similar to: accelerating matrix multiply

> Do you have R code (including set.seed(.) if relevant) to show on how to generate > the large square matrices you've mentioned in the beginning? So we get to some > reproducible benchmarks? Hi Martin, Here is the program I used. I only generate 2 random numbers and reuse them to make the benchmark run faster. Let me know if there is something I can do to help--alternate

Hi Tomas, Can you share the full code for your benchmark, compiler options, and performance results so that I can try to reproduce them? There are a lot of variables that can affect the results. Private email is fine if it is too much for the mailing list. I am measuring on Knight's Landing (KNL) that was released in November. KNL is not a co-processor so no offload is necessary. R executes

>>>>> Cohn, Robert S <robert.s.cohn at intel.com> >>>>> on Sat, 7 Jan 2017 16:41:42 +0000 writes: > I am using R to multiply some large (30k x 30k double) > matrices on a 64 core machine (xeon phi). I added some timers > to src/main/array.c to see where the time is going. All of the > time is being spent in the matprod function, most of that

Hi Robert, thanks for the report and your suggestions how to make the NaN checks faster. Based on my experiments it seems that the "break" in the loop actually can have positive impact on performance even in the common case when we don't have NaNs. With gcc on linux (corei7), where isnan is inlined, the "break" version uses a conditional jump while the

Hi, I was wondering if I could use the matprod function from array.c in my own C routine. I tried the following as a test /* my_matprod.c */ # include <Rinternals.h> /* for REAL, SEXP etc */ # include <R_ext/Applic.h> /* array.c says need for dgemm */ /* following copied from array.c */ static void matprod(double *x, int nrx, int ncx, double *y, int nry, int ncy, double *z)

> From: "Cohn, Robert S" <robert.s.cohn at intel.com> > > I am using R to multiply some large (30k x 30k double) matrices on a > 64 core machine (xeon phi). I added some timers to > src/main/array.c to see where the time is going. All of the time is > being spent in the matprod function, most of that time is spent in > dgemm. 15 seconds is in matprod in

Dear R-devel, I've written a numerical solver for SOCPs (second order cone programs) in R, and now I want to move most of the solver code into C for speed. I've written combined R/C packages before, but in this case I need to do matrix operations in my C code. As I have never done that before, I'm trying to write some simple examples to make sure I understand the basics. I am stuck

Full_Name: J . R. M. Hosking Version: 1.8.0 OS: Windows 2000 Submission from: (NULL) (129.34.20.23) On R 1.8.0 (and on R 1.5.1), Windows binary: > NA %*% 0 [,1] [1,] 0 This is surprising. Is it a bug? Note that > 0 %*% NA [,1] [1,] NA > NA %*% 1 [,1] [1,] NA > NA * 0 [1] NA as expected.

Hi Tomas, Thanks for your answer. Indeed, I checked and my R-3.4.1 installed from the ubuntu repository use 'libopenblasp-r0.2.18.so' while my R-3.3.2 that I did compiled on my machine use 'libRblas.so' which explain the difference of behavior. I will use RhpcBLASctl to avoid issue when combining matrix product and other multi-threading package. Maybe this point regarding

I would like to see how the matrix multiplication operator %*% is implemented (because I want to see which external Fortran/C routines are used). How can I do so? Best S??ren

I've looked at the code for matrix multiplies in R, and found that it can speeded up quite a bit, for multiplies that are really vector dot products, and for other multiplies in which the result matrix is small. Here's my test program: u <- seq(0,1,length=1000) v <- seq(0,2,length=1000) A2 <- matrix(2.1,2,1000) A5 <- matrix(2.1,5,1000) B3 <- matrix(3.2,1000,3) A4 <-

Dear all, I need to calculate tr(xyxy) fast for matrices x and y. Inspired by the R-source code, I've created the following functions (I am *new* to writing external C-functions, so feel free to laugh at my code - or, perhaps, suggest changes): #include <Rinternals.h> #include <R_ext/Applic.h> /* for dgemm */ static void matprod(double *x, int nrx, int ncx, double *y, int

Dear R Core Team, I wish to report what can be viewed as a bug or at least a strange behavior in R-3.4.1. I ask my question here (as recommended on https://www.r-project.org/bugs.html) since I am not member of the R's Bugzilla. When running 'R --vanilla' from the command line, the standard matrix product is by default based on BLAS and multi-threaded on all cores available on

Not an expert in programming either, but to me it seems like you've forgotten to initialize the variable "tr". It just picks up garbage from allocated memory previously initialized by other processes. Med venlig hilsen Frede Aakmann T?gersen > -----Oprindelig meddelelse----- > Fra: r-help-bounces at stat.math.ethz.ch > [mailto:r-help-bounces at stat.math.ethz.ch] P?

Hi, I am trying to compile a single module (dgemm.c) using clang and generate dgemm.ll. Command: clang -emit-llvm dgemm.c -S -o dgemm.ll Some of the functions are declared as static and clang ignores these functions: One of the functions is: static void innerloop(double a, const double* b, double* c, double beta) { *b = a*beta; return; } Is there any way to make clang generate llvm code

Hi, I'm just following your messages the overhead that the code for dealing with possible NA/NaN values brings. When I was setting up part of the matrixStats package, I've also though about this. I was thinking of having an additional logical argument 'hasNA'/'has.na' where you as a user can specify whether there is NA/NaN:s or not, allowing the code to avoid it or not.

Hi, I'm trying to follow the R-admin instructions for using MKL10 as the external BLAS compiling R-2.6.2 under Linux on a RH EL head node of a cluster. The configure process seems to have problems when it checks for dgemm in the BLAS. I'm using configure as: ./configure CC=icc F77=ifort --with-lapack="$MKL" --with-blas="$MKL" where $MKL is defined as in R-admin

Hi Arvind, you need to use it effectively : static int add(int a, int b) { return a+b; } int use() { return add(4,5); } ==> ; ModuleID = '<stdin>' target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32" target triple = "i386-pc-linux-gnu" define i32 @use()

Hi, Sorry for not being specific. I just wanted to know if there is any way at all to force clang to generate intermediate code for static functions when they are not being called anywhere inside the current module. Other compilers seem to generate intermediate code (lcc, for instance). Thanks for your reply..Olivier. Sincerely Arvind On Mon, Dec 14, 2009 at 1:10 PM, Olivier Meurant

Ah ok. Sorry. :) I think that argument "-femit-all-decls" will help you. Olivier. On Mon, Dec 14, 2009 at 9:18 PM, Arvind Sudarsanam < arvind.sudarsanam at aggiemail.usu.edu> wrote: > Hi, > > Sorry for not being specific. I just wanted to know if there is any > way at all to force clang to generate intermediate code for static > functions when they are not being