Message-ID: <CAF1bQ=RfESfkYj3DPHjjNOEJxwwKBHgYp84=Tnk4=NwkjPuMxw@mail.gmail.com>
Date: Mon, 29 Jul 2024 13:52:51 -0700
From: Rong Xu <xur@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Han Shen <shenhan@...gle.com>, Sriraman Tallam <tmsriram@...gle.com>, 
	David Li <davidxl@...gle.com>, Jonathan Corbet <corbet@....net>, 
	Masahiro Yamada <masahiroy@...nel.org>, Nathan Chancellor <nathan@...nel.org>, 
	Nicolas Schier <nicolas@...sle.eu>, Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>, 
	Borislav Petkov <bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org, 
	"H . Peter Anvin" <hpa@...or.com>, Ard Biesheuvel <ardb@...nel.org>, Arnd Bergmann <arnd@...db.de>, 
	Josh Poimboeuf <jpoimboe@...nel.org>, Nick Desaulniers <ndesaulniers@...gle.com>, 
	Bill Wendling <morbo@...gle.com>, Justin Stitt <justinstitt@...gle.com>, 
	Vegard Nossum <vegard.nossum@...cle.com>, John Moon <john@...on.dev>, 
	Andrew Morton <akpm@...ux-foundation.org>, Heiko Carstens <hca@...ux.ibm.com>, 
	Luis Chamberlain <mcgrof@...nel.org>, Samuel Holland <samuel.holland@...ive.com>, 
	Mike Rapoport <rppt@...nel.org>, "Paul E . McKenney" <paulmck@...nel.org>, Rafael Aquini <aquini@...hat.com>, 
	Petr Pavlu <petr.pavlu@...e.com>, Eric DeVolder <eric.devolder@...cle.com>, 
	Bjorn Helgaas <bhelgaas@...gle.com>, Randy Dunlap <rdunlap@...radead.org>, 
	Benjamin Segall <bsegall@...gle.com>, Breno Leitao <leitao@...ian.org>, 
	Wei Yang <richard.weiyang@...il.com>, Brian Gerst <brgerst@...il.com>, 
	Juergen Gross <jgross@...e.com>, Palmer Dabbelt <palmer@...osinc.com>, 
	Alexandre Ghiti <alexghiti@...osinc.com>, Kees Cook <kees@...nel.org>, 
	Sami Tolvanen <samitolvanen@...gle.com>, Xiao Wang <xiao.w.wang@...el.com>, 
	Jan Kiszka <jan.kiszka@...mens.com>, linux-doc@...r.kernel.org, 
	linux-kernel@...r.kernel.org, linux-kbuild@...r.kernel.org, 
	linux-efi@...r.kernel.org, linux-arch@...r.kernel.org, llvm@...ts.linux.dev
Subject: Re: [PATCH 0/6] Add AutoFDO and Propeller support for Clang build

On Mon, Jul 29, 2024 at 1:51 AM Peter Zijlstra <peterz@...radead.org> wrote:
>
> On Sun, Jul 28, 2024 at 01:29:53PM -0700, Rong Xu wrote:
> > Hi,
> >
> > This patch series is to integrate AutoFDO and Propeller support into
> > the Linux kernel. AutoFDO is a profile-guided optimization technique
> > that leverages hardware sampling to enhance binary performance.
> > Unlike Instrumentation-based FDO (iFDO), AutoFDO offers a user-friendly
> > and straightforward application process. While iFDO generally yields
> > superior profile quality and performance, our findings reveal that
> > AutoFDO achieves remarkable effectiveness, bringing performance close
> > to iFDO for benchmark applications. Similar to AutoFDO, Propeller too
> > utilizes hardware sampling to collect profiles and apply post-link
> > optimizations to improve the benchmark’s performance over and above
> > AutoFDO.
> >
> > Our empirical data demonstrates significant performance improvements
> > with AutoFDO and Propeller, up to 10% on microbenchmarks and up to 5%
> > on large warehouse-scale benchmarks. This makes a strong case for their
> > inclusion as supported features in the upstream kernel.
> >
> > Background
> >
> > A significant fraction of fleet processing cycles (excluding idle time)
> > from data center workloads are attributable to the kernel. Ware-house
> > scale workloads maximize performance by optimizing the production kernel
> > using iFDO (a.k.a instrumented PGO, Profile Guided Optimization).
> >
> > iFDO can significantly enhance application performance but its use
> > within the kernel has raised concerns. AutoFDO is a variant of FDO that
> > uses the hardware’s Performance Monitoring Unit (PMU) to collect
> > profiling data. While AutoFDO typically yields smaller performance
> > gains than iFDO, it presents unique benefits for optimizing kernels.
> >
> > AutoFDO eliminates the need for instrumented kernels, allowing a single
> > optimized kernel to serve both execution and profile collection. It also
> > minimizes slowdown during profile collection, potentially yielding
> > higher-fidelity profiling, especially for time-sensitive code, compared
> > to iFDO. Additionally, AutoFDO profiles can be obtained from production
> > environments via the hardware’s PMU whereas iFDO profiles require
> > carefully curated load tests that are representative of real-world
> > traffic.
> >
> > AutoFDO facilitates profile collection across diverse targets.
> > Preliminary studies indicate significant variation in kernel hot spots
> > within Google’s infrastructure, suggesting potential performance gains
> > through target-specific kernel customization.
> >
> > Furthermore, other advanced compiler optimization techniques, including
> > ThinLTO and Propeller can be stacked on top of AutoFDO, similar to iFDO.
> > ThinLTO achieves better runtime performance through whole-program
> > analysis and cross module optimizations. The main difference between
> > traditional LTO and ThinLTO is that the latter is scalable in time and
> > memory.
>
> This,
>
> > Propeller is a profile-guided, post-link optimizer that improves
> > the performance of large-scale applications compiled with LLVM. It
> > operates by relinking the binary based on an additional round of runtime
> > profiles, enabling precise optimizations that are not possible at
> > compile time.
>
> should be on top somewhere, not hidden away inside a giant wall of text
> somewhere at the end.

Thanks for the suggestion. I'll move it up. Maybe after the first
paragraph in Background.

Sorry if you received a duplicated message -- I'm resending this in
plain text mode.

-Rong

Powered by blists - more mailing lists