using syrk for performing special cases of matrix multiplication

[vtavana]

In this PR, the syrk routines from oneMKL is used to perform a rank-k update which is used for a specialized matrix multiplication where the result is a symmetric matrix.

$ sycl-ls
[level_zero:gpu][level_zero:0] Intel(R) oneAPI Unified Runtime over Level-Zero, Intel(R) Data Center GPU Max 1100 12.60.7 [1.6.31294+9]
[opencl:cpu][opencl:0] Intel(R) OpenCL, Intel(R) Xeon(R) Platinum 8480+ OpenCL 3.0 (Build 0) [2025.19.1.0.16_160000]
[opencl:gpu][opencl:1] Intel(R) OpenCL Graphics, Intel(R) Data Center GPU Max 1100 OpenCL 3.0 NEO  [24.39.31294]

size	syrk-GPU	gemm-GPU	syrk-CPU	gemm-CPU
2048	1.37 ms ± 2.81 μs	2.02 ms ± 3.69 μs	17.5 ms ± 1.21 ms	12 ms ± 365 μs
4096	7.94 ms ± 16.6 μs	14.2 ms ± 55.9 μs	73.2 ms ± 4.94 ms	68.2 ms ± 5.93 ms
8192	59 ms ± 144 μs	107 ms ± 126 μs	481 ms ± 37.1 ms	674 ms ± 56.5 ms

Time measurement using:

import dpnp
size = 4096
ia = dpnp.ones((size, 2*size), device="cpu")
%timeit r = dpnp.matmul(ia, ia.mT); r.sycl_queue.wait()

Also see timing measured here.

• Have you provided a meaningful PR description?
• Have you added a test, reproducer or referred to an issue with a reproducer?
• Have you tested your changes locally for CPU and GPU devices?
• Have you made sure that new changes do not introduce compiler warnings?
• Have you checked performance impact of proposed changes?
• Have you added documentation for your changes, if necessary?
• Have you added your changes to the changelog?

[github-actions]

View rendered docs @ https://intelpython.github.io/dpnp/index.html

[github-actions]

Array API standard conformance tests for dpnp=0.19.0dev1=py313h509198e_24 ran successfully.
Passed: 1227
Failed: 0
Skipped: 9

[coveralls]

coverage: 72.044% (-0.08%) from 72.128%
when pulling a45a747 on syrk
into 1a7ce22 on master.

[antonwolfy]

Thank you @vtavana, it looks as a great improvement. No more review comments from me.