search for: adds

The loop vectorizer is doing an amazing job so far. Most of the time. I just came across one function which led to unexpected behavior: On this function the loop vectorizer finds a 256 bit vector as the wides vector type for the x86-64 architecture. (!) This is strange, as it was always finding the correct size of 128 bit as the widest type. I isolated the IR of the function to check if this is

I looked more into this. For the previously sent IR the vector width of 256 bit is found mistakenly (and reproducibly) on this hardware: model name : Intel(R) Xeon(R) CPU E5-2650 0 @ 2.00GHz For the same IR the loop vectorizer finds the correct vector width (128 bit) on: model name : Intel(R) Xeon(R) CPU E5630 @ 2.53GHz model name : Intel(R) Core(TM) i7 CPU M 640 @

Hi Frank, I'm not an Intel expert, but it seems that your Xeon E5 supports AVX, which does have 256-bit vectors. The other two only supports SSE instructions, which are only 128-bit long. cheers, --renato On 10 November 2013 06:05, Frank Winter <fwinter at jlab.org> wrote: > I looked more into this. For the previously sent IR the vector width of > 256 bit is found mistakenly

If someone has some free time, can you go over my ipfw config. See if I have any problems, or things i should add. Im not an ipfw expert or anything. Here is the config. add 100 allow all from any to any via lo0 add 110 deny log all from any to 127.0.0.0/8 add 120 deny log ip from 127.0.0.0/8 to any add 00200 check-state add 00250 deny all from any to any frag in via bge0 add 00260 deny

Hi Renato, you are right! There is 'avx' support: fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 x2apic popcnt aes xsave

Hi, I´m shaping traffic using htb on both interfaces, I noticed that shaping download traffic is workinggreat but shaping upload traffic is not working at all (no sent packets, no dropped, no overlimits)I have eth0 facing the backbone and eth1 facing the LAN. Thanks for your help.These are the commands I run:tc qdisc del dev eth0 root tc qdisc add dev eth0 root handle 1 htb default 10 r2q 5 tc

Hi ! First of all, I am sorry if this is not the list for that, but I've been learning (a little bit...) a way to implement a freeBSD firewall. So far I came up with a set of rules I would like to show you for commenting. I am sure there're a lot of errors and/or stupid rules (I am not sure the rules order is good for what I need) and I would be really pleased if one could have a look

The Wine maintenance release 3.0.4 is now available. What's new in this release (see below for details): - Added a lot of icons in Shell32 - Various bug fixes The source is available from the following locations: https://dl.winehq.org/wine/source/3.0/wine-3.0.4.tar.xz http://mirrors.ibiblio.org/wine/source/3.0/wine-3.0.4.tar.xz Binary packages for various distributions will be

Hi, I have a following data set: id event time (in sec) 1 add 1373502892 2 add 1373502972 3 delete 1373502995 4 view 1373503896 5 add 1373503996 ... I'd like to add new column "time on task" which is time elapsed between two events (id2 - id1...). What would be the best approach to do that? Thanks, Srecko [[alternative HTML

This one has me perplexed. OpenSSH6.4p1 on a FreeBSD 7 box (I know it's old; it's being replaced this month). I can't spot anything changed in OpenSSH commit logs or git blame of the current file. I ssh into the box from a system with OpenSSH6.6p1 and three keys loaded, RSA, ECDSA and ED25519. As expected, key_from_blob and key_fingerprint complain about the ED25519 key in the

Hi! The Netfilter project proudly presents: iptables 1.6.1 iptables is the userspace command line program used to configure the Linux 2.4.x and later packet filtering ruleset. It is targeted towards system administrators. This update contains accumulated bugfixes, several new extensions and lots of translations via iptables-translate to ease migration to nftables. See ChangeLog that comes

HI All , I am running a FC6 box with two internet links with load balance . Every thing is working fine expect the MSN connection that failed and reconnect every time and SSL connections . I would link to know if with the nona howto I could fix that . I have been tried with no success to redirect that connection only to one link but its look like do not work . Here my configuration :

Hi, I am investigating a performance degradation between llvm-3.1 and llvm-3.2 (Note: current top-of-tree shows a similar degradation) One issue I see is the following: - 'loop invariant code motion' seems to be depending on the result of the 'reassociate expression' pass: In the samples below I observer the following behavior: Both start with the same expression: %add = add

The Wine development release 3.15 is now available. What's new in this release (see below for details): - Support for DPI scaling on Android. - HID device support in Raw Input. - Many more new icons in Shell32. - WinHTTP converted to use Windows Sockets. - Syntax fixes in the command line interpreter. - Various bug fixes. The source is available from the following locations:

Hi all. I have a bridge running Linux 2.4.24 that I use as a bandwidth manager on a broadband wireless network. I''m using HTB and SFQ to prioritize that share bandwidth on a per-cell basis. My IP tables rules divide the traffic based on IPand traffic type (using layer-7 filter and ipp2p). My goal is to make sure that p2p traffic on the network doesn''t sink all of the

Hello! I have an internet connection of 64kbps garanteed in a channel of 256kbps. On this connection the metropolitan speed is 10Mbps and in the provider''s network the speed is 100Mbps. I have a few clients behind my linux box and i want to set up some limitations because some of them are using it irrational. I am marking the packets with 0 for internet; 1 for metropolitan 2 for

Hi All, I have installed llvm-gcc4 patch to enable various llvm optimizations at -O1/-O2/-O3. This means instead of $ llvm-gcc4 --emit-llvm foo.c -o foo.bc $ opt foo.bc -o foo_optimized.bc $ llc foo_optimized.bc -o foo.o One can directly use $ llvm-gcc4 -O2 foo.c -o foo.o to get optimized foo.o - Devang + + if (optimize > 0) { + + +

As far as I can understand of the code, the Reassociate tries to achieve this result by its "ranking" mechanism. If it dose not, it is not hard to achieve this result, just restructure the expression in a way such that the earlier definition of the sub-expression is permute earlier in the resulting expr. e.g. outer-loop1 x= outer-loop2 y =

Hi! The Netfilter project proudly presents: libnftnl 1.0.3 libnftnl is a userspace library providing a low-level netlink programming interface (API) to the in-kernel nf_tables subsystem. The library libnftnl has been previously known as libnftables. This library is currently used by the nft command line tool. This release comes with new features available up to 3.18, see ChangeLog for

It's an interesting problem. The best stuff I've seen published is by Cooper, Eckhart, & Kennedy, in PACT '08. Cooper gives a nice intro in one of his lectures: http://www.cs.rice.edu/~keith/512/2012/Lectures/26ReassocII-1up.pdf I can't tell, quickly, what's going on in Reassociate; as usual, the documentation resolutely avoids giving any credit for the ideas. Why is that?