similar to: Loop distribute / versioning to remove control flow

Displaying 20 results from an estimated 10000 matches similar to: "Loop distribute / versioning to remove control flow"

2020 Mar 23
2
questionabout loop rotation
Hi, Aditya, I took a look but I was hoping for a simpler example. And something that is more "usual". As Florian mentioned, these branches are on undefs. But thank you. Best, Stefanos Στις Δευ, 23 Μαρ 2020 στις 1:16 μ.μ., ο/η Florian Hahn < florian_hahn at apple.com> έγραψε: > > > > On Mar 21, 2020, at 23:13, Aditya K via llvm-dev < > llvm-dev at
2018 Apr 09
3
InductiveRangeCheckElimination and BranchProbabilityInfo
Hi, extractRangeChecksFromBranch uses BranchProbabilityInfo to decide whether its worth trying the InductiveRangeCheckElimination transformation. For the following example: void split() { for (int i = 0; i < 100; ++i) { if (i < 99) do_something() else do_something_else() } } But the reported BPI is reported as 50/50 to whether do_something will be called, but we
2018 Feb 22
3
Loop splitting as a special case of unswitch
For the example code below, int L = M + 10; for (k = 1 ; k <=L; k++) { dummy(); if (k < M) dummy2(); } , we can split the loop into two parts like : for (k = 1 ; k != M; k++) { dummy(); dummy2(); } for (; k <=L; k++) { dummy(); } By splitting the loop, we can remove the conditional block in the loop and indirectly increase vectorization
2018 Apr 10
0
InductiveRangeCheckElimination and BranchProbabilityInfo
Adding Maxim On Apr 9, 2018, at 10:06 AM, Sam Parker via llvm-dev <llvm-dev at lists.llvm.org<mailto:llvm-dev at lists.llvm.org>> wrote: Hi, extractRangeChecksFromBranch uses BranchProbabilityInfo to decide whether its worth trying the InductiveRangeCheckElimination transformation. For the following example: void split() { for (int i = 0; i < 100; ++i) { if (i < 99)
2020 Mar 21
4
questionabout loop rotation
Hi Stefanos, Thanks for your comments. I added both as reviewer. > One question though. Are you sure that this: > This helps with LICM when instructions inside a conditional is loop invariant  > is not achieved with the current LoopRotate pass? Because AFAIK, it does. Basically it inserts > a guard (that branches to the preheader) and then passes like LICM hoist invariant
2008 Dec 13
2
Bitrate peeling
Hi all, I recently started to study the Ogg Vorbis codec and found an interesting feature called bitrate peeling [1]. Do you know where I can find more information on this topic? E.g., how is the actual peeling being implemented, what are the performance results in terms of resulting quality, what are the requirements for bitrate peeling (can it be applied to any ogg vorbis stream), ...? Also,
2000 Oct 29
2
Question Re: Bitrate Peeling
Monty, You helped me out quite a bit the other day, but I just wanted to make sure I understand something. The "ideal" way to do bit rate peeling is to have the encoder set the file up to be conducive to the peeling process, and the streamer would be the device that actually does the peeling. Am I correct in assuming, then, that the decoder would think that the file it is
2002 Jun 23
1
peeling as I understand it (was Re: When will quality increase be unnoticable?)
