This is the mail archive of the
mailing list for the GCC project.
Re: Fix scheduler ix86_issue_rate and ix86_adjust_cost for modern x86 chips
- From: Jan Hubicka <hubicka at ucw dot cz>
- To: "Gopalasubramanian, Ganesh" <Ganesh dot Gopalasubramanian at amd dot com>
- Cc: Jan Hubicka <hubicka at ucw dot cz>, "gcc-patches at gcc dot gnu dot org" <gcc-patches at gcc dot gnu dot org>, "Uros Bizjak (ubizjak at gmail dot com)" <ubizjak at gmail dot com>, "H.J. Lu (hjl dot tools at gmail dot com)" <hjl dot tools at gmail dot com>
- Date: Thu, 24 Oct 2013 15:18:11 +0200
- Subject: Re: Fix scheduler ix86_issue_rate and ix86_adjust_cost for modern x86 chips
- Authentication-results: sourceware.org; auth=none
- References: <EB4625145972F94C9680D8CADD6516155C23F184 at SATLEXDAG02 dot amd dot com> <20131024092425 dot GA13149 at atrey dot karlin dot mff dot cuni dot cz> <EB4625145972F94C9680D8CADD6516155C23F201 at SATLEXDAG02 dot amd dot com>
> > Is this with -fschedule-insns? Or only with default settings? Did you test the compile time implications of increasing the lookahead? (value of 8 is very large, we may consider enbling it only for -Ofast, limiting for postreload only or something similar).
> The improvement is seen with the options "-fschedule-insns -fschedule-insns2 -fsched-pressure"
> Below are the build times of some of the SPEC benchmarks
> dfa8 no_lookahead
> perlbench - 196s 193s
> bzip2 - 19s 19s
> gcc - 439s 429s
> mcf - 3s 3s
> gobmk - 119s 115s
> hmmer - 62s 60s
> sjeng - 18s 17s
> libquantum - 6s 6s
> h264ref - 110s 107s
> omnetpp - 132s 128s
> astar - 7s 7s
> bwaves - 4s 5s
> gamess - 1996s 1957s
> milc - 18s 18s
> GemsFDTD - 276s 272s
> I think we can enable it by default rather than for -Ofast.
> Please let me know your inputs.
OK, so it is about 2%. Did you try if you need lookahead even in the early
pass (before reload)? My guess would be so, but if not, it could cut the cost
to half. For -Ofast/-O3 it looks resonable to me, but we will need to announce
it on the ML. For other settings I think we need to work on more improvmeents or cut
> -----Original Message-----
> From: Jan Hubicka [mailto:firstname.lastname@example.org]
> Sent: Thursday, October 24, 2013 2:54 PM
> To: Gopalasubramanian, Ganesh
> Cc: email@example.com; Uros Bizjak (firstname.lastname@example.org); email@example.com; H.J. Lu (firstname.lastname@example.org)
> Subject: Re: Fix scheduler ix86_issue_rate and ix86_adjust_cost for modern x86 chips
> > Attached is the patch which does the following scheduler related changes.
> > * re-models bdver3 decoder.
> > * It enables lookahead with value 8 for all BD architectures. The patch doesn't consider if reloading is completed or not (an area that needs to be worked on).
> > * The issue rate for BD architectures are set to 4.
> > I see the following performance improvements on bdver3 machine.
> > * GemsFDTD improves by 6-7% with lookahead value changed to 8.
> > * Hmmer improves by 9% when issue rate when set to 4 .
> Is this with -fschedule-insns? Or only with default settings? Did you test the compile time implications of increasing the lookahead? (value of 8 is very large, we may consider enbling it only for -Ofast, limiting for postreload only or something similar).
> > I have considered the following hardware details for the model.
> > * There are four decoders inside a hardware decoder block.
> > * These four independent decoders can execute in parallel. (They can take 8B from four different instructions and decode).
> > * These four decoders are pipelined 4 cycles deep and are non-stalling.
> > * Each decoder takes 8B of instruction data every cycle and tries decoding it.
> > * Issue rate is 4.
> What is the overall limitation on number of bytes the instructions can occupy?
> I think they need to fit into 2 16 byte windows, right?
> In that case we may want to tweak the existing corei7 scheduling code to take care of this. Making scheduler not overly optimistic about the parallelism is good since it will make less register pressure during the first pass..
> > Is it OK for upstream?
> Otherwise the patch seems OK, but I would like to know the compile time effect first.
> > Changelog
> > ========
> > 2013-10-24 Ganesh Gopalasubramanian
> > <Ganesh.Gopalasubramanian@amd.com>
> > * config/i386/bdver3.md : Added two additional decoder units
> > to support issue rate of 4 and remodeled vector unit.
> > * config/i386/i386.c (ix86_issue_rate): Issue rate for BD
> > architectures is set to 4.
> > * config/i386/i386.c (ia32_multipass_dfa_lookahead): DFA
> > lookahead is set to 8 for BD architectures.
> > Regards
> > Ganesh