On 5/10/25 9:46 PM, Vineet Gupta wrote:
Frankly I'm surprised we need FRM adjustments as much as we do, though
presumably there's some builtin or somesuch that we need to twiddle FRM
to implement and as a result if the builtin ever gets used it leads to
FRM games. But it still seems high.
On 5/11/25 19:22, 钟居哲 wrote:
> Hi, vineet.
>
> >> I have a feeling this has to do with following:
> >> https://godbolt.org/z/Px9es7j1r
>
> I saw in there are 2 fsrm instruction inside the main loop in Clang generated
> ASM which I think GCC is better.
>
> Correct me if I am wrong. Thanks.
Yes you
Hi, vineet.
>> I have a feeling this has to do with following:
>> https://godbolt.org/z/Px9es7j1r
I saw in there are 2 fsrm instruction inside the main loop in Clang generated
ASM which I think GCC is better.
Correct me if I am wrong. Thanks.
juzhe.zh...@rivai.ai
From: Vineet Gupta
Date: 2
On 5/10/25 06:49, Jeff Law wrote:
> On 5/9/25 2:27 PM, Vineet Gupta wrote:
>> Hi,
>>
>> This came out of Rivos perf team reporting (shoutout to Siavash) that
>> some of the SPEC2017 workloads had unnecessary FRM wiggles, when
>> none were needed. The writes in particular could be expensive.
>>
>> I
On 5/9/25 2:27 PM, Vineet Gupta wrote:
Hi,
This came out of Rivos perf team reporting (shoutout to Siavash) that
some of the SPEC2017 workloads had unnecessary FRM wiggles, when
none were needed. The writes in particular could be expensive.
I started with reduced test for PR/119164 from blen
