[llvm-dev] General question about enabling partial inlining
Jun Lim via llvm-dev
llvm-dev at lists.llvm.org
Tue Oct 3 10:06:37 PDT 2017
> As for the cost model, right now it's platform independent, so I'm
assuming you'll need some sort of hook for platform-specific costs/bonuses
to detect spilling of different types of registers. Also, I'm not quite sure
how you'll do this type of detection at the IR level. Are you thinking some
sort of heuristic?
Agree, it should be a target specific hook if doing so make sense. As far
as I see the CSRCost used in RegAllocGreedy is extremely low, so in most
cases we allocate a CSR if a live range expand across a function call. I
guess we can estimate this by checking if a user of a value defined in the
entry block is reachable from a block with a function call.
From: Graham Yiu [mailto:gyiu at ca.ibm.com]
Sent: Tuesday, October 3, 2017 12:45 PM
To: Jun Lim <junbuml at codeaurora.org>
Cc: llvm-dev at lists.llvm.org
Subject: RE: [llvm-dev] General question about enabling partial inlining
Hi Jun,
If we were to enable this by default, I think we'd make a push to enable it
with or without PGO. I'm not sure what's currently preventing the partial
inlining pass to be enabled by default, actually. David Li may have a better
sense on this as he's been actively working on it most recently.
As for the cost model, right now it's platform independent, so I'm assuming
you'll need some sort of hook for platform-specific costs/bonuses to detect
spilling of different types of registers. Also, I'm not quite sure how
you'll do this type of detection at the IR level. Are you thinking some sort
of heuristic?
Graham Yiu
LLVM Compiler Development
IBM Toronto Software Lab
Office: (905) 413-4077 C2-707/8200/Markham
Email: gyiu at ca.ibm.com <mailto:gyiu at ca.ibm.com>
"Jun Lim" ---10/03/2017 12:21:38 PM---Hi Graham,
From: "Jun Lim" <junbuml at codeaurora.org <mailto:junbuml at codeaurora.org> >
To: "'Graham Yiu'" <gyiu at ca.ibm.com <mailto:gyiu at ca.ibm.com> >
Cc: <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org> >
Date: 10/03/2017 12:21 PM
Subject: RE: [llvm-dev] General question about enabling partial inlining
_____
Hi Graham,
Thanks for sharing this. Are you planning on enabling the pass only on PGO?
Even in non-PGO, I noticed some performance gains when we are aggressive in
partially inlining the early return part, especially when the callee spill
CSRs in the entry block. At a high level, I have two questions:
1. What is the main obstacle that prevent the pass from being enabled by
default?
2. Would it make sense to give some bonus in the cost model when we detect
the possibility of spilling CSRs in the entry block?
Thanks,
Jun
From: Graham Yiu [mailto:gyiu at ca.ibm.com]
Sent: Tuesday, October 3, 2017 11:08 AM
To: junbuml at codeaurora.org <mailto:junbuml at codeaurora.org>
Cc: llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>
Subject: Re: [llvm-dev] General question about enabling partial inlining
Hi Jun,
We're actually looking at enhancing the partial inlining pass right now (see
<https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.llvm.org_pipermai
l_llvm-2Ddev_2017-2DAugust_116515.html&d=DwMFAg&c=jf_iaSHvJObTbx-siA1ZOg&r=4
ST7e3kMd0GTi3w9ByK5Cw&m=9oYOvB3l33-euX7ag6texitDSABCTLWfauz0YGW7zZ8&s=lZOJDe
oavpuEHo29CLd9Kvkn1ibSdgK5125f13O-LYQ&e=>
http://lists.llvm.org/pipermail/llvm-dev/2017-August/116515.html)
We'd be interested in turning on the pass by default some time in the
future, if our enhancements prove beneficial.
Cheers,
Graham Yiu
LLVM Compiler Development
IBM Toronto Software Lab
Office: (905) 413-4077 C2-707/8200/Markham
Email: <mailto:gyiu at ca.ibm.com> gyiu at ca.ibm.com
via llvm-dev ---09/13/2017 01:12:02 PM---Hi, I noticed some performance
gains in some spec benchmarks without
From: via llvm-dev < <mailto:llvm-dev at lists.llvm.org>
llvm-dev at lists.llvm.org>
To: <mailto:llvm-dev at lists.llvm.org> llvm-dev at lists.llvm.org
Date: 09/13/2017 01:12 PM
Subject: [llvm-dev] General question about enabling partial inlining
Sent by: "llvm-dev" < <mailto:llvm-dev-bounces at lists.llvm.org>
llvm-dev-bounces at lists.llvm.org>
_____
Hi,
I noticed some performance gains in some spec benchmarks without
significant code size bloat when aggressively performing partial
inlining, especially when the original callee spill CSRs in the entry
block. I guess the partial inlining is not enabled mainly due to the
code size. Is there any other issue which prevent the pass from being
enabled? Do we have any plan or any on-going works to enable partial
inlining ?
Thanks,
Jun
--
Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm
Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a
Linux Foundation Collaborative Project.
_______________________________________________
LLVM Developers mailing list
<mailto:llvm-dev at lists.llvm.org> llvm-dev at lists.llvm.org
<https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.llvm.org_cgi-2Dbi
n_mailman_listinfo_llvm-2Ddev&d=DwIGaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=4ST7e3kMd0
GTi3w9ByK5Cw&m=zEValqMYe9FvZqI-GQUgWPmVUgbEq8OBAjTrBjz9xhY&s=1h4Cw3vDlJBIknk
n0Ts3R_e3PU64h_dyvEkyCdonAVo&e=>
https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.llvm.org_cgi-2Dbin
_mailman_listinfo_llvm-2Ddev&d=DwIGaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=4ST7e3kMd0G
Ti3w9ByK5Cw&m=zEValqMYe9FvZqI-GQUgWPmVUgbEq8OBAjTrBjz9xhY&s=1h4Cw3vDlJBIknkn
0Ts3R_e3PU64h_dyvEkyCdonAVo&e=
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20171003/90e1fa8b/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.gif
Type: image/gif
Size: 105 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20171003/90e1fa8b/attachment.gif>
More information about the llvm-dev
mailing list