linaro-toolchain

linaro-toolchain@lists.linaro.org

1 participants
5600 discussions

by Richard Sandiford

== Last week == * Patch review. * Backported second attempt to fix get_arm_condition_code ICE. * Worked on -fsched-pressure. Experimented with various combinations of ideas. This is giving some good results (e.g. a 2x improvement in libav's put_h264_qpel8_hv_lowpass_8) but needs a bit more work to fix some outliers. I'll be away from 18th Oct to 14th Nov. Richard

13 years, 8 months

Native build performance

by Michael Hope

Random data for the day: Dave Pigott has installed some new PandaBoard build machines in the validation lab. They're identical to mine except that root is on USB Flash instead of NFS, and they have a much faster flash drive for the build area. The time taken to bootstrap and test gcc-linaro-2011.09 with C, C++, Fortran, and LTO is: * ursa3, ursa4 (Toshiba USB stick): 301 minutes build / 369 test * ursa2 (no-name USB stick): 324 minutes build / 422 test * tcpanda (fast USB stick): 274 minutes build / 265 test So the new combo gives a 1.38 x faster build. I'm surprised as I though the build was CPU bound. I'd hate to see what building on an SD card is like. Note that /tmp is in RAM, /scratch is ext4, the new boards use noatime, and the kernel doesn't have the new USB performance fix. -- Michael

13 years, 8 months

[ACTIVITY] weekly status

by Revital Eres

Continue working on estimating register pressure with SMS: - Discussed current approach with Richard which gave useful leads. - Started to implement this approach. - Doing experiments on libav microbench.

13 years, 8 months

Re: Use of memcpy() in libpng

by jbowler＠acm.org

The unaligned accesses in libpng are, for the large copies, a bug. Our attempt to align the row buffer to a 16 byte boundary was off-by-one so we end up always mis-aligning it. I've posted a patch on the png-mng-implement list: http://sourceforge.net/mailarchive/message.php?msg_id=28194444 The time spent in memcpy() is probably an illusion. The data out of zlib gets copied to one row buffer where it is unfiltered (if necessary) then a copy is made in a separate buffer that is only used for the filter handling. If you test using images with large rows (I don't know what pngbench does) the copy buffer may well get flushed out of the second level cache between each row, then the memcpy will stall bringing it back in. If you have machine level profiling you may see this as a massive time spike on some probably unrelated instruction which just happens to be in the PC when the stall stops everything. Anyway, I have several ideas of how to avoid the copy when it isn't required. John Bowler <jbowler(a)acm.org> -----Original Message----- From: Glenn Randers-Pehrson [mailto:glennrp@gmail.com] Sent: Monday, October 03, 2011 1:15 PM To: PNG/MNG implementation discussion list Subject: [png-mng-implement] Use of memcpy() in libpng [Fwd from linaro-toolchain list] Re: Use of memcpy() in libpng David Gilbert Tue, 27 Sep 2011 06:20:14 -0700 On 27 September 2011 14:16, Christian Robottom Reis <k...(a)linaro.org> wrote: > On Tue, Sep 27, 2011 at 09:47:33AM +0100, Ramana Radhakrishnan wrote: >> On 26 September 2011 21:51, Michael Hope <michael.h...(a)linaro.org> wrote: >> > Saw this on the linaro-multimedia list: >> > >> > http://lists.linaro.org/pipermail/linaro-multimedia/2011-September/ >> > 000074.html >> > >> > libpng spends a significant amount of time in memcpy(). This might >> > tie in with Ramana's investigation or the unaligned access work by >> > allowing more memcpy()s to be inlined. >> >> It's the unaligned access and the change / improvements to the memcpy >> that *might* help in this case. But that ofcourse depends on the >> compiler knowing when it can do such a thing. Ofcourse what might be >> more interesting is the kind of workload analysis that Dave's done in >> the past with memcpy to know what the alignment and size of the >> buffer being copied is. > > If you guys could take a look at this there is a potential requirement > for the MMWG around libpng optimization; we could fit this in along > with other work (possible vectorizing, etc) on that component. It wouldn't take long to analyse the memcpy calls - life would be easier if we had the test program and some details on things like what size of images were used in these benchmarks. Dave

