[GPU][MTL] Resolve long token performance regression in MTL 125H plat…

[riverlijunjie]

Details:

• PR27831 enable MLP fusion in cldnn, it can improve performance, but it is not enabled in MTL 125H due to EU number is 112. So there should be no performance improvement, but PR26940, which integrate dynamic quantization, causes MTL 125H first token performance drop about 8% for 6K input token size. If we enable MLP fusion in MTL 125H, the performance regression will disappear.

• test result:

Test cases	First token latency	Commit id
PR27900, before MLP fusion	22297.2 ms	536bd69
PR27831, MLP fusion PR but MLP fusion is disabled by EU < 128	22783.2 ms	bf62609
PR26940 [GPU] Integrate dynamic quantization for onednn	24395.8 ms	b840082
PR26940 + patch to enable MLP on MTL 125H (112 EUs)	22875.3 ms	b840082

Tickets:

• CVS-159322

[yeonbok]

Hi @riverlijunjie according to @isanghao , PR26940 should not affect MTL because the PR was for onednn case. Could you clarify how PR26940 affected perf?

(And apart from the question, I think we can apply this change though)

[riverlijunjie]

Hi @riverlijunjie according to @isanghao , PR26940 should not affect MTL because the PR was for onednn case. Could you clarify how PR26940 affected perf?

(And apart from the question, I think we can apply this change though)

PR26940 updates dynamic_quantize for cldnn, it should take effect on MTL, am i right?