From patchwork Sat May 13 05:19:06 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Noah Goldstein X-Patchwork-Id: 69294 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 1F7183856242 for ; Sat, 13 May 2023 05:19:41 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 1F7183856242 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1683955181; bh=M2SzAruT1I0fQTFLwOPkIqsPrp7cs3odnzKhyOeCKNs=; h=To:Cc:Subject:Date:In-Reply-To:References:List-Id: List-Unsubscribe:List-Archive:List-Post:List-Help:List-Subscribe: From:Reply-To:From; b=YgPxMJnDuAI0RnFbhtqC/oV1VbbYb53JHipOo+pmczpOyZt8gqKgrrLUKn66wKdTh AoPNtnUa5HqV3wvm6oWPQqhmFD5Fa+m8bC55yUpfFPFMIc8UNXkGJJnbtppCTo/+iQ kZFWngQZSAvIy+1LkX4CkDk37bJ54C+hcW0K/2f0= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from mail-oi1-x234.google.com (mail-oi1-x234.google.com [IPv6:2607:f8b0:4864:20::234]) by sourceware.org (Postfix) with ESMTPS id F248A385696B for ; Sat, 13 May 2023 05:19:12 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org F248A385696B Received: by mail-oi1-x234.google.com with SMTP id 5614622812f47-39420384cc4so2759836b6e.0 for ; Fri, 12 May 2023 22:19:12 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1683955152; x=1686547152; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=M2SzAruT1I0fQTFLwOPkIqsPrp7cs3odnzKhyOeCKNs=; b=UM7FHpKkqQn5E3fAENi5C77XXMIC0jm63Jyykv86VRRSQ/A/08ThLv2bFqlC1yosAB 3nzijdEIK9qA3bc10IRDNihiLXDKy89wwIHSe6JNoRLWSDF0m5DMJc/t/g7wxzJWna2Y KSqR3B38IK1ivpn35wO0liJbiu+MIuVSNxUa00wvCIS9W/KdquAbKJwR3sb/vq2hAVqx bAqRDGVcZcJemF7XEb0LbqGBIpC9LkKMpmTTXSRZiNeQZf6508mnFxhAOpgsQUsKdM8c 45/P+PfQ0B9/KsDMTlevj364fSp+EKHa5Fc4mwrcR3g5oVk13cWtFrsU9ixpckf2riNV Tviw== X-Gm-Message-State: AC+VfDxp6C7v7WBQFmzE8V67vykvsdJ/Gm9jz+lfuWhHI4fnyxbwldra k3WD/Q66gTWSoiqdKStgHbh27nE1pM4= X-Google-Smtp-Source: ACHHUZ6I7lwDl4UnXLVQUnXrZRU5Fgj0yPvAN6xlT6Q+ZCqIAMyQQEd5z14wiLXVGXSQfbix802Z+w== X-Received: by 2002:a05:6808:690:b0:38e:8275:fdf8 with SMTP id k16-20020a056808069000b0038e8275fdf8mr7379496oig.34.1683955151907; Fri, 12 May 2023 22:19:11 -0700 (PDT) Received: from noahgold-desk.lan (2603-8080-1301-76c6-16d7-947e-b630-b39b.res6.spectrum.com. [2603:8080:1301:76c6:16d7:947e:b630:b39b]) by smtp.gmail.com with ESMTPSA id p5-20020acad805000000b003907dcabf3bsm5384734oig.36.2023.05.12.22.19.10 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 12 May 2023 22:19:11 -0700 (PDT) To: libc-alpha@sourceware.org Cc: goldstein.w.n@gmail.com, hjl.tools@gmail.com, carlos@systemhalted.org Subject: [PATCH v9 3/3] x86: Make the divisor in setting `non_temporal_threshold` cpu specific Date: Sat, 13 May 2023 00:19:06 -0500 Message-Id: <20230513051906.1287611-3-goldstein.w.n@gmail.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230513051906.1287611-1-goldstein.w.n@gmail.com> References: <20230424050329.1501348-1-goldstein.w.n@gmail.com> <20230513051906.1287611-1-goldstein.w.n@gmail.com> MIME-Version: 1.0 X-Spam-Status: No, score=-12.2 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, FREEMAIL_FROM, GIT_PATCH_0, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Noah Goldstein via Libc-alpha From: Noah Goldstein Reply-To: Noah Goldstein Errors-To: libc-alpha-bounces+patchwork=sourceware.org@sourceware.org Sender: "Libc-alpha" Different systems prefer a different divisors. From benchmarks[1] so far the following divisors have been found: ICX : 2 SKX : 2 BWD : 8 For Intel, we are generalizing that BWD and older prefers 8 as a divisor, and SKL and newer prefers 2. This number can be further tuned as benchmarks are run. [1]: https://github.com/goldsteinn/memcpy-nt-benchmarks --- sysdeps/x86/cpu-features.c | 27 +++++++++++++++++-------- sysdeps/x86/dl-cacheinfo.h | 32 ++++++++++++++++++------------ sysdeps/x86/include/cpu-features.h | 3 +++ 3 files changed, 41 insertions(+), 21 deletions(-) diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 29b8c8c133..ba789d6fc1 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -635,6 +635,7 @@ init_cpu_features (struct cpu_features *cpu_features) unsigned int stepping = 0; enum cpu_features_kind kind; + cpu_features->cachesize_non_temporal_divisor = 4; #if !HAS_CPUID if (__get_cpuid_max (0, 0) == 0) { @@ -714,12 +715,13 @@ init_cpu_features (struct cpu_features *cpu_features) /* Bigcore/Default Tuning. */ default: + default_tuning: /* Unknown family 0x06 processors. Assuming this is one of Core i3/i5/i7 processors if AVX is available. */ if (!CPU_FEATURES_CPU_P (cpu_features, AVX)) break; - case INTEL_BIGCORE_NEHALEM: - case INTEL_BIGCORE_WESTMERE: + + enable_modern_features: /* Rep string