similar to: [LLVMdev] Vectorization of pointer PHI nodes

Renato, can you post the c code for the function and the assembly that gcc produces? Your initial example could be well handled by vectorization of strided loops (and the mentioning of VLD3(.8?)/VST3(.8?) lead me to assume that this is what happened). But the LLVM-IR you sent has a store of 0 in there ;) and strides by 4. Thanks, Arnold Vectorization of strided loops: I am using float as the

On 14 October 2013 19:31, Arnold Schwaighofer <aschwaighofer at apple.com>wrote: > Renato, can you post the c code for the function and the assembly that gcc > produces? > Attached. Your initial example could be well handled by vectorization of strided > loops (and the mentioning of VLD3(.8?)/VST3(.8?) lead me to assume that > this is what happened). But the LLVM-IR you

Hi Nadav, Arnold, (now copying LLVM-dev, not commits), I'm working on an example of a code that current GCC trunk can vectorize but LLVM cannot, and after analysing the intermediate IR just before the loop vectorization and by stepping through the process, I can see that the vectorizer only recognizes integer and float reduction variables, not pointers. My code looks like this: for (i: 0

Hi Renato, Thanks for working on this. As you said, we don't support pointer reductions. Handling pointer reductions should be straightforward. You can copy the logic for handling RK_IntegerAdd and create a new enum entry for RK_PointerAdd. You will need to detect the relevant patterns (GEP probably) and implement the cost model and vectorization parts. You will need to generate

On 14 October 2013 18:15, Nadav Rotem <nrotem at apple.com> wrote: > 1. We have 4 stores to consecutive locations, but the last element is the > constant zero, and not an additional SUB. At the moment we don’t have > support for idempotence operations, but this is something that we should > add. > The fourth write is not necessary for GCC to vectorize it (nor was in the

Hi, I am behind a firewall which does not permit connections to port 22, so I run my ssh server on port 23. :-) Unfortunately, the stupid firewall prints a few lines of junk when you make a connection to port 23 before actually starting the connection. This confuses ssh. Attached is an (ugly) patch against openssh-1.2pre15 which makes it ignore a configurable number of lines while looking for

Hi all, Just a quick question about the idempotence of an intrinsic function. Is there a way to specify that an intrinsic function is idempotent? I am trying to give as much information about the intrinsic function I added to LLVM so that LLVM can do optimizations otherwise disabled. Thanks a lot in advance. Bin

On 4/9/2011 6:09 AM, Duncan Sands wrote: > Hi Jack, thanks for the numbers. Any chance of analysing why gcc does better on > those where it does much better than dragonegg? > > Ciao, Duncan. Also, does -fplugin-arg-dragonegg-enable-gcc-optzns get Dragonegg to match GCC performance where GCC was faster? Marcus

On Sat, Apr 09, 2011 at 08:56:49AM -0600, Marcus G. Daniels wrote: > On 4/9/2011 6:09 AM, Duncan Sands wrote: > > Hi Jack, thanks for the numbers. Any chance of analysing why gcc does better on > > those where it does much better than dragonegg? > > > > Ciao, Duncan. > Also, does -fplugin-arg-dragonegg-enable-gcc-optzns get Dragonegg to > match GCC performance

On 12/18/2014 11:56 AM, dag at cray.com wrote: > "Demikhovsky, Elena" <elena.demikhovsky at intel.com> writes: > >> Semantics: >> For i=0,1,…,N-1: if (Mask[i]) {*(BaseAddr + VectorOfIndices[i]*Scale) >> = VectorValue[i];} >> VectorValue: any float or integer vector type. >> BaseAddr: a pointer; may be zero if full address is placed in the

Viswanath Puttagunta wrote: > I responded to your feedback before I started on RFCv3.. and took your > silence as approval :).. I guess that email got lost in your inbox sea > some where.. so re-posting the responses. Sorry, I did see it but I guess I read it rather more quickly than I thought. Apologies for that. > guidance. I wouldn't know where else to put this. Without

Trying to build today's svn on fc5, gcc-4.1.0,amd64: gcc -DHAVE_CONFIG_H -I. -I. -I.. -I../include -I../include -I.. -I/usr/include -O2 -fPIC -funswitch-loops -ftree-loop-linear -march=k8 -ftree-vectorize -pipe -mfpmath=sse -frename-registers -O3 -msse -MT nb_celp.lo -MD -MP -MF .deps/nb_celp.Tpo -c nb_celp.c -fPIC -DPIC -o .libs/nb_celp.o nb_celp.c: In function 'nb_encode':

Hi, I am trying to turn on the new GCC auto-vectorization feature within llvmgcc4. Below is the command I used, but nothing was vectorized. Does it mean that llvmgcc4 has disabled this optimization and all I can do is to embed SSE intrinsics in the source code by hand? Thanks! ./llvm-gcc4-x86/bin/llvm-gcc -c -O2 -ftree-vectorize -msse -ftree-vectorizer-verbose=5 -emit-llvm vec.c -o vec.bc

trying to install this new release and got this message. I tried to locate the dev. pkgs but no luck. yum install did not bring back anything. also tried to search on Fedora to loacate them to install but no luck. any help would be appreciated. Larry checking for X... no configure: error: X development files not found. Wine will be built without X support, which probably isn't what you want.

Does llvmgcc4 convert the high-level AST to LLVM (like llvmgcc3x) or does it go from GIMPL to LLVM? If the latter, would it be possible to allow some TreeSSA optimizations before emitting LLVM? --Vikram http://www.cs.uiuc.edu/~vadve http://llvm.cs.uiuc.edu/ On Jul 31, 2006, at 1:10 PM, Devang Patel wrote: > llvmgcc4 emits LLVM byte code before executing GCC optimizations, > so one

Hello Guys, I guess that I found a bug in Dovecot 2.2.18 and 2.2.25 versions. The problem it's when I try to connect in a Dovecot used a proxy to another e-mail server (in our case it's a Smartermail Server) the DoveCot send a lot of IDLE commands to the destination server. With that, the LOG files grow and grow and grow :( I make a test with 1 connection only and if you see

The flags -fprofile-generate and -fprofile-use are currently ignored for GCC compatibility. I would like to enable them and give them similar semantics to GCC. These flags are baked pretty deeply into our build environment, so supporting them at the driver level will make our lives a lot simpler. >From https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html:

llvmgcc4 emits LLVM byte code before executing GCC optimizations, so one can say that llvmgcc4 disables all GCC optimizations. On Jul 31, 2006, at 11:01 AM, Zhiru Zhang wrote: > Hi, > I am trying to turn on the new GCC auto-vectorization feature > within llvmgcc4. Below is the command I used, but nothing was > vectorized. Does it mean that llvmgcc4 has disabled this >

Not sure if it is just my configuration but building the RPM on Centos x86_64 fails. Also not sure if this is to be fixed in the Makefile or in the configure. The rpm compile proceeds apace until the build reaches the %files section. Here it uses the _libdir directive to look for the libraries that have just been compiled. However in an x86_64 environment the _libdir directive points to lib64

Hello, Just a quick reminder that the November 29th (10p.m. PST) is the end of Phase 1 testing and Release Candidate 2 (RC2) deadline. After RC2 deadline, LLVM-Clang 3.2 release will be considered feature complete and no new functionality can be added. With 2 days left please use following guidelines when initiating request for patches before RC2 deadline. I will be happy to merge *approved*