topic Re: MKL_DIRECT_CALL and ICX in Intel® oneAPI Math Kernel Library

MKL_DIRECT_CALL and ICX

AndrewC — Tue, 19 Jul 2022 15:36:26 GMT

Are there any limitations/caveats when using ICX ( Intel C++ Compiler 2022.2) and MKL_DIRECT_CALL. I am looking through some of the headers and notice some __INTEL_COMPILER blocks ( which is ICL specfic). It seems to be that ICX disables MKL_DIRECT_CALL. The snippet below is from the mkl_direct.h in MKL 2022.1.0. When MKL_DC_USE_C is 0, many of the direct calls are skipped. I am not sure why this is restricted to __INTEL_COMPILER. Simply forcing MKL_DC_USE_C to 1 for ICX seems to work just fine. I suppose it's not clear to me if MKL_DIRECT_CALL is abandonware now?

#ifdef __INTEL_COMPILER #define MKL_DC_USE_C 1 #if (__INTEL_COMPILER <= 1500) #define MKL_DC_POTRF_DISABLE 1 #else #define MKL_DC_POTRF_DISABLE 0 #endif #elif defined(__GNUC__) #if defined(__STRICT_ANSI__) && !defined(__STDC_VERSION__) #define MKL_DC_USE_C 0 #else #define MKL_DC_USE_C 1 #endif #define MKL_DC_POTRF_DISABLE 1 #else #define MKL_DC_USE_C 0 #endif

Re:MKL_DIRECT_CALL and ICX

Gennady_F_Intel — Fri, 22 Jul 2022 10:13:26 GMT

Andrew,

MKL_DIRECT_CALL is not abandonware. We need to check this version.

Checking the small gemm calls with/without direct call, I see the following perf results ( MKL v 2022.1.0 ) :

icx --version

Intel(R) oneAPI DPC++/C++ Compiler 2022.1.0 (2022.1.0.20220316)

[2 x 2], SGEMM Execution Time == 6.798655e-08 sec

[2 x 2], JIT_SGEMM Execution Time == 4.284084e-08 sec

....

[8 x 8], SGEMM Execution Time == 7.217750e-08 sec

[8 x 8], JIT_SGEMM Execution Time == 4.936010e-08 sec

that's mean direct call mode works with jit version of gemm as well.

-Gennady

Re: Re:MKL_DIRECT_CALL and ICX

AndrewC — Fri, 22 Jul 2022 18:00:00 GMT

Code compiled using ICX with MKL_DIRECT_CALL defined seems to skip the calls to the direct version (because __INTEL_COMPILER is NOT defined)

As I mentioned in my original post, the "variable" MKL_DC_USE_C is defined "0" unless __INTEL_COMPILER is defined

#define MKL_DC_GEMM3M_CHECKSIZE(m,n,k) (((*(m) <= 4 && *(n) <= 4 && *(k) <= 4)) && MKL_DC_USE_C)

Always evaluates to FALSE, so the direct call is never made - example below.

#define zgemm(transa,transb,m,n,k,alpha,a,lda,b,ldb,beta,c,ldc) MKL_DC_ZGEMM_CONVERT(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc) #define zgemm_(transa,transb,m,n,k,alpha,a,lda,b,ldb,beta,c,ldc) MKL_DC_ZGEMM_CONVERT(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc) #define ZGEMM(transa,transb,m,n,k,alpha,a,lda,b,ldb,beta,c,ldc) MKL_DC_ZGEMM_CONVERT(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc) /* ZGEMM3M */ #define MKL_DC_ZGEMM3M_CONVERT(transa, transb, m, n, k, alpha, a, lda, b, ldb, beta, c, ldc) do { \ if (MKL_DC_GEMM3M_CHECKSIZE(m,n,k)) { \ mkl_dc_zgemm((transa), (transb), (m), (n), (k), (alpha), (a), (lda), (b), (ldb), (beta), (c), (ldc));\ } else { \ MKL_DIRECT_CALL_INIT_FLAG; \ zgemm3m_direct((transa), (transb), (m), (n), (k), (alpha), (a), (lda), (b), (ldb), (beta), (c), (ldc), &mkl_direct_call_flag); \ }\ } while (0)

Am I missing something here?

Re:MKL_DIRECT_CALL and ICX

Gennady_F_Intel — Wed, 21 Dec 2022 12:36:20 GMT

Andrew,

Please check the latest version of MKL 2023 and let us know if the problem is still there.

Thanks,

Gennady

Re: MKL_DIRECT_CALL and ICX

AndrewC — Wed, 21 Dec 2022 23:06:45 GMT

Will do! Thanks for following up.

Re: MKL_DIRECT_CALL and ICX

AndrewC — Thu, 29 Dec 2022 17:33:25 GMT

Hi Gennady,

Just checked 2023.0 and its clear that has been taken care of.

Thanks

Andrew