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/waitcnt-flat.ll

29 lines
1.2 KiB
LLVM
Raw Normal View History

AMDGPU: Start selecting global instructions llvm-svn: 309470
2017-07-29 09:03:53 +08:00
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s
AMDGPU/SI: Fix s_waitcnt insertion for flat instructions Summary: This was broken in r260694 which swapped the address and data operands for flat store instructions. The code in SIInsertWaits assumes that the data operand always comes before the address operand, so we need to add a special case for flat. Reviewers: arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17366 llvm-svn: 261330
2016-02-19 23:33:13 +08:00
; If flat_store_dword and flat_load_dword use different registers for the data
; operand, this test is not broken. It just means it is no longer testing
; for the original bug.
; GCN: {{^}}test:
AMDGPU: Define priorities for register classes Allocating larger register classes first should give better allocation results (and more importantly for myself, make the lit tests more stable with respect to scheduler changes). Patch by Matthias Braun llvm-svn: 270312
2016-05-21 11:55:07 +08:00
; XGCN: flat_store_dword v[{{[0-9]+:[0-9]+}}], [[DATA:v[0-9]+]]
; XGCN: s_waitcnt vmcnt(0) lgkmcnt(0)
; XGCN: flat_load_dword [[DATA]], v[{{[0-9]+:[0-9]+}}]
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
define amdgpu_kernel void @test(i32* %out, i32 %in) {
store volatile i32 0, i32* %out
%val = load volatile i32, i32* %out
AMDGPU: Start selecting global instructions llvm-svn: 309470
2017-07-29 09:03:53 +08:00
ret void
}
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
; Make sure lgkmcnt isn't used for global_ addrspace(5)* instructions
AMDGPU: Start selecting global instructions llvm-svn: 309470
2017-07-29 09:03:53 +08:00
; GCN-LABEL: {{^}}test_waitcnt_type_flat_global:
; GFX9: global_load_dword [[LD:v[0-9]+]]
; GFX9-NEXT: s_waitcnt vmcnt(0){{$}}
; GFX9-NEXT: ds_write_b32 [[LD]]
define amdgpu_kernel void @test_waitcnt_type_flat_global(i32 addrspace(1)* %in) {
%val = load volatile i32, i32 addrspace(1)* %in
store volatile i32 %val, i32 addrspace(3)* undef
AMDGPU/SI: Fix s_waitcnt insertion for flat instructions Summary: This was broken in r260694 which swapped the address and data operands for flat store instructions. The code in SIInsertWaits assumes that the data operand always comes before the address operand, so we need to add a special case for flat. Reviewers: arsenm Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17366 llvm-svn: 261330
2016-02-19 23:33:13 +08:00
ret void
}