[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAK7LNARiEhNBPikEv--YpdKTPt5B5tFF_J0T8+xbi1CS6WJBFQ@mail.gmail.com>
Date: Sat, 2 Nov 2024 03:01:31 +0900
From: Masahiro Yamada <masahiroy@...nel.org>
To: Rong Xu <xur@...gle.com>
Cc: Alice Ryhl <aliceryhl@...gle.com>, Andrew Morton <akpm@...ux-foundation.org>,
Arnd Bergmann <arnd@...db.de>, Bill Wendling <morbo@...gle.com>, Borislav Petkov <bp@...en8.de>,
Breno Leitao <leitao@...ian.org>, Brian Gerst <brgerst@...il.com>,
Dave Hansen <dave.hansen@...ux.intel.com>, David Li <davidxl@...gle.com>,
Han Shen <shenhan@...gle.com>, Heiko Carstens <hca@...ux.ibm.com>, "H. Peter Anvin" <hpa@...or.com>,
Ingo Molnar <mingo@...hat.com>, Jann Horn <jannh@...gle.com>, Jonathan Corbet <corbet@....net>,
Josh Poimboeuf <jpoimboe@...nel.org>, Juergen Gross <jgross@...e.com>,
Justin Stitt <justinstitt@...gle.com>, Kees Cook <kees@...nel.org>,
"Mike Rapoport (IBM)" <rppt@...nel.org>, Nathan Chancellor <nathan@...nel.org>,
Nick Desaulniers <ndesaulniers@...gle.com>, Nicolas Schier <nicolas@...sle.eu>,
"Paul E. McKenney" <paulmck@...nel.org>, Peter Zijlstra <peterz@...radead.org>,
Sami Tolvanen <samitolvanen@...gle.com>, Thomas Gleixner <tglx@...utronix.de>,
Wei Yang <richard.weiyang@...il.com>, workflows@...r.kernel.org,
Miguel Ojeda <miguel.ojeda.sandonis@...il.com>, Maksim Panchenko <max4bolt@...il.com>,
Yonghong Song <yonghong.song@...ux.dev>, Yabin Cui <yabinc@...gle.com>,
Krzysztof Pszeniczny <kpszeniczny@...gle.com>, Sriraman Tallam <tmsriram@...gle.com>,
Stephane Eranian <eranian@...gle.com>, x86@...nel.org, linux-arch@...r.kernel.org,
linux-doc@...r.kernel.org, linux-kbuild@...r.kernel.org,
linux-kernel@...r.kernel.org, llvm@...ts.linux.dev
Subject: Re: [PATCH v5 1/7] Add AutoFDO support for Clang build
On Thu, Oct 24, 2024 at 7:44 AM Rong Xu <xur@...gle.com> wrote:
>
> Add the build support for using Clang's AutoFDO. Building the kernel
> with AutoFDO does not reduce the optimization level from the
> compiler. AutoFDO uses hardware sampling to gather information about
> the frequency of execution of different code paths within a binary.
> This information is then used to guide the compiler's optimization
> decisions, resulting in a more efficient binary. Experiments
> showed that the kernel can improve up to 10% in latency.
>
> The support requires a Clang compiler after LLVM 17. This submission
> is limited to x86 platforms that support PMU features like LBR on
> Intel machines and AMD Zen3 BRS. Support for SPE on ARM 1,
> and BRBE on ARM 1 is part of planned future work.
>
> Here is an example workflow for AutoFDO kernel:
>
> 1) Build the kernel on the host machine with LLVM enabled, for example,
> $ make menuconfig LLVM=1
> Turn on AutoFDO build config:
> CONFIG_AUTOFDO_CLANG=y
> With a configuration that has LLVM enabled, use the following
> command:
> scripts/config -e AUTOFDO_CLANG
> After getting the config, build with
> $ make LLVM=1
>
> 2) Install the kernel on the test machine.
>
> 3) Run the load tests. The '-c' option in perf specifies the sample
> event period. We suggest using a suitable prime number,
> like 500009, for this purpose.
> For Intel platforms:
> $ perf record -e BR_INST_RETIRED.NEAR_TAKEN:k -a -N -b -c <count> \
> -o <perf_file> -- <loadtest>
> For AMD platforms:
> The supported system are: Zen3 with BRS, or Zen4 with amd_lbr_v2
> For Zen3:
> $ cat proc/cpuinfo | grep " brs"
> For Zen4:
> $ cat proc/cpuinfo | grep amd_lbr_v2
> $ perf record --pfm-events RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a \
> -N -b -c <count> -o <perf_file> -- <loadtest>
>
> 4) (Optional) Download the raw perf file to the host machine.
>
> 5) To generate an AutoFDO profile, two offline tools are available:
> create_llvm_prof and llvm_profgen. The create_llvm_prof tool is part
> of the AutoFDO project and can be found on GitHub
> (https://github.com/google/autofdo), version v0.30.1 or later. The
> llvm_profgen tool is included in the LLVM compiler itself. It's
> important to note that the version of llvm_profgen doesn't need to
> match the version of Clang. It needs to be the LLVM 19 release or
> later, or from the LLVM trunk.
> $ llvm-profgen --kernel --binary=<vmlinux> --perfdata=<perf_file> \
> -o <profile_file>
> or
> $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file> \
> --format=extbinary --out=<profile_file>
>
> Note that multiple AutoFDO profile files can be merged into one via:
> $ llvm-profdata merge -o <profile_file> <profile_1> ... <profile_n>
>
> 6) Rebuild the kernel using the AutoFDO profile file with the same config
> as step 1, (Note CONFIG_AUTOFDO_CLANG needs to be enabled):
> $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<profile_file>
>
> Co-developed-by: Han Shen <shenhan@...gle.com>
> Signed-off-by: Han Shen <shenhan@...gle.com>
> Signed-off-by: Rong Xu <xur@...gle.com>
> Suggested-by: Sriraman Tallam <tmsriram@...gle.com>
> Suggested-by: Krzysztof Pszeniczny <kpszeniczny@...gle.com>
> Suggested-by: Nick Desaulniers <ndesaulniers@...gle.com>
> Suggested-by: Stephane Eranian <eranian@...gle.com>
> Tested-by: Yonghong Song <yonghong.song@...ux.dev>
> +Workflow
> +========
> +
> +Here is an example workflow for AutoFDO kernel:
> +
> +1) Build the kernel on the host machine with LLVM enabled,
> + for example, ::
> +
> + $ make menuconfig LLVM=1
> +
> + Turn on AutoFDO build config::
> +
> + CONFIG_AUTOFDO_CLANG=y
> +
> + With a configuration that with LLVM enabled, use the following command::
> +
> + $ scripts/config -e AUTOFDO_CLANG
> +
> + After getting the config, build with ::
> +
> + $ make LLVM=1
> +
> +2) Install the kernel on the test machine.
> +
> +3) Run the load tests. The '-c' option in perf specifies the sample
> + event period. We suggest using a suitable prime number, like 500009,
> + for this purpose.
> +
> + - For Intel platforms::
> +
> + $ perf record -e BR_INST_RETIRED.NEAR_TAKEN:k -a -N -b -c <count> -o <perf_file> -- <loadtest>
> +
> + - For AMD platforms::
I am not sure if this double-colon is needed
when the next line is not code.
> + The supported systems are: Zen3 with BRS, or Zen4 with amd_lbr_v2. To check,
> + For Zen3::
> +
> + $ cat proc/cpuinfo | grep " brs"
> +
> + For Zen4::
> +
> + $ cat proc/cpuinfo | grep amd_lbr_v2
> +
> + The following command generated the perf data file::
> +
> + $ perf record --pfm-events RETIRED_TAKEN_BRANCH_INSTRUCTIONS:k -a -N -b -c <count> -o <perf_file> -- <loadtest>
> +
> +4) (Optional) Download the raw perf file to the host machine.
> +
> +5) To generate an AutoFDO profile, two offline tools are available:
> + create_llvm_prof and llvm_profgen. The create_llvm_prof tool is part
> + of the AutoFDO project and can be found on GitHub
> + (https://github.com/google/autofdo), version v0.30.1 or later.
> + The llvm_profgen tool is included in the LLVM compiler itself. It's
> + important to note that the version of llvm_profgen doesn't need to match
> + the version of Clang. It needs to be the LLVM 19 release of Clang
> + or later, or just from the LLVM trunk. ::
> +
> + $ llvm-profgen --kernel --binary=<vmlinux> --perfdata=<perf_file> -o <profile_file>
> +
> + or ::
> +
> + $ create_llvm_prof --binary=<vmlinux> --profile=<perf_file> --format=extbinary --out=<profile_file>
> +
> + Note that multiple AutoFDO profile files can be merged into one via::
> +
> + $ llvm-profdata merge -o <profile_file> <profile_1> <profile_2> ... <profile_n>
> +
> +6) Rebuild the kernel using the AutoFDO profile file with the same config as step 1,
> + (Note CONFIG_AUTOFDO_CLANG needs to be enabled)::
> +
> + $ make LLVM=1 CLANG_AUTOFDO_PROFILE=<profile_file>
> +
Trailing blank line.
.git/rebase-apply/patch:187: new blank line at EOF.
--
Best Regards
Masahiro Yamada
Powered by blists - more mailing lists