[PATCH] R600/SI: Fix crash in SIInstrInfo::areLoadsFromSameBasePtr()

[Matt Arsenault]

> On Mar 20, 2015, at 5:15 PM, Tom Stellard <thomas.stellard at amd.com> wrote:
> 
> This function assumed that SMRD instructions always have immediate
> offsets, which is not always the case.
> ---
> lib/Target/R600/SIInstrInfo.cpp                | 12 +++++++--
> test/CodeGen/R600/schedule-kernel-arg-loads.ll | 35 ++++++++++++++++++++++++--
> 2 files changed, 43 insertions(+), 4 deletions(-)
> 

LGTM. How did you run into this? I thought this was dead code since the mi scheduler was enabled