On Sat, May 16, 2015 at 11:25 AM, Matt Turner wrote:
> On Sat, May 16, 2015 at 8:37 AM, Jason Ekstrand wrote:
>> On Fri, May 15, 2015 at 2:02 PM, Matt Turner wrote:
>>> 32-bit x 32-bit integer multiplication requires multiple instructions
>>> until Broadwell. This patch just lets us treat the MU
On Sat, May 16, 2015 at 8:37 AM, Jason Ekstrand wrote:
> On Fri, May 15, 2015 at 2:02 PM, Matt Turner wrote:
>> 32-bit x 32-bit integer multiplication requires multiple instructions
>> until Broadwell. This patch just lets us treat the MUL instruction in
>> the FS backend like it operates on Broa
On Fri, May 15, 2015 at 2:02 PM, Matt Turner wrote:
> 32-bit x 32-bit integer multiplication requires multiple instructions
> until Broadwell. This patch just lets us treat the MUL instruction in
> the FS backend like it operates on Broadwell, and after optimizations
> we lower it into a sequence
32-bit x 32-bit integer multiplication requires multiple instructions
until Broadwell. This patch just lets us treat the MUL instruction in
the FS backend like it operates on Broadwell, and after optimizations
we lower it into a sequence of instructions on older platforms.
Doing this will allow us
