From patchwork Sun Jan 9 12:29:47 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Noah Goldstein X-Patchwork-Id: 49768 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 6296B388A02B for ; Sun, 9 Jan 2022 12:32:50 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 6296B388A02B DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1641731570; bh=bY2VZ0Y5BMIhyq+ySmKAWBqkWf2JOc4fO3B1Z6wOFUU=; h=To:Subject:Date:In-Reply-To:References:List-Id:List-Unsubscribe: List-Archive:List-Post:List-Help:List-Subscribe:From:Reply-To: From; b=TennBGsgeGukHm5sO630TNoog/9aEtk+JlXNb9kNJeywOAoubRLN9FkoZ50HVXy2q Dz/g7WRCE5XrYXhT8I9vM/LUgZcS9mfs2uB0lqqOj0do/EjHibMMUofsW5bLXXyeWJ aZLHvZ79PrxvtpB5cMNYXgwByL+cH8bRJvHY2jIY= X-Original-To: libc-alpha@sourceware.org Delivered-To: libc-alpha@sourceware.org Received: from mail-pj1-x102f.google.com (mail-pj1-x102f.google.com [IPv6:2607:f8b0:4864:20::102f]) by sourceware.org (Postfix) with ESMTPS id 6F52D388A012 for ; Sun, 9 Jan 2022 12:30:18 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 6F52D388A012 Received: by mail-pj1-x102f.google.com with SMTP id lr15-20020a17090b4b8f00b001b19671cbebso13199368pjb.1 for ; Sun, 09 Jan 2022 04:30:18 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=bY2VZ0Y5BMIhyq+ySmKAWBqkWf2JOc4fO3B1Z6wOFUU=; b=ce+uskk+tGzTZWhi3BBZaXspgvFrrALbBfsZai20PPx04RvgShSAIyN/ovbQzgO05k W5n8KdVC4LVgNsMPgmaENRy3nujSeDuSf4csQndgkOSYy3YvnIVDm/c/1aK6jo8nxL9y VLR1naR3GqYXXemQx/wsa0jpcLOeMGIoUdcbSqqgPdBezsJI4dL4TgcCgpx5Ztdpojzv pN6cULBkxcVjQO+40W8EEypTWXBKt1guEpGHlAg54+I0C8xd1lQLliyZG8GEggZMZnhv H6JZ1a+iLbwnfUwjPbGHjP6EcobRgUV7G9pDvByUrzfcwfzkk6j4KkpuURDRd3xyHlVy Nvag== X-Gm-Message-State: AOAM5307dsDw99ty1B0hy09avg+vfww6BkQnpCCOKzSQVoI8cQXimGQD gDyeiTEyCXVr/qfyMgG3BzhdfeJP3OU= X-Google-Smtp-Source: ABdhPJwGcCJYxUsPWMykfKpm4TlusKdXI9k6bLqrVy53HSyH1+/9uJJV5eox82K+/q4SnYZcO8W2Lg== X-Received: by 2002:a17:902:b48a:b0:149:5454:193e with SMTP id y10-20020a170902b48a00b001495454193emr68073449plr.131.1641731417375; Sun, 09 Jan 2022 04:30:17 -0800 (PST) Received: from localhost.localdomain (c-73-202-60-99.hsd1.ca.comcast.net. [73.202.60.99]) by smtp.googlemail.com with ESMTPSA id o27sm2979055pgm.1.2022.01.09.04.30.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 09 Jan 2022 04:30:17 -0800 (PST) To: libc-alpha@sourceware.org Subject: [PATCH v1 5/5] benchtests: Add more coverage for strcmp and strncmp benchmarks Date: Sun, 9 Jan 2022 06:29:47 -0600 Message-Id: <20220109122946.2754917-5-goldstein.w.n@gmail.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220109122946.2754917-1-goldstein.w.n@gmail.com> References: <20220109122946.2754917-1-goldstein.w.n@gmail.com> MIME-Version: 1.0 X-Spam-Status: No, score=-11.9 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 autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) 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" Add more small and medium sized tests for strcmp and strncmp. As well for strcmp add option for more direct control of alignment. Previously alignment was being pushed to the end of the page. While this is the most difficult case to implement, it is far from the common case and so shouldn't be the only benchmark. Signed-off-by: Noah Goldstein --- benchtests/bench-strcmp.c | 142 ++++++++++++++++++++++++++----------- benchtests/bench-strncmp.c | 110 ++++++++++++++++++++-------- 2 files changed, 183 insertions(+), 69 deletions(-) diff --git a/benchtests/bench-strcmp.c b/benchtests/bench-strcmp.c index 387e76fcfb..3a60edfb15 100644 --- a/benchtests/bench-strcmp.c +++ b/benchtests/bench-strcmp.c @@ -99,8 +99,8 @@ do_one_test (json_ctx_t *json_ctx, impl_t *impl, } static void -do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len, int - max_char, int exp_result) +do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len, + int max_char, int exp_result, int at_end) { size_t i; @@ -109,19 +109,28 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len, int if (len == 0) return; - align1 &= 63; + align1 &= ~(CHARBYTES - 1); + align2 &= ~(CHARBYTES - 1); + + align1 &= (getpagesize () - 1); if (align1 + (len + 1) * CHARBYTES >= page_size) return; - align2 &= 63; + align2 &= (getpagesize () - 1); if (align2 + (len + 1) * CHARBYTES >= page_size) return; /* Put them close to the end of page. */ - i = align1 + CHARBYTES * (len + 2); - s1 = (CHAR *) (buf1 + ((page_size - i) / 16 * 16) + align1); - i = align2 + CHARBYTES * (len + 2); - s2 = (CHAR *) (buf2 + ((page_size - i) / 16 * 16) + align2); + if (at_end) + { + i = align1 + CHARBYTES * (len + 2); + align1 = ((page_size - i) / 16 * 16) + align1; + i = align2 + CHARBYTES * (len + 2); + align2 = ((page_size - i) / 16 * 16) + align2; + } + + s1 = (CHAR *)(buf1 + align1); + s2 = (CHAR *)(buf2 + align2); for (i = 0; i < len; i++) s1[i] = s2[i] = 1 + (23 << ((CHARBYTES - 1) * 8)) * i % max_char; @@ -132,9 +141,9 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len, int s2[len - 1] -= exp_result; json_element_object_begin (json_ctx); - json_attr_uint (json_ctx, "length", (double) len); - json_attr_uint (json_ctx, "align1", (double) align1); - json_attr_uint (json_ctx, "align2", (double) align2); + json_attr_uint (json_ctx, "length", (double)len); + json_attr_uint (json_ctx, "align1", (double)align1); + json_attr_uint (json_ctx, "align2", (double)align2); json_array_begin (json_ctx, "timings"); FOR_EACH_IMPL (impl, 0) @@ -202,7 +211,8 @@ int test_main (void) { json_ctx_t json_ctx; - size_t i; + size_t i, j, k; + size_t pg_sz = getpagesize (); test_init (); @@ -221,36 +231,88 @@ test_main (void) json_array_end (&json_ctx); json_array_begin (&json_ctx, "results"); - - for (i = 1; i < 32; ++i) - { - do_test (&json_ctx, CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, 0); - do_test (&json_ctx, CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, 1); - do_test (&json_ctx, CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, -1); - } - - for (i = 1; i < 10 + CHARBYTESLOG; ++i) + for (k = 0; k < 2; ++k) { - do_test (&json_ctx, 0, 0, 2 << i, MIDCHAR, 0); - do_test (&json_ctx, 0, 0, 2 << i, LARGECHAR, 0); - do_test (&json_ctx, 0, 0, 2 << i, MIDCHAR, 1); - do_test (&json_ctx, 0, 0, 2 << i, LARGECHAR, 1); - do_test (&json_ctx, 0, 0, 2 << i, MIDCHAR, -1); - do_test (&json_ctx, 0, 0, 2 << i, LARGECHAR, -1); - do_test (&json_ctx, 0, CHARBYTES * i, 2 << i, MIDCHAR, 1); - do_test (&json_ctx, CHARBYTES * i, CHARBYTES * (i + 1), 2 << i, LARGECHAR, 1); + for (i = 1; i < 32; ++i) + { + do_test (&json_ctx, CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, 0, k); + do_test (&json_ctx, CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, 1, k); + do_test (&json_ctx, CHARBYTES * i, CHARBYTES * i, i, MIDCHAR, -1, k); + } + + for (i = 1; i <= 8192;) + { + /* No page crosses. */ + do_test (&json_ctx, 0, 0, i, MIDCHAR, 0, k); + do_test (&json_ctx, i * CHARBYTES, 0, i, MIDCHAR, 0, k); + do_test (&json_ctx, 0, i * CHARBYTES, i, MIDCHAR, 0, k); + + /* False page crosses. */ + do_test (&json_ctx, pg_sz / 2, pg_sz / 2 - CHARBYTES, i, MIDCHAR, 0, + k); + do_test (&json_ctx, pg_sz / 2 - CHARBYTES, pg_sz / 2, i, MIDCHAR, 0, + k); + + do_test (&json_ctx, pg_sz - (i * CHARBYTES), 0, i, MIDCHAR, 0, k); + do_test (&json_ctx, 0, pg_sz - (i * CHARBYTES), i, MIDCHAR, 0, k); + + /* Real page cross. */ + for (j = 16; j < 128; j += 16) + { + do_test (&json_ctx, pg_sz - j, 0, i, MIDCHAR, 0, k); + do_test (&json_ctx, 0, pg_sz - j, i, MIDCHAR, 0, k); + + do_test (&json_ctx, pg_sz - j, pg_sz - j / 2, i, MIDCHAR, 0, k); + do_test (&json_ctx, pg_sz - j / 2, pg_sz - j, i, MIDCHAR, 0, k); + } + + if (i < 32) + { + ++i; + } + else if (i < 160) + { + i += 8; + } + else if (i < 512) + { + i += 32; + } + else + { + i *= 2; + } + } + + for (i = 1; i < 10 + CHARBYTESLOG; ++i) + { + do_test (&json_ctx, 0, 0, 2 << i, MIDCHAR, 0, k); + do_test (&json_ctx, 0, 0, 2 << i, LARGECHAR, 0, k); + do_test (&json_ctx, 0, 0, 2 << i, MIDCHAR, 1, k); + do_test (&json_ctx, 0, 0, 2 << i, LARGECHAR, 1, k); + do_test (&json_ctx, 0, 0, 2 << i, MIDCHAR, -1, k); + do_test (&json_ctx, 0, 0, 2 << i, LARGECHAR, -1, k); + do_test (&json_ctx, 0, CHARBYTES * i, 2 << i, MIDCHAR, 1, k); + do_test (&json_ctx, CHARBYTES * i, CHARBYTES * (i + 1), 2 << i, + LARGECHAR, 1, k); + } + + for (i = 1; i < 8; ++i) + { + do_test (&json_ctx, CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, + MIDCHAR, 0, k); + do_test (&json_ctx, 2 * CHARBYTES * i, CHARBYTES * i, 8 << i, + LARGECHAR, 0, k); + do_test (&json_ctx, CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, + MIDCHAR, 1, k); + do_test (&json_ctx, 2 * CHARBYTES * i, CHARBYTES * i, 8 << i, + LARGECHAR, 1, k); + do_test (&json_ctx, CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, + MIDCHAR, -1, k); + do_test (&json_ctx, 2 * CHARBYTES * i, CHARBYTES * i, 8 << i, + LARGECHAR, -1, k); + } } - - for (i = 1; i < 8; ++i) - { - do_test (&json_ctx, CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, MIDCHAR, 0); - do_test (&json_ctx, 2 * CHARBYTES * i, CHARBYTES * i, 8 << i, LARGECHAR, 0); - do_test (&json_ctx, CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, MIDCHAR, 1); - do_test (&json_ctx, 2 * CHARBYTES * i, CHARBYTES * i, 8 << i, LARGECHAR, 1); - do_test (&json_ctx, CHARBYTES * i, 2 * CHARBYTES * i, 8 << i, MIDCHAR, -1); - do_test (&json_ctx, 2 * CHARBYTES * i, CHARBYTES * i, 8 << i, LARGECHAR, -1); - } - do_test_page_boundary (&json_ctx); json_array_end (&json_ctx); diff --git a/benchtests/bench-strncmp.c b/benchtests/bench-strncmp.c index b7a01fde64..6673a53521 100644 --- a/benchtests/bench-strncmp.c +++ b/benchtests/bench-strncmp.c @@ -150,43 +150,43 @@ do_test (json_ctx_t *json_ctx, size_t align1, size_t align2, size_t len, size_t if (n == 0) return; - align1 &= 63; + align1 &= getpagesize () - 1; if (align1 + (n + 1) * CHARBYTES >= page_size) return; - align2 &= 7; + align2 &= getpagesize () - 1; if (align2 + (n + 