similar to: [LLVMdev] SIMD Projects with LLVM

I have a group of students working with me on some LLVM projects related to our Parabix research. One interesting issue that has come up for us is code generation support for the Haswell new instructions pext and pdep. These instructions shuffle bits within a 64-bit word, either gathering all selected bits to the beginning (pext) or scattering some initial bits throughout (pdep). A natural

Dear all I am a PhD student of Computer Scince at Simon Fraser University ( http://www.cs.sfu.ca) interested in applying to GSoC. My PhD is focused on theoretical computer science, but since Sep. 2008 I have started working on Software projects again. Currently I am working in COSTAR lab ( http://costar.sfu.ca/) on a high performance regular expression engine based on Parallel bit streams

Hi everyone! Here, I have a question and am curious about i128. I want to know how the LLVM handle i128, because many compiler backend doesn't support i128 directly. So I am very curious and want to how the llvm handle this situation? Besides i128, such as i256, i512, even i24? Thanks. Best Regards Wu Zhao -------------- next part -------------- An HTML attachment was scrubbed...

Hi Evan Thanks for the email. I had a look at gcc implementation of TBAA and I think three main steps in implementation of TBAA for LLVM will be this: April 20 ~ May 23: I will read gcc implementation in depth and play around with LLVM code. May 23 ~ July 6: Implementation and test of a simple version of TBAA that does not work with all aggregate types. I think part of the coding required for

Hi Ehsan, All of the projects you have listed are quite interesting. If I were to advocate for one, it would be #2. I think the scope of work is perfect for GSoc. I'd encourage send out a more concrete proposal when you're ready. Thanks, Evan On Mar 27, 2009, at 2:35 PM, Ehsan Amiri wrote: > Dear all > > I am a PhD student of Computer Scince at Simon Fraser University

Hi Nick, I tried to rework changes as you requested. One of patches (0004 with extra assertions) has been removed. > + bool isEquivalentType(Type *Ty1, Type *Ty2) const { > + return cmpType(Ty1, Ty2) == 0; > + } > > Why do we still need isEquivalentType? Can we nuke this? Yup. After applying all the patches isEquivalentType will be totally replaced with cmpType. All

Hi, First, sorry in advance for pasting code like this :) I'm doing a simple optimization pass for a cs326 class project. The pass in question is LICM, and I'm getting an assertion when I try to hoist an instruction. My hoist function is below. I dont think I need that copying in there, that was just something people on the newsgroup suggested. I get the same assertion

Hi Tobias, could we use information about memory accesses of a SCoP statement and def-use chains to determine statements, which don’t contain matrix multiplication of the following form? for (int i = 0; i < Upper Bound1; i++) for (int j = 0; j < Upper Bound2; j++) for (int k = 0; k < Upper Bound3; j++) C[i][j] += A[i][k] * B[k][j] We could probably check that memory access

Buenas tardes amigos, De nuevo por aqui con un incoveniente, tengo el siguiente arreglo: > MuestraS [1] 1 0 0 0 1 0 1 1 1 1 1 0 Deseo realizar todas las permutaciones posibles para luego tomar una muestra aleatoria pequeña, esto lo debo hacer varias veces incrementando el largo del arreglo "MuestraS". El inconveniente esta en que al hacer las permutaciones con este arreglo de 12

Hi, Let me try to give a bit more context on why select is so tricky. First thing to consider is which transformations we would like to support: 1) Control-flow -> select (SimplifyCFG) if (c) a = x else a = y => %a = select %c, %x, %y 2) select -> control-flow; reverse of 1) Not sure if this is done at IR level, or only later at SDAG. 3) select ->

Hi gurus, I have a doubt about multiclass classification SVM. The population in my data includes a couple of class labels that have relatively small proportion of the entire population compared to other classes. I would like SVM to pay more attention to these classes. However, the question I am having here is that is there any systematic/theoretic framework to determine the weights for each

Hi Nick, I have committed 0001 as r203788. I'm working on fixes for 0002 - 0014. > After reading through this patch series, I feel like I'm missing > something important. Where's the sort function? It looks like we're > still comparing all functions to all other functions. When you insert functions into std::set or its analogs it does all the job for you. Since

Rob, Ahmed, and Jingu, [I'm sorry if my point of view is too x86 centric.] >>the tricky part about fixing it is the need to settle on a memory layout for these vectors >> (packed vs byte per i1; packed would be compatible with AVX512, I think). I agree with Ahmed here, in principle. It's actually more than that, since vector compare in AVX2 and below produces the same

Hi friends, Please can anyone help me with an easier solution of doing the below mentioned work. Suppose i have a dataset like this:--- i1 i2 i3 i4 i5 1 7 13 1 2 2 8 14 2 2 3 9 15 3 3 4 10 16 4 4 5 11 17 5 5 6 12 18 6 7 *i1,i2,i3,i4,i5 are my items.I am able to find all possible pairs i.e Say this dataframe is "item_pairs" **i1,i2 **i1,i3 **i1,i4 i1,i5 **i2,i1

Hi Everyone, quick question before the end of the year. I have soem indices to select data from a bigger sample. I want to select n days before each index and n days after the index. Any clever way to do it. A for loop would do but I wanted to know if there is a moreR-friendly way to approach this Example # InitialIndices i2 = (90, 190, 290) # Indices I want to end up with i3 = c(85, 86, 87,

On 05/17/2016 01:47 PM, Michael Kruse wrote: > 2016-05-16 19:52 GMT+02:00 Roman Gareev <gareevroman at gmail.com>: >> Hi Tobias, >> >> could we use information about memory accesses of a SCoP statement and >> def-use chains to determine statements, which don’t contain matrix >> multiplication of the following form? > > Assuming s/don't/do you want

On 01/01/2013 02:45 PM, Duncan Sands wrote: > Hi Dmitry, > >> >> In our compiler we use a modified version LLVM Polly, which is very >> sensitive to >> proper code generation. Among the number of limitations, the loop region >> (enclosed by phi node on induction variable and branch) is required to >> be free >> of additional memory-dependent

On 9/25/2017 9:14 AM, Björn Pettersson A wrote: > > (Not sure if this exactly maps to “truncating store”, but I think it > at least touches some of the subjects discussed in this thread) > > Our out-of-tree-target need several patches to get things working > correctly for us. > > We have introduced i24 and i40 types in ValueTypes/MachineValueTypes > (in addition to

hello. i downloaded the latest i2 wiki from the subversion repository. i''m not able to see it working even running under webrick (under windows xp sp2). i created the database (mysql 4.1) via "rake migrate" and instantiated the first web through the console (as suggested by the readme file). when running it what i get in the browser window is a blank page and in the webrick

I'm using functions to return a matrix of all permutations of a specified size from a larger list for predictor selection. For each predictor size I use a seperate function like this: bag2 <- function(n) { rl <- c() for (i1 in seq(n)) { for (i2 in seq(n)) { if (length(unique(c(i1,i2)))==1) {next} rl <- cbind(rl,matrix(c(i1,i2))) } }