From nobody Mon Feb 9 20:32:47 2026 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass header.i=@intel.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass(p=none dis=none) header.from=intel.com ARC-Seal: i=1; a=rsa-sha256; t=1660816528; cv=none; d=zohomail.com; s=zohoarc; b=GEeWRfVhnHczkExRuhap1c/IKs6TKhpru5E5CZ/7/ch7R/fjX6A2bw4DrMla2ksb+66uyHZWmL52Rp41nobMEH1GTAtcrM6m59YAsV20IDOCWxHpkvHGTM8RinTYw0Xr0x4jN5w5jqq+AZ7BFUYknGFn4XQA9IN/wN5YVGIunio= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1660816528; h=Content-Transfer-Encoding:Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=S0NZ/kzFXKGrrutaJvNN4EoGF1s+DCdy6rMCUPuqaXc=; b=GqQfH9Vc8TMA7CMfeFn0uJMZSLlb9X6yW7InVWz8S7t6tCv6x5GFZsXFjBc3vsqPpY3vf0Uw5nR4wpSqD1shUp1Yy13VfWAn2ZuGDZ1k9h6AztABErR2FT82FeIVeSdX8TRrXMhJhY7j0AKhdKbwq1cT/T0ewdHU7zAOlYNSj9U= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass header.i=@intel.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1660816528952951.6680856613378; Thu, 18 Aug 2022 02:55:28 -0700 (PDT) Received: from localhost ([::1]:51602 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1oOcFL-0007d7-ST for importer@patchew.org; Thu, 18 Aug 2022 05:55:27 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:55296) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1oObwl-0007nJ-9O for qemu-devel@nongnu.org; Thu, 18 Aug 2022 05:36:22 -0400 Received: from mga14.intel.com ([192.55.52.115]:6877) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1oObwi-0003zT-3s for qemu-devel@nongnu.org; Thu, 18 Aug 2022 05:36:14 -0400 Received: from orsmga006.jf.intel.com ([10.7.209.51]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 18 Aug 2022 02:36:10 -0700 Received: from xuling-b360m-d3h.sh.intel.com ([10.239.82.110]) by orsmga006.jf.intel.com with ESMTP; 18 Aug 2022 02:36:08 -0700 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1660815372; x=1692351372; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=8u59AutCz/2JxSxCAgBK75k3MJzrZ4K4Arv1S6Pc7Yg=; b=NMuSWlnE3fYsVHUvERD2zlNE1A+/OB1mn8a1Cf1PycMRnd1bs1vcoILA 5jUHygH2lmPLY8etvN7l8LydwbaJw54dmyJAAAze9qpQef5g1SJw8pt9H Kcv4jREg2To1wrQ8wItX8uTBPil0zC0ENi7z3xHUvWbJL0W3YCA3tsAH4 63x93qqpYyf5ifRlMLnjPeSqOS6FVfpSwVOJiNbsS7Nns1Y2HRIkPFLzj lI6TsSzntcrLWChN+yEONIB7ZbyKI7g0DyROdnTh1Vbupdir68mXC5BNn NdQLtxfmCENyFpddmloxPjDvA2EAxjIh5PmB916BnTVZrR9xysbRLCkjn g==; X-IronPort-AV: E=McAfee;i="6500,9779,10442"; a="292713294" X-IronPort-AV: E=Sophos;i="5.93,246,1654585200"; d="scan'208";a="292713294" X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.93,246,1654585200"; d="scan'208";a="584141641" From: ling xu To: qemu-devel@nongnu.org Cc: quintela@redhat.com, dgilbert@redhat.com, ling xu , Zhou Zhao , Jun Jin Subject: [PATCH v5 2/2] Test code and benchmark code Date: Thu, 18 Aug 2022 17:35:59 +0800 Message-Id: <20220818093559.2342594-3-ling1.xu@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220818093559.2342594-1-ling1.xu@intel.com> References: <20220818093559.2342594-1-ling1.xu@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=192.55.52.115; envelope-from=ling1.xu@intel.com; helo=mga14.intel.com X-Spam_score_int: -71 X-Spam_score: -7.2 X-Spam_bar: ------- X-Spam_report: (-7.2 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.082, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_HI=-5, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail-DKIM: pass (identity @intel.com) X-ZM-MESSAGEID: 1660816531584100001 Content-Type: text/plain; charset="utf-8" Test code in test-xbzrle.c, benchmark code in xbzrle-bench.c for performance benchmarking. Signed-off-by: ling xu Co-authored-by: Zhou Zhao Co-authored-by: Jun Jin --- tests/bench/meson.build | 4 + tests/bench/xbzrle-bench.c | 468 +++++++++++++++++++++++++++++++++++++ tests/unit/test-xbzrle.c | 39 +++- 3 files changed, 506 insertions(+), 5 deletions(-) create mode 100644 tests/bench/xbzrle-bench.c diff --git a/tests/bench/meson.build b/tests/bench/meson.build index 279a8fcc33..daefead58d 100644 --- a/tests/bench/meson.build +++ b/tests/bench/meson.build @@ -3,6 +3,10 @@ qht_bench =3D executable('qht-bench', sources: 'qht-bench.c', dependencies: [qemuutil]) =20 +xbzrle_bench =3D executable('xbzrle-bench', + sources: 'xbzrle-bench.c', + dependencies: [qemuutil,migration]) + executable('atomic_add-bench', sources: files('atomic_add-bench.c'), dependencies: [qemuutil], diff --git a/tests/bench/xbzrle-bench.c b/tests/bench/xbzrle-bench.c new file mode 100644 index 0000000000..6ffac62e15 --- /dev/null +++ b/tests/bench/xbzrle-bench.c @@ -0,0 +1,468 @@ +/* + * Xor Based Zero Run Length Encoding unit tests. + * + * Copyright 2013 Red Hat, Inc. and/or its affiliates + * + * Authors: + * Orit Wasserman + * + * This work is licensed under the terms of the GNU GPL, version 2 or late= r. + * See the COPYING file in the top-level directory. + * + */ +#include "qemu/osdep.h" +#include "qemu/cutils.h" +#include "../migration/xbzrle.h" + +#define XBZRLE_PAGE_SIZE 4096 + +//int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int, +// uint8_t *, int) =3D xbzrle_encode_buffer; +#if defined(CONFIG_AVX512BW_OPT) +static bool is_cpu_support_avx512bw; +#include "qemu/cpuid.h" +static void __attribute__((constructor)) init_cpu_flag(void) +{ + unsigned max =3D __get_cpuid_max(0, NULL); + int a, b, c, d; + is_cpu_support_avx512bw =3D false; + if (max >=3D 1) { + __cpuid(1, a, b, c, d); + /* We must check that AVX is not just available, but usable. */ + if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >=3D 7) { + int bv; + __asm("xgetbv" : "=3Da"(bv), "=3Dd"(d) : "c"(0)); + __cpuid_count(7, 0, a, b, c, d); + /* 0xe6: + * XCR0[7:5] =3D 111b (OPMASK state, upper 256-bit of ZMM0-ZMM= 15 + * and ZMM16-ZMM31 state are enabled by OS) + * XCR0[2:1] =3D 11b (XMM state and YMM state are enabled by O= S) + */ + if ((bv & 0xe6) =3D=3D 0xe6 && (b & bit_AVX512BW)) { + //xbzrle_encode_buffer_func =3D xbzrle_encode_buffer_avx51= 2; + is_cpu_support_avx512bw =3D true; + } + } + } + return ; +} +#endif + +struct ResTime{ + float t_raw; + float t_512; +}; + +static void encode_decode_zero(struct ResTime *res) +{ + uint8_t *buffer =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + int i =3D 0; + int dlen =3D 0, dlen512 =3D 0; + int diff_len =3D g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); + + for (i =3D diff_len; i > 