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/spill-alloc-sgpr-init-bug.ll

29 lines
1.3 KiB
LLVM
Raw Normal View History

AMDGPU: Fix using incorrect private resource with no allocation It's possible to have a use of the private resource descriptor or scratch wave offset registers even though there are no allocated stack objects. This would result in continuing to use the maximum number reserved registers. This could go over the number of SGPRs available on VI, or violate the SGPR limit requested by the function attributes. llvm-svn: 285435
2016-10-29 03:43:31 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefix=TONGA %s
AMDGPU/SI: Do not move scratch resource register on Tonga & Iceland Due to the SGPR init bug, every program claims to use the same number of SGPRs anyway, so there's no point in trying to shift those registers down from their initial spot of reservation. Add a test that uses VGPR spilling and blocks most SGPRs from being used for the scratch resource register. Previously, this would run into an assertion. Differential Revision: http://reviews.llvm.org/D15724 llvm-svn: 256870
2016-01-06 04:42:49 +08:00
; On Tonga and Iceland, limited SGPR availability means care must be taken to
; allocate scratch registers correctly. Check that this test compiles without
; error.
; TONGA-LABEL: test
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(<256 x i32> addrspace(1)* %out, <256 x i32> addrspace(1)* %in) {
AMDGPU/SI: Do not move scratch resource register on Tonga & Iceland Due to the SGPR init bug, every program claims to use the same number of SGPRs anyway, so there's no point in trying to shift those registers down from their initial spot of reservation. Add a test that uses VGPR spilling and blocks most SGPRs from being used for the scratch resource register. Previously, this would run into an assertion. Differential Revision: http://reviews.llvm.org/D15724 llvm-svn: 256870
2016-01-06 04:42:49 +08:00
entry:
AMDGPU: Remove llvm.SI.tid intrinsic Mesa doesn't emit this for llvm >= 3.8 anymore. llvm-svn: 273050
2016-06-18 05:18:41 +08:00
%mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0)
%tid = call i32 @llvm.amdgcn.mbcnt.hi(i32 -1, i32 %mbcnt.lo)
AMDGPU/SI: Do not move scratch resource register on Tonga & Iceland Due to the SGPR init bug, every program claims to use the same number of SGPRs anyway, so there's no point in trying to shift those registers down from their initial spot of reservation. Add a test that uses VGPR spilling and blocks most SGPRs from being used for the scratch resource register. Previously, this would run into an assertion. Differential Revision: http://reviews.llvm.org/D15724 llvm-svn: 256870
2016-01-06 04:42:49 +08:00
%aptr = getelementptr <256 x i32>, <256 x i32> addrspace(1)* %in, i32 %tid
%a = load <256 x i32>, <256 x i32> addrspace(1)* %aptr
call void asm sideeffect "", "~{memory}" ()
%outptr = getelementptr <256 x i32>, <256 x i32> addrspace(1)* %in, i32 %tid
store <256 x i32> %a, <256 x i32> addrspace(1)* %outptr
; mark 128-bit SGPR registers as used so they are unavailable for the
; scratch resource descriptor
AMDGPU: Fix register name format in tests These were changed to match the asm output name a long time ago, although I think the old tablegenerated names still work. llvm-svn: 328651
2018-03-28 02:39:42 +08:00
call void asm sideeffect "", "~{s4},~{s8},~{s12},~{s16},~{s20},~{s24},~{s28}" ()
call void asm sideeffect "", "~{s32},~{s36},~{s40},~{s44},~{s48},~{s52},~{s56}" ()
call void asm sideeffect "", "~{s60},~{s64},~{s68}" ()
AMDGPU/SI: Do not move scratch resource register on Tonga & Iceland Due to the SGPR init bug, every program claims to use the same number of SGPRs anyway, so there's no point in trying to shift those registers down from their initial spot of reservation. Add a test that uses VGPR spilling and blocks most SGPRs from being used for the scratch resource register. Previously, this would run into an assertion. Differential Revision: http://reviews.llvm.org/D15724 llvm-svn: 256870
2016-01-06 04:42:49 +08:00
ret void
}
AMDGPU: Remove llvm.SI.tid intrinsic Mesa doesn't emit this for llvm >= 3.8 anymore. llvm-svn: 273050
2016-06-18 05:18:41 +08:00
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #0
declare i32 @llvm.amdgcn.mbcnt.hi(i32, i32) #0
attributes #0 = { nounwind readnone }