similar to: [LLVMdev] [PATCH] Start of SIMD Reorg

Hi David, On Fri, Jul 9, 2010 at 3:25 PM, David Greene <dag at cray.com> wrote: > Now that Bruno is putting in some AVX stuff, it's a good motivator to > move my x86 SIMD reorg work into trunk (and got management to agree to > prioritize it - Thanks Bruno! :) ). > > Attached is the first patch of many to accomplish this.  The overall > goal is to have all x86 SIMD

Bruno Cardoso Lopes <bruno.cardoso at gmail.com> writes: >> This patch merely moves some common pattern fragments (memop, >> alignedload, etc.) to a file separate from X86InstrSSE.td so that all >> current x86 SIMD implementations can still use the classes while the >> transition happens. >> >> Ok to commit? > > I'm Ok with this patch. So

Bruno Cardoso Lopes <bruno.cardoso at gmail.com> writes: >> Ok to commit? > > I'm Ok with this patch. > > Despite that, I think we should discuss the ones to come, If you really go > "tablegen auto generates everything" as I've noticed in some tablegen patches > you commited, there's a great chance the sse/avx code would become unreadable, >

I'd like to start moving some of our AVX work into trunk. We've got quite a bit of it implemented already. I wanted to make sure we got something that would work and remain relatively stable. Here's how I'd like to do this. First, I have some more TableGen fixes and enhancements that are prereqs for AVX templates. I'd like to get those in first. Then there are a number of

I'm having a problem with the code generated for the popcnt intrinsic on MacOSX. The `llc` program will generate the assembly just fine, but the assembler fails with the error: suffix or operands invalid for `popcnt' The problem is that the mac assembler does not support length suffixes on the popcnt instruction (e.g. {w,l,q} suffixes). GCC handles this by not adding the suffixes to

On Jul 12, 2010, at 11:45 AM, David A. Greene wrote: > > I don't see how this patch could cause any failures. > > Is somethinmg tricky going on with the Frontend* tests at the moment? I just updated and ran everything and it's working fine for me. (Note that I haven't tested with your patch.) -eric

This is a medium-ish article I wrote up about the current state of the x86 SSE .td files (sans Bruno's ongoing work on AVX). While some of the code snippets are a little bit out-of-date (owing to said work by Bruno and others), the basic concepts still apply. Essentially, the article outlines several places in the current .td files that have redundancy and how that redundancy has led to some

Hi, On Sat, Oct 22, 2011 at 12:03 PM, David Peixotto <dmp at rice.edu> wrote: > I'm having a problem with the code generated for the popcnt intrinsic on MacOSX. The `llc` program will generate the assembly just fine, but the assembler fails with the error: > >   suffix or operands invalid for `popcnt' > > The problem is that the mac assembler does not support length

Hi Bruno, > Some comments: > > + // Try to synthesize horizontal adds from adds of shuffles. > + if (((Subtarget->hasSSE3()&& (VT == MVT::v4f32 || VT == MVT::v2f64)) || > + (Subtarget->hasAVX()&& (VT == MVT::v8f32 || VT == MVT::v4f64)))&& > + isHorizontalBinOp(LHS, RHS, true)) > > 1) You probably want to do something like: >

Hi all, When using "make check" with the DejaGNU test collection, I encounter two unexpected failures (they seem to be closely related). My question: are they well known, and if so what's the problem and how can I fix it? This is the error text I get: FAIL: /var/data/common/trunk/llvm/test/FrontendC/2008-05-19-AlwaysInline.c Failed with exit(1) at line 1 while running:

This is the first in a series of patches to move around some X86 .td file contents in preparation for starting to add AVX patterns. This is stuff that will be shared by SSE, MMX and AVX patterns. Eventually, they will all converge under one framework but in the meantime we need to do some code sharing so I want to move the common stuff into a single file. Assuming this patch looks ok, I'll

> -----Original Message----- > From: llvmdev-bounces at cs.uiuc.edu [mailto:llvmdev-bounces at cs.uiuc.edu] > On Behalf Of Tom Stellard > Sent: 19 September 2014 01:36 > To: Sanjay Patel > Cc: llvmdev at cs.uiuc.edu > Subject: Re: [LLVMdev] predicates vs. requirements [TableGen, > X86InstrInfo.td] > > On Thu, Sep 18, 2014 at 03:25:07PM -0600, Sanjay Patel wrote: >

I've moved our source repository into the top-level svn.xiph.org tree. After using the new set up for a bit, I think having everything (but icecast) in one tree makes more sense. If you have a check out from the old location you can migrate your working copy: cd <theora-working-directory> svn switch http://svn.xiph.org/trunk/theora or svn switch

I am new to the LLVM backends, I am wondering how instruction selection is done in LLVM backends, I looked at the .td files in Target/X86, they all seem to be small and do not deal with common X86 instructions, i.e. mov, push, pop, etc. Thanks -------------- next part -------------- An HTML attachment was scrubbed... URL:

I have a system with 4 disk drives, two 512 Gb and two 1 Tb. It look like this: CentOS release 5.9 (Final) Disk /dev/sda: 500.1 GB, 500107862016 bytes Disk /dev/sdb: 1000.2 GB, 1000204886016 bytes Disk /dev/sdc: 500.1 GB, 500107862016 bytes Disk /dev/sdd: 1000.2 GB, 1000204886016 bytes ================================================================= Disk /dev/sda: 500.1 GB, 500107862016 bytes

On 14/07/2009, at 12.35, Harel Cain wrote: > When using "make check" with the DejaGNU test collection, I encounter > two unexpected failures (they seem to be closely related). > My question: are they well known, and if so what's the problem and how > can I fix it? > FAIL: /var/data/common/trunk/llvm/test/FrontendC/2008-05-19- > AlwaysInline.c > FAIL:

Building r80796 of the "release_26" branch on Ubuntu 9.04, I'm getting an XPASS on: ssen at ssen:~/llvm/build$ make TESTONE=FrontendC/2009-08-11- AsmBlocksComplexJumpTarget.c check-one make[1]: Entering directory `/home/ssen/llvm/build/test' Making a new site.exp file... XPASS: /home/ssen/llvm/test/FrontendC/2009-08-11- AsmBlocksComplexJumpTarget.c make[1]: Leaving directory

I successfully built LLVM (r102824) with ./configure --enable-optimized --enable-targets=host --with-built-clang on Fedora 12 on an Athlon64 processor. (The clang is the 2.7 pre-built version.) However, running `make check' produced 6 unexpected failures (see below). If there's something you'd like me to do, just holler. --- Vladimir FAIL:

The output of the avx-hadd program is 3 11 7 15 Preston -----Original Message----- From: llvmdev-bounces at cs.uiuc.edu [mailto:llvmdev-bounces at cs.uiuc.edu] On Behalf Of Duncan Sands Sent: Thursday, September 22, 2011 3:14 PM To: Bruno Cardoso Lopes Cc: LLVMdev Subject: Re: [LLVMdev] Patch to synthesize x86 hadd instructions; need help with the tablegen bits Hi Bruno, > Some comments:

I'm getting the following when building llvm-gcc with an optimized set of LLVM libraries: /ptmp/dag/build.llvm-gcc-4.2.trunk.official.opt/x86_64-unknown-linux-gnu/./gcc/xgcc -B/ptmp/dag/build.llvm-gcc-4.2.trunk.official.opt/x86_64-unknown-linux-gnu/./gcc/ -B/cray/iss/compiler/cost/tools/llvm-tools/llvm/install.trunk.official.opt/x86_64-unknown-linux-gnu/x86_64-unknown-linux-gnu/bin/