0; i--) { + buffer[1000 + i] =3D i; + buffer512[1000 + i] =3D i; + } + + buffer[1000 + diff_len + 3] =3D 103; + buffer[1000 + diff_len + 5] =3D 105; + + buffer512[1000 + diff_len + 3] =3D 103; + buffer512[1000 + diff_len + 5] =3D 105; + + /* encode zero page */ + time_t t_start, t_end, t_start512, t_end512; + t_start =3D clock(); + dlen =3D xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, compre= ssed, + XBZRLE_PAGE_SIZE); + t_end =3D clock(); + float time_val =3D difftime(t_end, t_start); + g_assert(dlen =3D=3D 0); + + t_start512 =3D clock(); + dlen512 =3D xbzrle_encode_buffer_avx512(buffer512, buffer512, XBZRLE_P= AGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 =3D clock(); + float time_val512 =3D difftime(t_end512, t_start512); + g_assert(dlen512 =3D=3D 0); + + res->t_raw =3D time_val; + res->t_512 =3D time_val512; + + g_free(buffer); + g_free(compressed); + g_free(buffer512); + g_free(compressed512); + +} + +static void test_encode_decode_zero_avx512(void) +{ + int i; + float time_raw =3D 0.0, time_512 =3D 0.0; + struct ResTime res; + for (i =3D 0; i < 10000; i++) { + encode_decode_zero(&res); + time_raw +=3D res.t_raw; + time_512 +=3D res.t_512; + } + printf("Zero test:\n"); + printf("Raw xbzrle_encode time is %f ms\n", time_raw); + printf("512 xbzrle_encode time is %f ms\n", time_512); +} + +static void encode_decode_unchanged(struct ResTime *res) +{ + uint8_t *compressed =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + int i =3D 0; + int dlen =3D 0, dlen512 =3D 0; + int diff_len =3D g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); + + for (i =3D diff_len; i > 0; i--) { + test[1000 + i] =3D i + 4; + test512[1000 + i] =3D i + 4; + } + + test[1000 + diff_len + 3] =3D 107; + test[1000 + diff_len + 5] =3D 109; + + test512[1000 + diff_len + 3] =3D 107; + test512[1000 + diff_len + 5] =3D 109; + + /* test unchanged buffer */ + time_t t_start, t_end, t_start512, t_end512; + t_start =3D clock(); + dlen =3D xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, compressed, + XBZRLE_PAGE_SIZE); + t_end =3D clock(); + float time_val =3D difftime(t_end, t_start); + g_assert(dlen =3D=3D 0); + + t_start512 =3D clock(); + dlen512 =3D xbzrle_encode_buffer_avx512(test512, test512, XBZRLE_PAGE_= SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 =3D clock(); + float time_val512 =3D difftime(t_end512, t_start512); + g_assert(dlen512 =3D=3D 0); + + res->t_raw =3D time_val; + res->t_512 =3D time_val512; + + g_free(test); + g_free(compressed); + g_free(test512); + g_free(compressed512); + +} + +static void test_encode_decode_unchanged_avx512(void) +{ + int i; + float time_raw =3D 0.0, time_512 =3D 0.0; + struct ResTime res; + for (i =3D 0; i < 10000; i++) { + encode_decode_unchanged(&res); + time_raw +=3D res.t_raw; + time_512 +=3D res.t_512; + } + printf("Unchanged test:\n"); + printf("Raw xbzrle_encode time is %f ms\n", time_raw); + printf("512 xbzrle_encode time is %f ms\n", time_512); +} + +static void encode_decode_1_byte(struct ResTime *res) +{ + uint8_t *buffer =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed =3D g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 =3D