13 years, 8 months

[ACTIVITY] 3rd - 7th October

by Andrew Stubbs

Continued work on my constant reuse optimizations. Not too much this week though. I've now fixed some issues with the ARM size-costs code that was causing it to wildly over-estimate the cost of a MOVT instruction. I'll have to post this upstream sometime soon. Took another look at the shift-amount bug. Discussed the issue with Paul Brook. I've now fixed the original bug, and fixed the new bug introduced by Paul's original fix, and committed that upstream. I still need to backport it to Linaro GCC though, and the latent bug that Richard S spotted is still being analysed. Did a merge from FSF 4.5 & 4.6 to Linaro, and pushed them the Launchpad branches for testing. Begun work benchmarking different setups for the generic tuning patches. I had a lot of trouble trying to set up SPEC2000 though. Hopefully these issues are now resolved, with some help from Michael, and I have established some baseline figures on both A8 and A9 to work from. No progress on native tuning. I'm still waiting for upstream review. In other news: Mentor's contract with Linaro has now been extended for another 6 months. :)

13 years, 8 months

[ACTIVITY] 2011-10-07

by David Gilbert

== String Routines == * Built and tested a newlib with my memchr in - ready to go with a bit of tidy up. * Followed up on my eglibc patch submission by a comment suggesting the use of --with-cpu pointing back at the previous discussion. == 64 Bit atomics == * Updated gcc patch based on Ramana's comments, retested and posted new version - Lost half a day to a failing SD card in our panda. == QEMU == * Posted a patch that made one variable thread local using __thread that fixes multi threaded user mode ARM programs (e.g. firefox); this seems to have mutated on the list into a patch for more general thread local support. Dave

13 years, 8 months

[ACTIVITY] Oct 04 - Oct 07

by Ulrich Weigand

== GDB == * Reimplemented patch to disable address space randomization in gdbserver to respect the "set disable-randomization" command, and checked it in to mainline and Linaro GDB 7.3 * Worked on support for cross-platform core file generation. == GCC == * Checked in mainline fix for PR 50305. Mit freundlichen Gruessen / Best Regards Ulrich Weigand -- Dr. Ulrich Weigand | Phone: +49-7031/16-3727 STSM, GNU compiler and toolchain for Linux on System z and Cell/B.E. IBM Deutschland Research & Development GmbH Vorsitzender des Aufsichtsrats: Martin Jetter | Geschäftsführung: Dirk Wittkopp Sitz der Gesellschaft: Böblingen | Registergericht: Amtsgericht Stuttgart, HRB 243294

13 years, 8 months

[ACTIVITY] October 2-6

by Ira Rosen

Hi, - worked on the RTL part of the widen-shift patch - backported to linaro 2/3 of the SLP patches, and proposed the third one - worked on additional SLP improvements: - swap operands to make statements isomorphic - support load with offset 1 (after load from 0) - started working on presentation for NEON forum Upcoming holidays: Oct 12, Wed - half day Oct 13, Thu Oct 16-19, Sun-Wed - half day Oct 20, Thu Ira

13 years, 8 months

[RFC ARM] Use vcvt.f32.s32 with immediate bits to do fixed to floating point conversions.

