From: David Laight <David.Laight@ACULAB.COM> To: 'Geert Uytterhoeven' <geert@linux-m68k.org>, Evan Green <evan@rivosinc.com> Cc: "Palmer Dabbelt" <palmer@rivosinc.com>, "Heiko Stuebner" <heiko@sntech.de>, "linux-doc@vger.kernel.org" <linux-doc@vger.kernel.org>, "Björn Töpel" <bjorn@rivosinc.com>, "Conor Dooley" <conor.dooley@microchip.com>, "Guo Ren" <guoren@kernel.org>, "Jisheng Zhang" <jszhang@kernel.org>, "linux-riscv@lists.infradead.org" <linux-riscv@lists.infradead.org>, "Jonathan Corbet" <corbet@lwn.net>, "Sia Jee Heng" <jeeheng.sia@starfivetech.com>, "Marc Zyngier" <maz@kernel.org>, "Masahiro Yamada" <masahiroy@kernel.org>, "Greentime Hu" <greentime.hu@sifive.com>, "Simon Hosie" <shosie@rivosinc.com>, "Andrew Jones" <ajones@ventanamicro.com>, "Albert Ou" <aou@eecs.berkeley.edu>, "Alexandre Ghiti" <alexghiti@rivosinc.com>, "Ley Foon Tan" <leyfoon.tan@starfivetech.com>, "Paul Walmsley" <paul.walmsley@sifive.com>, "Anup Patel" <apatel@ventanamicro.com>, "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>, "Xianting Tian" <xianting.tian@linux.alibaba.com>, "Palmer Dabbelt" <palmer@dabbelt.com>, "Andy Chiu" <andy.chiu@sifive.com> Subject: RE: [PATCH v4 1/2] RISC-V: Probe for unaligned access speed Date: Thu, 14 Sep 2023 08:46:54 +0000 [thread overview] Message-ID: <de95229a14614198894a8ce421c30d94@AcuMS.aculab.com> (raw) In-Reply-To: <CAMuHMdV594xA1UoTeVixpXm3i5LDFO5cT=dd_iRwWLwvxQctZg@mail.gmail.com> From: Geert Uytterhoeven > Sent: 14 September 2023 08:33 ... > > > rzfive: > > > cpu0: Ratio of byte access time to unaligned word access is > > > 1.05, unaligned accesses are fast > > > > Hrm, I'm a little surprised to be seeing this number come out so close > > to 1. If you reboot a few times, what kind of variance do you get on > > this? > > Rock-solid at 1.05 (even with increased resolution: 1.05853 on 3 tries) Would that match zero overhead unless the access crosses a cache line boundary? (I can't remember whether the test is using increasing addresses.) ... > > > vexriscv/orangecrab: > > > > > > cpu0: Ratio of byte access time to unaligned word access is > > > 0.00, unaligned accesses are slow > > cpu0: Ratio of byte access time to unaligned word access is 0.00417, > unaligned accesses are slow > > > > I am a bit surprised by the near-zero values. Are these expected? > > > > This could be expected, if firmware is trapping the unaligned accesses > > and coming out >100x slower than a native access. If you're interested > > in getting a little more resolution, you could try to print a few more > > decimal places with something like (sorry gmail mangles the whitespace > > on this): I'd expect one of three possible values: - 1.0x: Basically zero cost except for cache line/page boundaries. - ~2: Hardware does two reads and merges the values. - >100: Trap fixed up in software. I'd think the '2' case could be considered fast. You only need to time one access to see if it was a fault. David - Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)
WARNING: multiple messages have this Message-ID (diff)
From: David Laight <David.Laight@ACULAB.COM> To: 'Geert Uytterhoeven' <geert@linux-m68k.org>, Evan Green <evan@rivosinc.com> Cc: "Palmer Dabbelt" <palmer@rivosinc.com>, "Heiko Stuebner" <heiko@sntech.de>, "linux-doc@vger.kernel.org" <linux-doc@vger.kernel.org>, "Björn Töpel" <bjorn@rivosinc.com>, "Conor Dooley" <conor.dooley@microchip.com>, "Guo Ren" <guoren@kernel.org>, "Jisheng Zhang" <jszhang@kernel.org>, "linux-riscv@lists.infradead.org" <linux-riscv@lists.infradead.org>, "Jonathan Corbet" <corbet@lwn.net>, "Sia Jee Heng" <jeeheng.sia@starfivetech.com>, "Marc Zyngier" <maz@kernel.org>, "Masahiro Yamada" <masahiroy@kernel.org>, "Greentime Hu" <greentime.hu@sifive.com>, "Simon Hosie" <shosie@rivosinc.com>, "Andrew Jones" <ajones@ventanamicro.com>, "Albert Ou" <aou@eecs.berkeley.edu>, "Alexandre Ghiti" <alexghiti@rivosinc.com>, "Ley Foon Tan" <leyfoon.tan@starfivetech.com>, "Paul Walmsley" <paul.walmsley@sifive.com>, "Anup Patel" <apatel@ventanamicro.com>, "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>, "Xianting Tian" <xianting.tian@linux.alibaba.com>, "Palmer Dabbelt" <palmer@dabbelt.com>, "Andy Chiu" <andy.chiu@sifive.com> Subject: