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

AMDGPU/SI: Fix a GPU hang with POS_W_FLOAT enabled 

Reviewers: tstellarAMD, arsenm

Subscribers: arsenm

Differential Revision: http://reviews.llvm.org/D16037

llvm-svn: 257625
This commit is contained in:
Marek Olsak 2016-01-13 17:23:20 +00:00
parent 774c0d689f
commit 46dadbfab2
2 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@ -646,8 +646,15 @@ SDValue SITargetLowering::LowerFormalArguments(
// based on run-time states. Since we can't know what the final PSInputEna
// will look like, so we shouldn't do anything here and the user should take
// responsibility for the correct programming.
//
// Otherwise, the following restrictions apply:
// - At least one of PERSP_* (0xF) or LINEAR_* (0x70) must be enabled.
// - If POS_W_FLOAT (11) is enabled, at least one of PERSP_* must be
// enabled too.
if (Info->getShaderType() == ShaderType::PIXEL &&
(Info->getPSInputAddr() & 0x7F) == 0) {
((Info->getPSInputAddr() & 0x7F) == 0 ||
((Info->getPSInputAddr() & 0xF) == 0 &&
Info->isPSInputAllocated(11)))) {
CCInfo.AllocateReg(AMDGPU::VGPR0);
CCInfo.AllocateReg(AMDGPU::VGPR1);
Info->markPSInputAllocated(0);

17
llvm/test/CodeGen/AMDGPU/ret.ll
View File

@ -76,6 +76,23 @@ define float @ps_input_ena_no_inputs([9 x <16 x i8>] addrspace(2)* byval, i32 in
}
; GCN: .long 165580
; GCN-NEXT: .long 2081
; GCN-NEXT: .long 165584
; GCN-NEXT: .long 2081
; GCN-LABEL: {{^}}ps_input_ena_pos_w:
; GCN-DAG: v_mov_b32_e32 v0, v4
; GCN-DAG: v_mov_b32_e32 v1, v2
; GCN: v_mov_b32_e32 v2, v3
; GCN-NOT: s_endpgm
define {float, <2 x float>} @ps_input_ena_pos_w([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) #1 {
%f = bitcast <2 x i32> %8 to <2 x float>
%s = insertvalue {float, <2 x float>} undef, float %14, 0
%s1 = insertvalue {float, <2 x float>} %s, <2 x float> %f, 1
ret {float, <2 x float>} %s1
}
; GCN: .long 165580
; GCN-NEXT: .long 562
; GCN-NEXT: .long 165584