>> Is bit-peeling going to be real (or just a rumor forever)? > Apparently the RC3 streams are capable of being bit peeled, however the > tool to do so was looking likely to be quite complex. I believe the plan > was to have RC4 produce streams that left better hints for the peeling > tool, so as to make the tool simpler and faster, but I doubt we'll see it > until
2002 Nov 15
1
Peeling Specification
After reading the recent thread [http://www.xiph.org/archives/vorbis/200211/0057.html] on the vorbis list about bitrate peeling, I was wondering if it would be possible for xiph.org to post a specification, outline, flowchart, or a drawing on a napkin of what the basic operations of bit peeling would entail. If there was some sort of starting point, then it may be a little more inviting for
2005 Oct 21
2
Ogg Vorbis bitrate peeling bounty on Launchpad
Hello all, Just a quick note to let you all know that I have placed a bounty on Lauchpad to get bitrate peeling added to Vorbis. It is a feature that I think we would all like to have, and would probably pay something to get, but it hasn't been done. My request to you is to add to the bounty. I have seeded it with US$20, which is not enough to motivate a developer to get it done, but I am a
2002 Dec 21
4
had a thought on peeling last night
I was up late last night, and i had a thought on peeling that would probably provide 100% accurate peeling data to a decoder, but take a maximum of 1101 times normal time to encode (taking into account the range from q-1 to q10 ). ay you want to encode a track at q10, but you want it to be peelable. the 1101 encoder would encode from the source at every quantifiable level (since there are 2
2018 Feb 22
1
Loop splitting as a special case of unswitch
On 2018-02-22 16:21, Roman Lebedev wrote: > On Fri, Feb 23, 2018 at 12:15 AM, Jun Lim via llvm-dev > <llvm-dev at lists.llvm.org> wrote: >> For the example code below, >> int L = M + 10; >> for (k = 1 ; k <=L; k++) { >> dummy(); >> if (k < M) >> dummy2(); >> } >> , we can split the loop into two parts like :
2001 Mar 21
3
bitrtate peeling and lossless compression
I just read some of the discussion on the list about 'bitrate peeling' and remembered an interview of Monty that I have read recently. In it he says that Vorbis uses MCDTs <sp> and that these are theoretically reversable. And now, I learn that theoretically we can use bitrate peeling to make smaller files from larger ones, and that leads to my question. Could I theoretically
2003 Jun 22
2
Bit Rate Peeling Quality
Hi All, Let me ask this question of the group: When bit rate peeling becomes available, how will the quality of the peeled Vorbis file compare to a file encoded at the target quality directly from the original? So, for: a.wav --> b.ogg (at q6) --> c.ogg (at q2) a.wav --------------------> d.ogg (at q2) how are c.ogg and d.ogg likely to compare in terms of audio
2002 Jul 11
1
RC4/1.0 and peeling
first, congrats to monty and the whole crew for getting this close to 1.0. it's a monumental achievement reflecting a huge amount of hard work -- kudos! econd, i know the bitrate peeling feature has been pushed back until after 1.0 is out. but i'm wondering -- will oggs created with a 1.0 encoder be peelable with an as-yet-unreleased utility, or do "peelable oggs" have to be
2004 Aug 06
2
Howto stream using icecast/ices bit rate peeled ogg files
Icecast / Vorbis community, I have a icecast/ices audio streaming server from which I stream ogg audio files. I know that I can encode different streams for low, medium and /or high quality broadcasts (for example). However, I would like to have one stream that uses bit rate peeling to send the user the highest quality stream that their bandwidth will allow. Has any one done this? Does any
2002 Jun 30
4
bitrate peeling
Hi I read in http://grahammitchell.net/writings/vorbis_intro.html > Ogg Vorbis files support "bitrate peeling", which means you can produce > a lower bitrate file from a higher bitrate file without re-encoding and > at the same quality as if you'd encoded the file directly into the lower > bitrate from the original file. No other lossy audio codec currently > supports
2008 Feb 27
1
Scalable Extension
With the newly released SVC (Scalable Video Coding) of H264 I was wondering if Ogg/Theora has any plans of following suit or are there plans to implement a better solution? the closest to SVC I have seen at Xiph is bitrate peeling but that never happened and to date does not seem to be in any TODO list. thanks, -------------- next part -------------- An HTML attachment was scrubbed... URL:
2004 Jan 01
1
Proposal for Bitrate peeling.
Hi all, First up, this is not a proposal on how to do it, but rather on how to get it done. In the latest thread it was mentioned that it was most likely that either Monty or Segher would be the most likely people to implement this code. It was also stated that this is not their priority at the moment. I can only see two solutions to this problem: 1. Find someone else with the knowledge and
2011 Feb 08
1
[LLVMdev] A question about LICM (Loop Invariant Code Motion)
On Tue, Feb 8, 2011 at 4:55 AM, Duncan Sands <baldrick at free.fr> wrote: > Hi Yuelu, > >> After tracking the LICM pass, I find that both loads are loop >> invariant, and canSinkOrHoist() also returns true; however the >> difference is at Instruction::isSafeToSpeculativelyExecute(), >> for load from function parameter pointer, it return false; with load >>