On Mon, Jan 18, 2016 at 12:40 AM, Jose Fonseca wrote:
> On 17/01/16 20:55, Oded Gabbay wrote:
>>
>> This patch fixes a bug when building a pack instruction.
>>
>> For POWER (altivec), in case the destination is signed and the
>> src width is 32, we need to use vpkswss. The original code used vpkuw
On Sun, Jan 17, 2016 at 11:16 PM, Roland Scheidegger wrote:
> Reviewed-by: Roland Scheidegger
>
> Am 17.01.2016 um 21:55 schrieb Oded Gabbay:
>> This patch fixes a bug when building a pack instruction.
>>
>> For POWER (altivec), in case the destination is signed and the
>> src width is 32, we nee
On 17/01/16 20:55, Oded Gabbay wrote:
This patch fixes a bug when building a pack instruction.
For POWER (altivec), in case the destination is signed and the
src width is 32, we need to use vpkswss. The original code used vpkuwus,
which emits an unsigned result.
This fixes the following piglit
Reviewed-by: Roland Scheidegger
Am 17.01.2016 um 21:55 schrieb Oded Gabbay:
> This patch fixes a bug when building a pack instruction.
>
> For POWER (altivec), in case the destination is signed and the
> src width is 32, we need to use vpkswss. The original code used vpkuwus,
> which emits an un
This patch fixes a bug when building a pack instruction.
For POWER (altivec), in case the destination is signed and the
src width is 32, we need to use vpkswss. The original code used vpkuwus,
which emits an unsigned result.
This fixes the following piglit tests on ppc64le:
- spec@arb_color_buffe