choose _mm512_permutevar_epi32 or _mm512_shuffle/permute4f128_epi32?
Hi all,It appears that the _mm512_permutevar_epi32 can perform any kinds of data-reordering patterns according to the given index vector. On the case of that, why do we need to use the...
View ArticleWhat does __kmp_wait_yield_4 imply in hot spot analysis of vTune
Hi,I am rewriting part of LibSVM code for vectorization in order to accelerate it on Xeon Phi. Unfortunately, the performance of my rewriting code is the same as, if not slightly worse than, the...
View Articleperformance jpeg on phi
Hello.I am new in Phi world. I tested jpeg encoding performance (tested on image 1680x1050, single thread):14 ms - xeon E5-2620 - libjpeg-turbo with SIMD 39 ms - xeon E5-2620 - libjpeg-turbo without...
View Articlecannot run GDB-MIC
Hello,I am unable to debug Xeon Phi code. I am using Intel Parallel Studio 2015 and its debugger. Specifically I am not able to run gdb-mic.I follow these stepssource compilervars.sh intel64 gdb-micI...
View Articlebootup Phi in Xen/Dom0 failed with kernel crash
Hello.I have unusual (and unsupported) config: - centos 5.10 - kernel 3.10 (patched by citrix - XenServer Creedence Release Candidate) - xen from git - mpss-3.4.2 (some *.rpm without dependencies...
View ArticleUpdated info on virtualized host support?
I'm looking to install a Phi unit in my workstation which is a virtualized machine; it's running Linux / kvm as the hypervisor with multiple Linux and Windows vm's. The host machine is a current E5...
View Articleinternal error: backend signals (when compiling an asynchronous offloading...
Hello, I tried to compile the following program on Intel Xeon Phi with icpc 13.0.1. But I failed to compile it. The error message says "": internal error: backend signals" This message tell me no...
View Articleparallel_studio_xe_2015 NOT openmp 4.0 compliance?
Hi,The following code does not work as expected:------------------------------------------------------------------------MODULE SIM_DATA !$OMP declare target (GX) ! DIR$ ATTRIBUTES...
View ArticleClik here to view.
Intel® Xeon Phi™ Coprocessor
Optimizing Execution Performance for an Isotropic Double Precision 3DE Finite Difference Stencil Algorithm on the Intel® Xeon Phi™ CoprocessorAbstractThis paper discusses applying programming...
View ArticleClik here to view.
LAMMPS* for Intel® Xeon Phi™ Coprocessor
PurposeThis code recipe describes how to get, build, and use the LAMMPS* code for the Intel® Xeon Phi™ coprocessor.IntroductionLarge-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS*) is a...
View ArticleMIC Fortran offload linker issue on windows
HiI am in the process of migrating a Fortran application for Xeon Phi offload and I had it almost working with the v14 compiler. Compiler issues prevented me from completing the implementation,...
View ArticleHow can you know the execution status of an offloaded function on...
HiI am trying to measure power on Xeon Phi by using MicGetPowerUsage, which is one of APIs in MicAccessAPI library. I would like to measure the power only while a offloaded function is running on Xeon...
View ArticleAutomatic offload not working for R
Hello,I'm trying to run the R-benchmark-25.R using automatic offloading to the Xeon Phi but AO is not working.I have compiled my R library as explained here and set the env variables (MIC_ENABLE=1 and...
View Articlewhat is the CPUID test for KNCNI?
I'm using icc (ICC) 15.0.1 20141023 on a Haswell-based system. My software library has CPU-specific code using either SSE2, SSE41, AVX2, or KNCNI intrinsics. icc is successfully compiling the KNC...
View ArticlePhi application 2013 sp1.4.211 redist bug
Hi I am building an application with composer_xe_2013_sp1.4.211 that targets Xeon Phi on Linux I am testing the application with the redistributable libraries from...
View ArticleDifferent power usage on cards
Hi,I have two 31S1P cards. If I run exactly the same code on these cards, then one card uses 155W, the other 175W. This is very consistent and even true when idle (125W vs 104@). Why is there a...
View ArticleHow to dllexport with MIC offload?
I got dllexport not recognized error.I find that certain features are not supported with offload:"When you use code with these features in your application, you must correctly structure the code so...
View ArticleHow to implement Unpacklo, Unpachi with _m512i?
Hi guys,I am porting a source code from SSE intrinsic to KNC Intel Xeon Phi. An issue I have to deal with now is that I can't find the way to implement unpacklo and unpackhi of SSE in KNC.Anyone can...
View ArticleIntrinsic function on MIC (512)
Hey everyone, I'm working on a simple financial application (actually benchmarking CPU vs MIC), the first version of the code is without intrinsics function (the compiler is vectorizing the loops) and...
View ArticleStreaming store for _m512i
Hi guys, I'm looking for an intrinsic for streaming store _m512i in KNC. As far as I know, KNC has on some intrinsic instructions for streaming store float/double data, such as:extern void...
View Article