maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Remove the s_buffer workaround for GFX9 chips 

Summary:
I checked the AMD closed source compiler and the workaround is only
needed when x3 is emulated as x4, which we don't do in LLVM.

SMEM x3 opcodes don't exist, and instead there is a possibility to use x4
with the last component being unused. If the last component is out of
buffer bounds and falls on the next 4K page, the hw hangs.

Reviewers: arsenm, nhaehnle

Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye

Differential Revision: https://reviews.llvm.org/D42756

llvm-svn: 324486
This commit is contained in:
Marek Olsak 2018-02-07 16:00:40 +00:00
parent b4e789e8f6
commit b2cc77985b
3 changed files with 4 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
View File

@ -333,14 +333,6 @@ public:
return HasMadMixInsts;
}
bool hasSBufferLoadStoreAtomicDwordxN() const {
// Only use the "x1" variants on GFX9 or don't use the buffer variants.
// For x2 and higher variants, if the accessed region spans 2 VM pages and
// the second page is unmapped, the hw hangs.
// TODO: There is one future GFX9 chip that doesn't have this bug.
return getGeneration() != GFX9;
}
bool hasCARRY() const {
return (getGeneration() >= EVERGREEN);
}

5
llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
View File

@ -853,9 +853,8 @@ bool SILoadStoreOptimizer::optimizeBlock(MachineBasicBlock &MBB) {
continue;
}
if (STM->hasSBufferLoadStoreAtomicDwordxN() &&
(Opc == AMDGPU::S_BUFFER_LOAD_DWORD_IMM ||
Opc == AMDGPU::S_BUFFER_LOAD_DWORDX2_IMM)) {
if (Opc == AMDGPU::S_BUFFER_LOAD_DWORD_IMM ||
Opc == AMDGPU::S_BUFFER_LOAD_DWORDX2_IMM) {
// EltSize is in units of the offset encoding.
CI.InstClass = S_BUFFER_LOAD_IMM;
CI.EltSize = AMDGPU::getSMRDEncodedOffset(*STM, 4);

10
llvm/test/CodeGen/AMDGPU/smrd.ll
View File

@ -217,14 +217,8 @@ main_body:
; GCN-NEXT: %bb.
; SICI-NEXT: s_buffer_load_dwordx4 s[{{[0-9]}}:{{[0-9]}}], s[0:3], 0x1
; SICI-NEXT: s_buffer_load_dwordx2 s[{{[0-9]}}:{{[0-9]}}], s[0:3], 0x7
; VI-NEXT: s_buffer_load_dwordx4 s[{{[0-9]}}:{{[0-9]}}], s[0:3], 0x4
; VI-NEXT: s_buffer_load_dwordx2 s[{{[0-9]}}:{{[0-9]}}], s[0:3], 0x1c
; GFX9-NEXT: s_buffer_load_dword s{{[0-9]}}
; GFX9-NEXT: s_buffer_load_dword s{{[0-9]}}
; GFX9-NEXT: s_buffer_load_dword s{{[0-9]}}
; GFX9-NEXT: s_buffer_load_dword s{{[0-9]}}
; GFX9-NEXT: s_buffer_load_dword s{{[0-9]}}
; GFX9-NEXT: s_buffer_load_dword s{{[0-9]}}
; VIGFX9-NEXT: s_buffer_load_dwordx4 s[{{[0-9]}}:{{[0-9]}}], s[0:3], 0x4
; VIGFX9-NEXT: s_buffer_load_dwordx2 s[{{[0-9]}}:{{[0-9]}}], s[0:3], 0x1c
define amdgpu_ps void @smrd_imm_merged(<4 x i32> inreg %desc) #0 {
main_body:
%r1 = call float @llvm.SI.load.const.v4i32(<4 x i32> %desc, i32 4)