instructions, unaligned load, unaligned copy, and pminub are fast on Intel Core i3, i5 and i7. */ cpu_features->preferred[index_arch_Fast_Rep_String] @@ -728,12 +730,20 @@ init_cpu_features (struct cpu_features *cpu_features) | bit_arch_Prefer_PMINUB_for_stringop); break; - /* - Default tuned Bigcore microarch. + case INTEL_BIGCORE_NEHALEM: + case INTEL_BIGCORE_WESTMERE: + /* Older CPUs prefer non-temporal stores at lower threshold. */ + cpu_features->cachesize_non_temporal_divisor = 8; + goto enable_modern_features; + + /* Default tuned Bigcore microarch. */ case INTEL_BIGCORE_SANDYBRIDGE: case INTEL_BIGCORE_IVYBRIDGE: case INTEL_BIGCORE_HASWELL: case INTEL_BIGCORE_BROADWELL: + cpu_features->cachesize_non_temporal_divisor = 8; + goto default_tuning; + case INTEL_BIGCORE_SKYLAKE: case INTEL_BIGCORE_KABYLAKE: case INTEL_BIGCORE_COMETLAKE: @@ -749,13 +759,14 @@ init_cpu_features (struct cpu_features *cpu_features) case INTEL_BIGCORE_SAPPHIRERAPIDS: case INTEL_BIGCORE_EMERALDRAPIDS: case INTEL_BIGCORE_GRANITERAPIDS: - */ + cpu_features->cachesize_non_temporal_divisor = 2; + goto default_tuning; - /* - Default tuned Mixed (bigcore + atom SOC). + /* Default tuned Mixed (bigcore + atom SOC). */ case INTEL_MIXED_LAKEFIELD: case INTEL_MIXED_ALDERLAKE: - */ + cpu_features->cachesize_non_temporal_divisor = 2; + goto default_tuning; } /* Disable TSX on some processors to avoid TSX on kernels that diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h index 4a1a5423ff..864b00a521 100644 --- a/sysdeps/x86/dl-cacheinfo.h +++ b/sysdeps/x86/dl-cacheinfo.h @@ -738,19 +738,25 @@ dl_init_cacheinfo (struct cpu_features *cpu_features) cpu_features->level3_cache_linesize = level3_cache_linesize; cpu_features->level4_cache_size = level4_cache_size; - /* The default setting for the non_temporal threshold is 1/4 of size - of the chip's cache. For most Intel and AMD processors with an - initial release date between 2017 and 2023, a thread's typical - share of the cache is from 18-64MB. Using the 1/4 L3 is meant to - estimate the point where non-temporal stores begin outcompeting - REP MOVSB. As well the point where the fact that non-temporal - stores are forced back to main memory would already occurred to the - majority of the lines in the copy. Note, concerns about the - entire L3 cache being evicted by the copy are mostly alleviated - by the fact that modern HW detects streaming patterns and - provides proper LRU hints so that the maximum thrashing - capped at 1/associativity. */ - unsigned long int non_temporal_threshold = shared / 4; + unsigned long int cachesize_non_temporal_divisor + = cpu_features->cachesize_non_temporal_divisor; + if (cachesize_non_temporal_divisor <= 0) + cachesize_non_temporal_divisor = 4; + + /* The default setting for the non_temporal threshold is [1/2, 1/8] of size + of the chip's cache (depending on `cachesize_non_temporal_divisor` which + is microarch specific. The defeault is 1/4). For most Intel and AMD + processors with an initial release date between 2017 and 2023, a thread's + typical share of the cache is from 18-64MB. Using a reasonable size + fraction of L3 is meant to estimate the point where non-temporal stores + begin outcompeting REP MOVSB. As well the point where the fact that + non-temporal stores are forced back to main memory would already occurred + to the majority of the lines in the copy. Note, concerns about the entire + L3 cache being evicted by the copy are mostly alleviated by the fact that + modern HW detects streaming patterns and provides proper LRU hints so that + the maximum thrashing capped at 1/associativity. */ + unsigned long int non_temporal_threshold + = shared / cachesize_non_temporal_divisor; /* If no ERMS, we use the per-thread L3 chunking. Normal cacheable stores run a higher risk of actually thrashing the cache as they don't have a HW LRU hint. As well, there performance in highly parallel situations is diff --git a/sysdeps/x86/include/cpu-features.h b/sysdeps/x86/include/cpu-features.h index 40b8129d6a..f5b9dd54fe 100644 --- a/sysdeps/x86/include/cpu-features.h +++ b/sysdeps/x86/include/cpu-features.h @@ -915,6 +915,9 @@ struct cpu_features unsigned long int shared_cache_size; /* Threshold to use non temporal store. */ unsigned long int non_temporal_threshold; + /* When no user non_temporal_threshold is specified. We default to + cachesize / cachesize_non_temporal_divisor. */ + unsigned long int cachesize_non_temporal_divisor; /* Threshold to use "rep movsb". */ unsigned long int rep_movsb_threshold; /* Threshold to stop using "rep movsb". */