This matches the behavior of the HSAIL clock instruction. s_realmemtime is used if the subtarget supports it, and falls back to s_memtime if not. Also introduces new intrinsics for each of s_memtime / s_memrealtime. llvm-svn: 262119
2016-02-27 16:53:46 +08:00
%cycle0 = call i64 @llvm.amdgcn.s.memtime()
store volatile i64 %cycle0, i64 addrspace(1)* %out
%cycle1 = call i64 @llvm.amdgcn.s.memtime()
store volatile i64 %cycle1, i64 addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }