[llvm-dev] KNL Vectorization with larger vector width

[hameeza ahmed via llvm-dev]

Please help.
I need to vectorize remainder loops because with large iterations and
vector width remainder scalar iterations are big problem.

On Sat, Jul 28, 2018 at 4:12 PM, hameeza ahmed <hahmed2305 at gmail.com> wrote:

> Thank You.
>
> I am currently seeing how LLVM treats remainder loops. For eg with 63 loop
> iterations i get 3 v16i32 and 15 scalars. I want to use v8 and v4 for 15
> remainder instructions. How to do this?
>
> I am seeing LoopVectorize.cpp but unable to find the code lines that deal
> with remainder scalar loop iterations.
>
> Please help..
>
>
>
> On Tue, Jul 24, 2018 at 10:54 PM, Friedman, Eli <efriedma at codeaurora.org>
> wrote:
>
>> There currently isn't any implementation of epilog loop vectorization
>> (see https://reviews.llvm.org/D30247, but it never got merged).
>>
>> In some cases you might get lucky with loop unrolling plus SLP
>> vectorization.
>>
>> -Eli
>>
>>
>> On 7/24/2018 10:34 AM, hameeza ahmed wrote:
>>
>> Hello,
>> I need help here. I am able to adjust the vector width through
>> WidestRegister value. When number of iterations=31 and  I set vector
>> width=32 it gives <16xi32> and <8xi32> instructions.
>>
>> However if i replicate same behavior with number of iterations=63 and  I
>> set vector width=64, no vector instructions are emitted. it should do as
>> previous and gives <32xi32> and <16xi32> vector instructions.
>>
>> How to do this?
>> What adjustments are needed?
>>
>> Please help
>>
>> I m trying this but unable to solve.
>>
>> Thank You
>>
>> On Tue, Jul 24, 2018 at 4:44 PM, hameeza ahmed <hahmed2305 at gmail.com>
>> wrote:
>>
>>> Hello,
>>> Do i need to change following function;
>>>
>>> unsigned X86TTIImpl::getNumberOfRegisters(bool Vector) {
>>>   if (Vector && !ST->hasSSE1())
>>>     return 0;
>>>
>>>   if (ST->is64Bit()) {
>>>     if (Vector && ST->hasAVX512())
>>>       return 32;
>>>     return 16;
>>>   }
>>>   return 8;
>>> }
>>>
>>> to
>>>
>>> if (ST->is2048Bit()) {
>>>     if (Vector && ST->hasAVX512())
>>>       return 1024;
>>>     return 512;
>>>   }
>>>   return 256;
>>>
>>>
>>> please help...
>>>
>>> On Tue, Jul 24, 2018 at 5:05 AM, hameeza ahmed <hahmed2305 at gmail.com>
>>> wrote:
>>>
>>>> Thank You.
>>>> Right now to see the effect i did following changes;
>>>>
>>>> unsigned X86TTIImpl::getRegisterBitWidth(bool Vector) {
>>>>   if (Vector) {
>>>>     if (ST->hasAVX512())
>>>>       return 65536;
>>>>
>>>> here i changed 512 to 65536. Then in loopvectorize.cpp i did following;
>>>>
>>>>  assert(MaxVectorSize <= 2048 && "Did not expect to pack so many
>>>> elements"
>>>>                                 " into one vector!");
>>>>
>>>> changed 64 to 2048.
>>>>
>>>> It runs fine. I can see in IR <2048xi32> or <1024xi64> emission.
>>>>
>>>> But I cannot see the vector mix like in default knl if iterations=15 we
>>>> see 1<8xi32> and rest scalar. so here when i keep iteration=2047 i get all
>>>> scalar why is that so? similarly in polly as well i cant see vector mixes
>>>> like its happening for KNL it emits <v16i32>, <v8i32>,<v4i32>...so here it
>>>> should emit recursively like <v2048i32> <v1024i32> <v512i32>.....<v32i32>
>>>>
>>>> how to do this?
>>>>
>>>> What am i missing here?
>>>> what further changes do i need to make?
>>>>
>>>> Please help...
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> On Tue, Jul 24, 2018 at 1:52 AM, Friedman, Eli <efriedma at codeaurora.org
>>>> > wrote:
>>>>
>>>>> On 7/23/2018 12:40 PM, hameeza ahmed wrote:
>>>>>
>>>>>> Thank You. I got it. Version issue.
>>>>>>
>>>>>> TTI.getRegisterBitWidth(true)
>>>>>>
>>>>>> How to put my target machine info in TTI?
>>>>>>
>>>>>
>>>>> Each target has an implementation, e.g. X86TTIImpl::getRegisterBitWidth.
>>>>>
>>>>>
>>>>>
>>>>> -Eli
>>>>>
>>>>> --
>>>>> Employee of Qualcomm Innovation Center, Inc.
>>>>> Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a
>>>>> Linux Foundation Collaborative Project
>>>>>
>>>>>
>>>>
>>>
>> --
>> You received this message because you are subscribed to the Google Groups
>> "Polly Development" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to polly-dev+unsubscribe at googlegroups.com.
>> For more options, visit https://groups.google.com/d/optout.
>>
>>
>> --
>> Employee of Qualcomm Innovation Center, Inc.
>> Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project
>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20180728/70bfdfbd/attachment.html>