similar to: [LLVMdev] Parallelization

Hi Gokul Ramaswamy, > I am new to LLVM. So please help me out. Here is what I am trying to > achieve: > > If there are 2 statements in a source program - > S1; > S2; > > and I know these is no data and control dependency between them and > both take large amount of time to execute. So I want to execute them > in parallel. >

Hi Duncan Sands, As I have understood, GOMP and OpenMP provides support for parallelizing program at source program level. But I am at the IR level. That is I am trying to parallelize the IR code. This is the case of automatic parallelization. The programmer writing the code does not have any idea of parallelization going behind the hood. So my question is instead of support at the source

On Tue, Mar 22, 2011 at 1:36 PM, Gokul Ramaswamy <gokulhcramaswamy at gmail.com > wrote: > Hi Duncan Sands, > > As I have understood, GOMP and OpenMP provides support for > parallelizing program at source program level. But I am at the IR level. > That is I am trying to parallelize the IR code. This is the case of > automatic parallelization. The programmer writing the

On 03/22/2011 01:56 PM, Reid Kleckner wrote: > On Tue, Mar 22, 2011 at 1:36 PM, Gokul Ramaswamy > <gokulhcramaswamy at gmail.com <mailto:gokulhcramaswamy at gmail.com>> wrote: > > Hi Duncan Sands, > > As I have understood, GOMP and OpenMP provides support for > parallelizing program at source program level. But I am at the IR > level. That

On 5/7/11 2:01 PM, Gokul Ramaswamy wrote: > Hello All, > > I want to change the return type of a function in a Pass(in a > module Pass). I dont want to change any of the arguments of that function. > Assume that, I can handle the returning values properly inside the > function. Please guide me how to do this ? You need to do the following steps: 1) Create a new function

Hello All, I want to change the return type of a function in a Pass(in a module Pass). I dont want to change any of the arguments of that function. Assume that, I can handle the returning values properly inside the function. Please guide me how to do this ? -- Regards, Gokul Ramaswamy, Graduate Student, Department of CSE, IIT Bombay http://www.cse.iitb.ac.in/~ramaswamy --------------

Thanks John for the reply. Ya, I took a similar approach. I cloned the entire function using CloneFunctionInto() in Cloning.h. Now, I am facing a new Problem. I am not able to understand the concept of ValueToValueMap. I am trying to figure it out by testing it. But I am getting errors like "Referring to an argument in another function!". I am not able to get good examples nor good

Hi, I am looking into something similar as well for auto-parallelization i.e. some sort of low level support at the IR level for parallelization. I'd be interested in collaborating with anyone who is working on the same. >From a brief look at the architectural overview of Polly, it seems as if the parallel code generation is being done at the IR level since the input file is an LLVM IR

Hello, Iam getting the following error whem adding new task in redmine -- Internal error An error occurred on the page you were trying to access. If you continue to experience problems please contact your redMine administrator for assistance. Please advise. Thanks in advance. Regards, Gokul -- Posted via http://www.ruby-forum.com/.

Hi Folks , As per https://libvirt.org/formatdomain.html#elementsConsole Regardless of the type, character devices can have an optional log file associated with them. Whether the lgging functionality is same as mapping device to file ? Whether libvirt xml syntax below both 1 and 2 are same ? 1) <serial type='pty'> <log

Hi, I want to execute the iterations of a loop in parallel, by inserting calls either to pthreads or to the gomp library at the LLVM IR level. As a first step, I inserted an omp pragma in a C file and compiled it with llvm-gcc to check the generated LLVM code. If I understand correctly, to parallelize the loop in LLVM IR, I have to separate the loop in a new function, put all required parameters

Hi All, I am newbie in this asterisk and a2billing technology . i had successfully installed asterisk in my server fedora -8 [server behind NAT/STUN] i after installation i can able to create users and tested the call features with X-Lite . the was working fine . after i installed the A2Billing in my same server with follow the steps from a2billing installation guide. but u cant access the

This drop-in patch increases the performance of the get_checksum1() function on x86-64. On the target slow CPU performance of the function increased by nearly 50% in the x86-64 default SSE2 mode, and by nearly 100% if the compiler was told to enable SSSE3 support. The increase was over 200% on the fastest CPU tested in SSSE3 mode. Transfer time improvement with large files existing on both ends

On 02/08/2013 06:35 AM, Nadav Rotem wrote: > Hi Tobi, > > Thanks for reviewing the proposal. I imagine that it may also affects your parallelization work in Polly. Sure. I am interested in using it. >> I am not sure if I am able to follow your reasoning. How could the -loop-vectorizer detect parallelism violations? I had the feeling that we introduce the llvm.loop meta-data for

Dear all, I am having trouble creating summary tables using aggregate function. given the following table: Var1 Var2 Var3 dummy S1 T1 I 1 S1 T1 I 1 S1 T1 D 1 S1 T1 D 1 S1 T2 I 1 S1 T2 I 1 S1 T2 D 1 S1 T2 D 1 S2

Hi, I'm trying to get maximum likelihood estimates of \alpha, \beta_0 and \beta_1, this can be achieved by solving the following three equations: n / \alpha + \sum\limits_{i=1}^{n} ln(\psihat(i)) - \sum\limits_{i=1}^{n} ( ln(x_i + \psihat(i)) ) = 0 \alpha \sum\limits_{i=1}^{n} 1/(psihat(i)) - (\alpha+1) \sum\limits_{i=1}^{n} ( 1 / (x_i + \psihat(i)) ) = 0 \alpha \sum\limits_{i=1}^{n} (

Hello there, I wish to solve the following nonlinear System of equations: + u1 - Vmax11*S1/(S1 + Km11 *(1 + S2/Km21)) - Vmax12*S1/( S1 + Km12 *(1+S2/Km22)) == 0 + u2 - Vmax22*S2/(S2 + Km22 *(1 + S1/Km12)) - Vmax21*S2/( S2 + Km21 *(1+S1/Km11)) == 0 + Vmax11*S1/(S1 + Km11 *(1 + S2/Km21)) + Vmax12*S1/( S1 + Km12 *(1+S2/Km22)) - d1*P1 == 0 + Vmax22*S2/(S2 + Km22 *(1 + S1/Km12)) + Vmax21*S2/( S2 +

Hi Alexandra, I don't know much, maybe this topic should be bridged with polly-dev (adding it to CC) to bring it more attention. Indeed, polly uses ScopPass, that creates serious limitations in compatibility with other passes. To my understanding, scops are used because ISL loop analysis tool uses scops. In fact, just for handling OpenMP directives scops are not required, unless one need to

Hi Tobi, Thanks for reviewing the proposal. I imagine that it may also affects your parallelization work in Polly. > > I am not sure if I am able to follow your reasoning. How could the -loop-vectorizer detect parallelism violations? I had the feeling that we introduce the llvm.loop meta-data for the case where we want to inform the loop vectorizer that it can assume the absence of

I have three modules: ----------------------------------------------------------------- s1.ll: %0 = type <{ i32, i32 }> define void @s1(%0* byval %myStruct) nounwind { return: ret void } ----------------------------------------------------------------- s2.ll: %0 = type <{ i32, i32 }> define void @s2(%0* byval %myStruct) nounwind { return: ret void }