RE: [PATCH v4 1/2] RISC-V: Probe for unaligned access speed Date: Thu, 14 Sep 2023 08:46:54 +0000 [thread overview] Message-ID: <de95229a14614198894a8ce421c30d94@AcuMS.aculab.com> (raw) In-Reply-To: <CAMuHMdV594xA1UoTeVixpXm3i5LDFO5cT=dd_iRwWLwvxQctZg@mail.gmail.com> From: Geert Uytterhoeven > Sent: 14 September 2023 08:33 ... > > > rzfive: > > > cpu0: Ratio of byte access time to unaligned word access is > > > 1.05, unaligned accesses are fast > > > > Hrm, I'm a little surprised to be seeing this number come out so close > > to 1. If you reboot a few times, what kind of variance do you get on > > this? > > Rock-solid at 1.05 (even with increased resolution: 1.05853 on 3 tries) Would that match zero overhead unless the access crosses a cache line boundary? (I can't remember whether the test is using increasing addresses.) ... > > > vexriscv/orangecrab: > > > > > > cpu0: Ratio of byte access time to unaligned word access is > > > 0.00, unaligned accesses are slow > > cpu0: Ratio of byte access time to unaligned word access is 0.00417, > unaligned accesses are slow > > > > I am a bit surprised by the near-zero values. Are these expected? > > > > This could be expected, if firmware is trapping the unaligned accesses > > and coming out >100x slower than a native access. If you're interested > > in getting a little more resolution, you could try to print a few more > > decimal places with something like (sorry gmail mangles the whitespace > > on this): I'd expect one of three possible values: - 1.0x: Basically zero cost except for cache line/page boundaries. - ~2: Hardware does two reads and merges the values. - >100: Trap fixed up in software. I'd think the '2' case could be considered fast. You only need to time one access to see if it was a fault. David - Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales) _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv
next prev parent reply other threads:[~2023-09-14 8:47 UTC|newest] Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top 2023-08-18 19:41 [PATCH v4 0/2] RISC-V: Probe for misaligned access speed Evan Green 2023-08-18 19:41 ` Evan Green 2023-08-18 19:41 ` [PATCH v4 1/2] RISC-V: Probe for unaligned " Evan Green 2023-08-18 19:41 ` Evan Green 2023-09-13 12:36 ` Geert Uytterhoeven 2023-09-13 12:36 ` Geert Uytterhoeven 2023-09-13 17:46 ` Evan Green 2023-09-13 17:46 ` Evan Green 2023-09-14 7:32 ` Geert Uytterhoeven 2023-09-14 7:32 ` Geert Uytterhoeven 2023-09-14 8:46 ` David Laight [this message] 2023-09-14 8:46 ` David Laight 2023-09-14 15:01 ` Evan Green 2023-09-14 15:01 ` Evan Green 2023-09-14 15:55 ` David Laight 2023-09-14 15:55 ` David Laight 2023-09-14 16:36 ` Evan Green 2023-09-14 16:36 ` Evan Green 2023-09-15 7:57 ` David Laight 2023-09-15 7:57 ` David Laight 2023-09-15 16:47 ` Evan Green 2023-09-15 16:47 ` Evan Green 2023-10-19 6:37 ` Geert Uytterhoeven 2023-10-19 6:37 ` Geert Uytterhoeven 2023-10-19 7:51 ` Lad, Prabhakar 2023-10-19 7:51 ` Lad, Prabhakar 2023-08-18 19:41 ` [PATCH v4 2/2] RISC-V: alternative: Remove feature_probe_func Evan Green 2023-08-18 19:41 ` Evan Green 2023-08-30 20:30 ` [PATCH v4 0/2] RISC-V: Probe for misaligned access speed patchwork-bot+linux-riscv 2023-08-30 20:30 ` patchwork-bot+linux-riscv
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=de95229a14614198894a8ce421c30d94@AcuMS.aculab.com \ --to=david.laight@aculab.com \ --cc=ajones@ventanamicro.com \ --cc=alexghiti@rivosinc.com \ --cc=andy.chiu@sifive.com \ --cc=aou@eecs.berkeley.edu \ --cc=apatel@ventanamicro.com \ --cc=bjorn@rivosinc.com \ --cc=conor.dooley@microchip.com \ --cc=corbet@lwn.net \ --cc=evan@rivosinc.com \ --cc=geert@linux-m68k.org \ --cc=greentime.hu@sifive.com \ --cc=guoren@kernel.org \ --cc=heiko@sntech.de \ --cc=jeeheng.sia@starfivetech.com \ --cc=jszhang@kernel.org \ --cc=leyfoon.tan@starfivetech.com \ --cc=linux-doc@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-riscv@lists.infradead.org \ --cc=masahiroy@kernel.org \ --cc=maz@kernel.org \ --cc=palmer@dabbelt.com \ --cc=palmer@rivosinc.com \ --cc=paul.walmsley@sifive.com \ --cc=shosie@rivosinc.com \ --cc=xianting.tian@linux.alibaba.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.