[llvm] r328695 - Revert "[AMDGPU] For OS type AMDPAL, fixed scratch on compute shader"
Tim Renouf via llvm-commits
llvm-commits at lists.llvm.org
Wed Mar 28 04:21:08 PDT 2018
Author: tpr
Date: Wed Mar 28 04:21:07 2018
New Revision: 328695
URL: http://llvm.org/viewvc/llvm-project?rev=328695&view=rev
Log:
Revert "[AMDGPU] For OS type AMDPAL, fixed scratch on compute shader"
This reverts commit 0daf86291d3aa04d3cc280cd0ef24abdb0174981.
It was causing an assert in test/CodeGen/AMDGPU/amdpal.ll only on a
release-with-asserts build. I will resubmit the change when I have fixed
that.
Change-Id: If270594eba27a7dc4076bdeab3fa8e6bfda3288a
Modified:
llvm/trunk/lib/Target/AMDGPU/SIFrameLowering.cpp
llvm/trunk/test/CodeGen/AMDGPU/amdpal.ll
Modified: llvm/trunk/lib/Target/AMDGPU/SIFrameLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIFrameLowering.cpp?rev=328695&r1=328694&r2=328695&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIFrameLowering.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/SIFrameLowering.cpp Wed Mar 28 04:21:07 2018
@@ -405,7 +405,7 @@ void SIFrameLowering::emitEntryFunctionS
.addReg(ScratchRsrcReg, RegState::ImplicitDefine);
// We now have the GIT ptr - now get the scratch descriptor from the entry
- // at offset 0 (or offset 16 for a compute shader).
+ // at offset 0.
PointerType *PtrTy =
PointerType::get(Type::getInt64Ty(MF.getFunction().getContext()),
AMDGPUAS::CONSTANT_ADDRESS);
@@ -416,11 +416,9 @@ void SIFrameLowering::emitEntryFunctionS
MachineMemOperand::MOInvariant |
MachineMemOperand::MODereferenceable,
0, 0);
- unsigned Offset
- = MF.getFunction().getCallingConv() == CallingConv::AMDGPU_CS ? 16 : 0;
BuildMI(MBB, I, DL, LoadDwordX4, ScratchRsrcReg)
.addReg(Rsrc01)
- .addImm(Offset) // offset
+ .addImm(0) // offset
.addImm(0) // glc
.addReg(ScratchRsrcReg, RegState::ImplicitDefine)
.addMemOperand(MMO);
Modified: llvm/trunk/test/CodeGen/AMDGPU/amdpal.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/amdpal.ll?rev=328695&r1=328694&r2=328695&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/amdpal.ll (original)
+++ llvm/trunk/test/CodeGen/AMDGPU/amdpal.ll Wed Mar 28 04:21:07 2018
@@ -52,36 +52,7 @@ entry:
ret void
}
-; Check code sequence for amdpal use of scratch for alloca in a compute shader.
-; The scratch descriptor is loaded from offset 0x10 of the GIT, rather than offset
-; 0 in a graphics shader.
-
-; PAL-LABEL: {{^}}scratch2_cs:
-; PAL: s_movk_i32 s{{[0-9]+}}, 0x1234
-; PAL: s_mov_b32 s[[GITPTR:[0-9]+]], s0
-; PAL: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:{{[0-9]+\]}}, 0x10
-; PAL: buffer_store{{.*}}, s{{\[}}[[SCRATCHDESC]]:
-
-define amdgpu_cs void @scratch2_cs(i32 inreg, i32 inreg, i32 inreg, <3 x i32> inreg, i32 inreg, <3 x i32> %coord, <2 x i32> %in, i32 %extra, i32 %idx) #0 {
-entry:
- %v = alloca [3 x i32], addrspace(5)
- %v0 = getelementptr [3 x i32], [3 x i32] addrspace(5)* %v, i32 0, i32 0
- %v1 = getelementptr [3 x i32], [3 x i32] addrspace(5)* %v, i32 0, i32 1
- store i32 %extra, i32 addrspace(5)* %v0
- %v1a = bitcast i32 addrspace(5)* %v1 to [2 x i32] addrspace(5)*
- %vv = bitcast [2 x i32] addrspace(5)* %v1a to <2 x i32> addrspace(5)*
- store <2 x i32> %in, <2 x i32> addrspace(5)* %vv
- %e = getelementptr [2 x i32], [2 x i32] addrspace(5)* %v1a, i32 0, i32 %idx
- %x = load i32, i32 addrspace(5)* %e
- %xf = bitcast i32 %x to float
- call void @llvm.amdgcn.buffer.store.f32(float %xf, <4 x i32> undef, i32 0, i32 0, i1 0, i1 0)
- ret void
-}
-
attributes #0 = { nounwind "amdgpu-git-ptr-high"="0x1234" }
-declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1)
-
-
; Check we have CS_NUM_USED_VGPRS in PAL metadata.
; PAL: .amd_amdgpu_pal_metadata {{.*}},0x10000027,
More information about the llvm-commits
mailing list