similar to: [LLVMdev] Announcing ispc: a SPMD-on-SIMD compiler built on top of LLVM

An addition for the publications page on llvm.org (and of potential interest to other people using LLVM for high-performance SIMD computation.) The ispc project would never have been possible without LLVM; many thanks to all involved in the LLVM project for building such a great system. Thanks, -matt ispc: A SPMD Compiler for High-Performance CPU Programming Matt Pharr and William R. Mark

Hi Renato, On 07/07/2015 10:57 PM, Renato Golin wrote: > Now, IIRC, OpenCL had a lot of trouble from getting odd-sized vector > types in IR that the middle end would not understand, especially the > vectorizers. The solution, at least as of 2 years ago, was to > serialise everything and let the CL back-end to vectorize it. Perhaps you are referring to the problem of autovectorizing

On 07/07/2015 01:32 PM, Renato Golin wrote: > Wouldn't OpenMP account for some of that? At least on a single > machine, could you have both parallel and simd optimisations done on > the same loop? The point in SPMD program description (e.g. CUDA or OpenCL C) autovectorization is to produce something like OpenMP parallel loops or SIMD pragmas automatically from the single thread/WI

Hi, Are there any plans to integrate an autovectorizer for SPMD programs into LLVM? For example, there were previous discussions about integrating the whole function vectorizer (WFV) from Ralf Karrenberg into LLVM. Thanks, Zack -------------- next part -------------- An HTML attachment was scrubbed... URL:

We are working on OpenMP target offloading for GPUs in Flang, and adopting the same code generation strategy. The proposal is affecting us. It would be nice to know more details about the proposal. So we can prepare ourselves to adapt flang (if everything goes on the way). Have you find and a solution for data sharing? How are you going to manage data sharing for SPMD and non-SPMD? From: cfe-dev

Could you elaborate on what you refer to wrt data sharing. What do we currently do in the clang code generation that we could not effectively implement in the runtime, potentially with support of an llvm pass. Thanks, James Get Outlook for Android<https://aka.ms/ghei36> ________________________________ From: Alexey Bataev <a.bataev at outlook.com> Sent: Tuesday, January 22, 2019

In the course of implementing the instruction scheduler for the Intel Atom in LLVM, I have run across a problem with the critical anti-dependence breaker, whereby CriticalAntiDepBreak.cpp code changes some XMM0 references to be XMM9 references. This would be all well and good, were it not for the fact that the result of the expression needs to be in XMM0 because it is being returned as the

We could still do that in clang, couldn't we? Get Outlook for Android<https://aka.ms/ghei36> ________________________________ From: Alexey Bataev <a.bataev at outlook.com> Sent: Tuesday, January 22, 2019 12:52:42 PM To: Doerfert, Johannes Rudolf; cfe-dev at lists.llvm.org Cc: openmp-dev at lists.llvm.org; LLVM-Dev; Finkel, Hal J.; Alexey Bataev; Arpith Chacko Jacob Subject: Re:

There are tooooooo(!) many changes, I don't who's going to review sooooo big patch. You definitely need to split it into several smaller patches. Also, I don't like the idea adding of one more class for NVPTX codegen. All your changes should be on top of the eixisting solution. ------------- Best regards, Alexey Bataev 13.03.2019 15:08, Doerfert, Johannes пишет: > Please consider

I agree that a single vector index is sufficient for many cases. Matt Pharr (from the ISPC compiler), showed me an interesting case where there is a single pointer into an array. In this case we need to have two indices, where the first index is zero. Once the basic patch is in, we can start looking at adding support for arrays and multiple indices. Nadav -----Original Message----- From: David

On Jul 31, 2011, at 10:49 PM, Matt Pharr wrote: > I'm seeing some undesirable behavior where, when generating debugging information, sometimes the point in the debugger will jump forwards and backwards during single stepping, even though the output from our frontend (this is the ispc compiler), is emitting LLVM instructions with a strictly forward-moving/increasing set of source locations.

------------- Best regards, Alexey Bataev 13.03.2019 15:35, Doerfert, Johannes пишет: > > Hi Alexey, > > > thank you for your quick feedback. > > > > There are tooooooo(!) many changes, I don't who's going to review sooooo big > patch. > > > I can for sure split it in the three components/repositories that are > touched, clang, llvm, and openmp.

Duncan, Thanks for the quick review! Here is a short description (design) of where I am going with this patch: 1. Motivation: Vectors-of-pointers is the first step in supporting scatter/gather instructions (available in AVX2, for example). I believe that this feature was requested on the mailing list before. As mentioned by Hal Finkel earlier today, this feature is desired by autovectorizers as

We would still know that. We can do exactly the same reasoning as we do now. I think the important question is, how different is the code generated for either mode and can we hide (most of) the differences in the runtime. If I understand you correctly, you say the data sharing code looks very different and the differences cannot be hidden, correct? It would be helpful for me to understand your

<font size=2 face="sans-serif">Hi Johannes,</font><br><br><font size=2 face="sans-serif">Thank you for the explanation.</font><br><br><font size=2 face="sans-serif">I think we need to clarify some details about code generation in Clang today:</font><br><br><font size=2

Johannes, did you try it on AMD GPUs? If not, I think it might be early to claim it as a general interface for NVidia/AMD GPUs. I'm ok, if you want tointroduce a basic class for the GPU-specific codegen, but it must be done step-by-step and thoroughly tested and reviewed. Theremightbe some parts, common with NVPTX codegen. You can put the commonfunctions into a base class and remove them from

On 07/07/2015 09:30 PM, C Bergström wrote: > If you're going to "autopar" (turn a loop into a threads which run on > many cores or something) then please don't add a dependency on OMP. I wouldn't, but simply utilize the parallel loop metadata that was originally designed for this purpose. What is done with that MD is up to other passes. -- --Pekka

1. You don't need to implement everything in a single patch. The development process is a step-by-step process, when you commit something in small pieces. The code must nit be fully functional, you may start from some basic features. Currently it is very hard to review. 2. I rather doubt that it can be reused without changes for AMD etc., especially without being fully tested. The only tested

Where we are ------------ Currently, when we generate OpenMP target offloading code for GPUs, we use sufficient syntactic criteria to decide between two execution modes: 1) SPMD -- All target threads (in an OpenMP team) run all the code. 2) "Guarded" -- The master thread (of an OpenMP team) runs the user code. If an OpenMP distribute region is encountered,

Filed as http://llvm.org/bugs/show_bug.cgi?id=12678. On Apr 23, 2012, at 2:03 PM, llvmdev-request at cs.uiuc.edu wrote: > I'm seeing some strange behavior with generating debugging information from a simple program. (LLVM top of tree, minus a couple of days.) > > I suspect that there is a bug in LLVM, but thought I'd check in here to see if perhaps I'm doing something