1) * CHARBYTES >= page_size) return; json_element_object_begin (json_ctx); - json_attr_uint (json_ctx, "strlen", (double) len); - json_attr_uint (json_ctx, "len", (double) n); - json_attr_uint (json_ctx, "align1", (double) align1); - json_attr_uint (json_ctx, "align2", (double) align2); + json_attr_uint (json_ctx, "strlen", (double)len); + json_attr_uint (json_ctx, "len", (double)n); + json_attr_uint (json_ctx, "align1", (double)align1); + json_attr_uint (json_ctx, "align2", (double)align2); json_array_begin (json_ctx, "timings"); FOR_EACH_IMPL (impl, 0) - { - alloc_bufs (); - s1 = (CHAR *) (buf1 + align1); - s2 = (CHAR *) (buf2 + align2); - - for (i = 0; i < n; i++) - s1[i] = s2[i] = 1 + (23 << ((CHARBYTES - 1) * 8)) * i % max_char; - - s1[n] = 24 + exp_result; - s2[n] = 23; - s1[len] = 0; - s2[len] = 0; - if (exp_result < 0) - s2[len] = 32; - else if (exp_result > 0) - s1[len] = 64; - if (len >= n) - s2[n - 1] -= exp_result; + { + alloc_bufs (); + s1 = (CHAR *)(buf1 + align1); + s2 = (CHAR *)(buf2 + align2); + + for (i = 0; i < n; i++) + s1[i] = s2[i] = 1 + (23 << ((CHARBYTES - 1) * 8)) * i % max_char; + + s1[n] = 24 + exp_result; + s2[n] = 23; + s1[len] = 0; + s2[len] = 0; + if (exp_result < 0) + s2[len] = 32; + else if (exp_result > 0) + s1[len] = 64; + if (len >= n) + s2[n - 1] -= exp_result; - do_one_test (json_ctx, impl, s1, s2, n, exp_result); - } + do_one_test (json_ctx, impl, s1, s2, n, exp_result); + } json_array_end (json_ctx); json_element_object_end (json_ctx); @@ -319,7 +319,8 @@ int test_main (void) { json_ctx_t json_ctx; - size_t i; + size_t i, j, len; + size_t pg_sz = getpagesize (); test_init (); @@ -334,12 +335,12 @@ test_main (void) json_array_begin (&json_ctx, "ifuncs"); FOR_EACH_IMPL (impl, 0) - json_element_string (&json_ctx, impl->name); + json_element_string (&json_ctx, impl->name); json_array_end (&json_ctx); json_array_begin (&json_ctx, "results"); - for (i =0; i < 16; ++i) + for (i = 0; i < 16; ++i) { do_test (&json_ctx, 0, 0, 8, i, 127, 0); do_test (&json_ctx, 0, 0, 8, i, 127, -1); @@ -361,6 +362,57 @@ test_main (void) do_test (&json_ctx, i, 3 * i, 8, i, 255, -1); } + for (len = 0; len <= 128; len += 64) + { + for (i = 1; i <= 8192;) + { + /* No page crosses. */ + do_test (&json_ctx, 0, 0, i, i + len, 127, 0); + do_test (&json_ctx, i * CHARBYTES, 0, i, i + len, 127, 0); + do_test (&json_ctx, 0, i * CHARBYTES, i, i + len, 127, 0); + + /* False page crosses. */ + do_test (&json_ctx, pg_sz / 2, pg_sz / 2 - CHARBYTES, i, i + len, + 127, 0); + do_test (&json_ctx, pg_sz / 2 - CHARBYTES, pg_sz / 2, i, i + len, + 127, 0); + + do_test (&json_ctx, pg_sz - (i * CHARBYTES), 0, i, i + len, 127, + 0); + do_test (&json_ctx, 0, pg_sz - (i * CHARBYTES), i, i + len, 127, + 0); + + /* Real page cross. */ + for (j = 16; j < 128; j += 16) + { + do_test (&json_ctx, pg_sz - j, 0, i, i + len, 127, 0); + do_test (&json_ctx, 0, pg_sz - j, i, i + len, 127, 0); + + do_test (&json_ctx, pg_sz - j, pg_sz - j / 2, i, i + len, + 127, 0); + do_test (&json_ctx, pg_sz - j / 2, pg_sz - j, i, i + len, + 127, 0); + } + + if (i < 32) + { + ++i; + } + else if (i < 160) + { + i += 8; + } + else if (i < 256) + { + i += 32; + } + else + { + i *= 2; + } + } + } + for (i = 1; i < 8; ++i) { do_test (&json_ctx, 0, 0, 8 << i, 16 << i, 127, 0);