6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-13 04:30:23 +00:00
Code Issues Projects Releases Wiki Activity

R600: Fix R600ControlFlowFinalizer not considering VTX_READ 128 bit dst reg

Browse Source 
Patch by: Vincent Lejeune

https://bugs.freedesktop.org/show_bug.cgi?id=64877

NOTE: This is a candidate for the 3.3 branch.


Merged from r182600
Author: Tom Stellard <thomas.stellard@amd.com>
Date:   Thu May 23 18:26:42 2013 +0000

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_33@185868 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tom Stellard 2013-07-08 21:20:22 +00:00
parent ce337502f5
commit c4a246996d
2 changed files with 31 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
lib/Target/R600/R600ControlFlowFinalizer.cpp
View File

@ -116,8 +116,15 @@ private:
const MachineOperand &MO = *I; const MachineOperand &MO = *I;
if (!MO.isReg()) if (!MO.isReg())
continue; continue;
if (MO.isDef()) if (MO.isDef()) {
DstMI = MO.getReg(); unsigned Reg = MO.getReg();
if (AMDGPU::R600_Reg128RegClass.contains(Reg))
DstMI = Reg;
else
DstMI = TRI.getMatchingSuperReg(Reg,
TRI.getSubRegFromChannel(TRI.getHWRegChan(Reg)),
&AMDGPU::R600_Reg128RegClass);
}
if (MO.isUse()) { if (MO.isUse()) {
unsigned Reg = MO.getReg(); unsigned Reg = MO.getReg();
if (AMDGPU::R600_Reg128RegClass.contains(Reg)) if (AMDGPU::R600_Reg128RegClass.contains(Reg))

22
test/CodeGen/R600/vtx-schedule.ll Normal file
View File

@ -0,0 +1,22 @@
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
; This test is for a scheduler bug where VTX_READ instructions that used
; the result of another VTX_READ instruction were being grouped in the
; same fetch clasue.
; CHECK: @test
; CHECK: Fetch clause
; CHECK_VTX_READ_32 [[IN0:T[0-9]+\.X]], [[IN0]], 40
; CHECK_VTX_READ_32 [[IN1:T[0-9]+\.X]], [[IN1]], 44
; CHECK: Fetch clause
; CHECK_VTX_READ_32 [[IN0:T[0-9]+\.X]], [[IN0]], 0
; CHECK_VTX_READ_32 [[IN1:T[0-9]+\.X]], [[IN1]], 0
define void @test(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in0, i32 addrspace(1)* nocapture %in1) {
entry:
%0 = load i32 addrspace(1)* %in0, align 4
%1 = load i32 addrspace(1)* %in1, align 4
%cmp.i = icmp slt i32 %0, %1
%cond.i = select i1 %cmp.i, i32 %0, i32 %1
store i32 %cond.i, i32 addrspace(1)* %out, align 4
ret void
}