by Ramana Radhakrishnan

Hi, So one of the things Michael pointed out in today's call was that the ARM backend doesn't generate vcvt.f32.s<type> where you have an idiom conversion from fixed to floating point as in the example below. I've chosen to implement this in the following manner in the backend using these interfaces from real.c . The reason I've chosen to not allow this transformation in case flag_rounding_math is true is because this instruction always ends up rounding using round-to-nearest rather than obeying whats in the FPSCR and thus is not safe for programs that want to dynamically set their rounding modes. The benefits are quite obvious in that we eliminate a load from the constant pool and a floating point multiply and thus essentially shaving off a floating point multiply + Load latency off these sequences. This instruction can only write the output into the same register as the input register which is why I've modelled it as below by tying op1 into op0. If there's a simpler way of using the interfaces into real.c then I'm all ears ? Thoughts ? I believe such idioms are used in libav from where the original report appears to have come and thus it's a worthwhile gain where we can have it. Any other places where folks might have noticed this. I will post upstream as well once I finish testing this patch. I'm posting this here to get some feedback as well to let anyone who is really really keen about trying this out have a go given I'm out tomorrow. ( I took a quick look at the short -> f32 case as well but the fact remains that loads either zero or sign extend anyway so there's probably not much gain in modelling that right away and the win really is in getting rid of that fp mul and the constant pool load. There's probably some gain in going from i64-> f64 as well so those patterns need to be written up at some point for completeness ) cheers Ramana 2011-10-04 Ramana Radhakrishnan <ramana.radhakrishnan(a)linaro.org> * config/arm/arm.c (vfp3_const_double_for_fract_bits): Define. * config/arm/arm-protos.h (vfp3_const_double_for_fract_bits): Declare. * config/arm/constraints.md ("Dt"): New constraint. * config/arm/predicates.md (const_double_vcvt_power_of_two_reciprocal): New. * config/arm/vfp.md (*arm_combine_vcvt_f32_s32): New. (*arm_combine_vcvt_f32_u32): New. For the following testcases I see the code as follows with -mfloat-abi=hard -mfpu=vfpv3 and -mcpu=cortex-a9 float foo (int i) { float v = (float)i / (1 << 11); return v; } float foa_unsigned (unsigned int i) { float v = (float)i / (1 << 5); return v; } After patch . foo: @ args = 0, pretend = 0, frame = 0 @ frame_needed = 0, uses_anonymous_args = 0 @ link register save eliminated. fmsr s0, r0 @ int vcvt.f32.s32 s0, s0, #11 bx lr .size foo, .-foo .align 2 .global foa_unsigned .type foa_unsigned, %function foa_unsigned: @ args = 0, pretend = 0, frame = 0 @ frame_needed = 0, uses_anonymous_args = 0 @ link register save eliminated. fmsr s0, r0 @ int vcvt.f32.u32 s0, s0, #5 bx lr .size foa_unsigned, .-foa_unsigned .align 2 .global foo1 .type foo1, %function rather than .type foo, %function foo: @ args = 0, pretend = 0, frame = 0 @ frame_needed = 0, uses_anonymous_args = 0 @ link register save eliminated. fmsr s15, r0 @ int fsitos s0, s15 flds s15, .L2 fmuls s0, s0, s15 bx lr .L3: .align 2 .L2: .word 973078528 .size foo, .-foo .align 2 .global foa_unsigned .type foa_unsigned, %function foa_unsigned: @ args = 0, pretend = 0, frame = 0 @ frame_needed = 0, uses_anonymous_args = 0 @ link register save eliminated. fmsr s15, r0 @ int fuitos s0, s15 flds s15, .L5 fmuls s0, s0, s15 bx lr .L6: .align 2 .L5: .word 1023410176

13 years, 9 months

[ACTIVITY] 26th - 30th September

by Andrew Stubbs

* Vacation Monday, Tuesday, and Wednesday. * GCC Continued work on my constant reuse optimizations. Disappointingly, I've found that there are very few optimization opportunities in EEMBC (ARM/Thumb V7-A), although it's not difficult to write testcases that the optimization could improve. I also discovered that the data-flow chains don't work exactly how I thought (with respect to if-then-else cases) so I need to do a little more work. Pinged the native tuning patches; they're still waiting for upstream review. Still can't get the generic tuning work done as the CodeSourcery panda boards appear to be still offline.

13 years, 9 months

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

linaro-toolchain