I'm trying to setup a new system:
2 Intel Xeon Phis:
Coprocessor Stepping : B1
Board SKU : B1PRQ-31S1P
MPSS 3.5 and Scientific Linux 7.1
Could someone please tell me if this machine is compatible with this model of Xeon Phi?
We bought a workstation based on this list:
Once installed the card does not appear in lspci nor in BIOS.
Thanks in advance!
I try to use MKL to generate lots of random data every time on Xeon phi, but the performance is very bad comparing the performance on Xeon CPU.(E5620) .
The attachment is the original code, and the compile option for Xeon Phi is -O3 -mkl -mmic. and it takes about 115 seconds, however when I run it on Xeon CPU,it only takes 3.5 seconds. I do not know why the difference is so much. Is the way in which I use the Xeon Phi wrong or the real performance on Xeon Phi is bad?
I have isolated a small section of a loop in my code to vectorize and test for other kinds of optimization a well(like alignment etc)
Here is the actual code.
WORK1(:,:,kk) = KAPPA_THIC(:,:,kbt,k,bid) * SLX(:,:,kk,kbt,k,bid) * dz(k)
The optrpt says this
LOOP BEGIN at loop.F90(91,13)
remark #15541: outer loop was not auto-vectorized: consider using SIMD directive
remark #25436: completely unrolled by 8
I'm compiling Supersonic, an opensource database of google on Intel Phi using icc with option -mmic
but I find some lfence in the source code, but it seems that Phi doesn't support lfence instruction, so I want to replace lfence by some other instructions in Phi.
Is it practicable? for example,
I have been testing code using Intel MPI (version 4.1.3 build 20140226) and the Intel compiler (version 15.0.1 build 20141023) with 1024 or more total processes. When we attempt to run on 1024 or more processes we receive the following error:
MPI startup(): ofa fabric is not available and fallback fabric is not enabled
Anything less than 1024 processes does not produce this error, and I also do not receive this error with 1024 processes using OpenMPI and GCC.
I am setting up a cluster with 8 hosts with 2 MIC's each. I have installed the MPSS 3.4.3 software on Centos 6.6. We have also installed Intel TrueScale Infiniband
Al services start fine with no errors.
I see the following kernel modules loaded:
I'm tring to compile supersonic(an opensource in-memory database of google) on Xeon Phi with an Makefile:
CC = icc
CFLAGS= -Wall -O2 -g -DNDEBUG -mmic
but after executing "make", yield the following error: