Date: Sat, 13 May 2023 01:50:15 -0700 From: Mark Millard <marklmi@yahoo.com> To: freebsd-arm <freebsd-arm@freebsd.org> Subject: Re: -mcpu= selections and the Windows Dev Kit 2023: example from-scratch buildkernel times (after kernel-toolchain) Message-ID: <6196193E-4A75-464C-AB0B-AE2C3BC00D66@yahoo.com> In-Reply-To: <3B5EB0DD-E9CB-41BD-9BCC-6549BBF0C0DA@yahoo.com> References: <3B5EB0DD-E9CB-41BD-9BCC-6549BBF0C0DA@yahoo.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On May 13, 2023, at 01:28, Mark Millard <marklmi@yahoo.com> wrote: > While the selections were guided by some benchmark like > explorations, the results for the Windows Dev Kit 2023 > (WDK23 abbreviation) go like: >=20 >=20 > -mcpu=3Dcortex-a72 code generation produced a (non-debug) > kernel/world that, in turn, got (from scratch buildkernel after > kernel-toolchain): >=20 > Kernel(s) GENERIC-NODBG-CA72 built in 597 seconds, ncpu: 8, make -j8 >=20 > (The rest of the aarch64 that I've access to is nearly-all cortex-a72 > based, the others being cortex-a53 these days. So I was seeing how > code tailored for the cortex-a72 context performed on the WDK23. > cortex-a72 was my starting point with the WDK23.) >=20 >=20 > -mcpu=3Dcortex-x1c+flagm code generation produced a (non-debug) > kernel/world that, in turn, got (from scratch buildkernel after > kernel-toolchain): >=20 > Kernel(s) GENERIC-NODBG-CA78C built in 584 seconds, ncpu: 8, make -j8 >=20 > NOTE: "+flagm" is because of various clang/gcc having an inaccurate > set of features that omit flagm --and I'm making sure I've got it > enabled. -mcpu=3Dcortex-a78c is even worse: it has examples of = +fp16fml > by default in some toolchains --but neither of the 2 types of core has > support for such. (The cortex-x1c and cortex-a78c actually have = matching > features for code generation purposes, at least for all that I looked > at. Toolchain mismatches for default features are sufficient evidence > of an error in at least one case as far as I can tell.) >=20 > This context is implicitly +lse+rcpc . At the time I was not being > explicit when defaults matched. >=20 > Notes: > "lse" is the large system extension atomics, disabled below. > "rcpc" is the extension having load acquire and store release > instructions. (rcpc I was explicit about below, despite the > default matching.) >=20 >=20 > -mcpu=3Dcortex-x1c+flagm+nolse+rcpc code generation produced a > (non-debug) kernel/world that, in turn, got (from scratch buildkernel > after kernel-toolchain): >=20 > Kernel(s) GENERIC-NODBG-CA78CnoLSE built in 415 seconds, ncpu: 8, = make -j >=20 > Note: My explorations so far have tried the world combinations of > lse and rcpc status but with a kernel that was based on > -mcpu=3Dcortex-x1c+flagm . I then updated the kernel to match the > -mcpu=3Dcortex-x1c+flagm+nolse+rcpc and used it to produce the above. > So there is more exploring that I've not done yet. But I'm not > expecting decreases to notably below the 415 sec. >=20 > The benchmark like activity had showed that +lse+rcpc for the > world/benchmark builds lead to notable negative consequences for > cpus 0..3 compared to the other 3 combinations of status. For > cpus 4..7, it showed that +nolse+rcpc for the world/benchmark > builds had a noticeable gain compared to the other 3 combinations. > This guided the buildkernel testing selections done so far. The > buildkernel tests were, in part, to be sure that the apparent > consequences were not just odd consequences for time measurements > that could mess up benchmark result comparisons being useful. >=20 >=20 > For comparison to a standard FreeBSD non-debug build, I used a > snapshot download of: >=20 > = http://ftp3.freebsd.org/pub/FreeBSD/snapshots/ISO-IMAGES/13.2/FreeBSD-13.2= -STABLE-arm64-aarch64-ROCK64-20230504-7dea7445ba44-255298.img.xz >=20 > and dd'd it to media, replaced the EFI/*/* with ones that > work for the Windows Dev Kit 2023, booted the WDK23 with the media, > copied over my /usr/*-src/ to the media, did a "make -j8 = kernel-toolchain", > from the /usr/main-src/ copy and finally did a "make -j8 buildkernel" > (so, from-scratch, given the toolchain materials are already in = place): >=20 > Kernel(s) GENERIC built in 505 seconds, ncpu: 8, make -j8 >=20 > ( /usr/main-src/ has the source that the other buildkernel timings > were based on. ) >=20 >=20 > Looks like -mcpu=3Dcortex-a72 and -mcpu=3Dcortex-x1c+flagm are far = from > a good fit for buildkernel workloads to run under on the WDK23. = FreeBSD > defaults and -mcpu=3Dcortex-x1c+flagm+nolse+rcpc seems to be better = fits > for such use. >=20 >=20 > Note: This testing was in a ZFS context, using bectl to advantage, in > case that somehow matters. >=20 >=20 > For reference: >=20 > # grep mcpu=3D /usr/main-src/sys/arm64/conf/GENERIC-NODBG-CA78C > makeoptions CONF_CFLAGS=3D"-mcpu=3Dcortex-x1c+flagm+nolse+rcpc" >=20 > # grep mcpu=3D ~/src.configs/*CA78C-nodbg* > XCFLAGS+=3D -mcpu=3Dcortex-x1c+flagm+nolse+rcpc > XCXXFLAGS+=3D -mcpu=3Dcortex-x1c+flagm+nolse+rcpc > ACFLAGS.arm64cpuid.S+=3D -mcpu=3Dcortex-x1c > ACFLAGS.aesv8-armx.S+=3D -mcpu=3Dcortex-x1c > ACFLAGS.ghashv8-armx.S+=3D -mcpu=3Dcortex-x1c >=20 > # more /usr/local/etc/poudriere.d/main-CA78C-make.conf > CFLAGS+=3D -mcpu=3Dcortex-x1c+flagm+nolse+rcpc > CXXFLAGS+=3D -mcpu=3Dcortex-x1c+flagm+nolse+rcpc > CPPFLAGS+=3D -mcpu=3Dcortex-x1c+flagm+nolse+rcpc > RUSTFLAGS_CPU_FEATURES=3D -C target-cpu=3Dcortex-x1c -C = target-feature=3D+x1c,+flagm,-lse,+rcpc Note: RUSTFLAGS_CPU_FEATURES is something that I added to my environment to allow the experiment: # git -C /usr/ports/ diff Mk/Uses/cargo.mk diff --git a/Mk/Uses/cargo.mk b/Mk/Uses/cargo.mk index 50146372fee1..2f21453fd02b 100644 --- a/Mk/Uses/cargo.mk +++ b/Mk/Uses/cargo.mk @@ -145,7 +145,9 @@ WITH_LTO=3D yes . endif # Adjust -C target-cpu if -march/-mcpu is set by bsd.cpu.mk -. if ${ARCH} =3D=3D amd64 || ${ARCH} =3D=3D i386 +. if defined(RUSTFLAGS_CPU_FEATURES) +RUSTFLAGS+=3D ${RUSTFLAGS_CPU_FEATURES} +. elif ${ARCH} =3D=3D amd64 || ${ARCH} =3D=3D i386 RUSTFLAGS+=3D ${CFLAGS:M-march=3D*:S/-march=3D/-C target-cpu=3D/} . elif ${ARCH:Mpowerpc*} RUSTFLAGS+=3D ${CFLAGS:M-mcpu=3D*:S/-mcpu=3D/-C = target-cpu=3D/:S/power/pwr/} > diff --git a/secure/lib/libcrypto/Makefile = b/secure/lib/libcrypto/Makefile > index 8fde4f19d046..e13227d6450b 100644 > --- a/secure/lib/libcrypto/Makefile > +++ b/secure/lib/libcrypto/Makefile > @@ -22,7 +22,7 @@ SRCS+=3D mem.c mem_dbg.c mem_sec.c o_dir.c = o_fips.c o_fopen.c o_init.c > SRCS+=3D o_str.c o_time.c threads_pthread.c uid.c > .if defined(ASM_aarch64) > SRCS+=3D arm64cpuid.S armcap.c > -ACFLAGS.arm64cpuid.S=3D -march=3Darmv8-a+crypto > +ACFLAGS.arm64cpuid.S+=3D -march=3Darmv8-a+crypto > .elif defined(ASM_amd64) > SRCS+=3D x86_64cpuid.S > .elif defined(ASM_arm) > @@ -43,7 +43,7 @@ SRCS+=3D mem_clr.c > SRCS+=3D aes_cbc.c aes_cfb.c aes_ecb.c aes_ige.c aes_misc.c aes_ofb.c = aes_wrap.c > .if defined(ASM_aarch64) > SRCS+=3D aes_core.c aesv8-armx.S vpaes-armv8.S > -ACFLAGS.aesv8-armx.S=3D -march=3Darmv8-a+crypto > +ACFLAGS.aesv8-armx.S+=3D -march=3Darmv8-a+crypto > .elif defined(ASM_amd64) > SRCS+=3D aes_core.c aesni-mb-x86_64.S aesni-sha1-x86_64.S = aesni-sha256-x86_64.S > SRCS+=3D aesni-x86_64.S vpaes-x86_64.S > @@ -278,7 +278,7 @@ SRCS+=3D cbc128.c ccm128.c cfb128.c ctr128.c = cts128.c gcm128.c ocb128.c > SRCS+=3D ofb128.c wrap128.c xts128.c > .if defined(ASM_aarch64) > SRCS+=3D ghashv8-armx.S > -ACFLAGS.ghashv8-armx.S=3D -march=3Darmv8-a+crypto > +ACFLAGS.ghashv8-armx.S+=3D -march=3Darmv8-a+crypto =3D=3D=3D Mark Millard marklmi at yahoo.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?6196193E-4A75-464C-AB0B-AE2C3BC00D66>