g_malloc(XBZRLE_PAGE_SIZE); + int dlen =3D 0, rc =3D 0, dlen512 =3D 0, rc512 =3D 0; + uint8_t buf[2]; + uint8_t buf512[2]; + + test[XBZRLE_PAGE_SIZE - 1] =3D 1; + test512[XBZRLE_PAGE_SIZE - 1] =3D 1; + + time_t t_start, t_end, t_start512, t_end512; + t_start =3D clock(); + dlen =3D xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compress= ed, + XBZRLE_PAGE_SIZE); + t_end =3D clock(); + float time_val =3D difftime(t_end, t_start); + g_assert(dlen =3D=3D (uleb128_encode_small(&buf[0], 4095) + 2)); + + rc =3D xbzrle_decode_buffer(compressed, dlen, buffer, XBZRLE_PAGE_SIZE= ); + g_assert(rc =3D=3D XBZRLE_PAGE_SIZE); + g_assert(memcmp(test, buffer, XBZRLE_PAGE_SIZE) =3D=3D 0); + + t_start512 =3D clock(); + dlen512 =3D xbzrle_encode_buffer_avx512(buffer512, test512, XBZRLE_PAG= E_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 =3D clock(); + float time_val512 =3D difftime(t_end512, t_start512); + g_assert(dlen512 =3D=3D (uleb128_encode_small(&buf512[0], 4095) + 2)); + + rc512 =3D xbzrle_decode_buffer(compressed512, dlen512, buffer512, + XBZRLE_PAGE_SIZE); + g_assert(rc512 =3D=3D XBZRLE_PAGE_SIZE); + g_assert(memcmp(test512, buffer512, XBZRLE_PAGE_SIZE) =3D=3D 0); + + res->t_raw =3D time_val; + res->t_512 =3D time_val512; + + g_free(buffer); + g_free(compressed); + g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + +} + +static void test_encode_decode_1_byte_avx512(void) +{ + int i; + float time_raw =3D 0.0, time_512 =3D 0.0; + struct ResTime res; + for (i =3D 0; i < 10000; i++) { + encode_decode_1_byte(&res); + time_raw +=3D res.t_raw; + time_512 +=3D res.t_512; + } + printf("1 byte test:\n"); + printf("Raw xbzrle_encode time is %f ms\n", time_raw); + printf("512 xbzrle_encode time is %f ms\n", time_512); +} + +static void encode_decode_overflow(struct ResTime *res) +{ + uint8_t *compressed =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + int i =3D 0, rc =3D 0, rc512 =3D 0; + + for (i =3D 0; i < XBZRLE_PAGE_SIZE / 2 - 1; i++) { + test[i * 2] =3D 1; + test512[i * 2] =3D 1; + } + + /* encode overflow */ + time_t t_start, t_end, t_start512, t_end512; + t_start =3D clock(); + rc =3D xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, + XBZRLE_PAGE_SIZE); + t_end =3D clock(); + float time_val =3D difftime(t_end, t_start); + g_assert(rc =3D=3D -1); + + t_start512 =3D clock(); + rc512 =3D xbzrle_encode_buffer_avx512(buffer512, test512, XBZRLE_PAGE_= SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 =3D clock(); + float time_val512 =3D difftime(t_end512, t_start512); + g_assert(rc512 =3D=3D -1); + + res->t_raw =3D time_val; + res->t_512 =3D time_val512; + + g_free(buffer); + g_free(compressed); + g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + +} + +static void test_encode_decode_overflow_avx512(void) +{ + int i; + float time_raw =3D 0.0, time_512 =3D 0.0; + struct ResTime res; + for (i =3D 0; i < 10000; i++) { + encode_decode_overflow(&res); + time_raw +=3D res.t_raw; + time_512 +=3D res.t_512; + } + printf("Overflow test:\n"); + printf("Raw xbzrle_encode time is %f ms\n", time_raw); + printf("512 xbzrle_encode time is %f ms\n", time_512); +} + +static void encode_decode_range_avx512(struct ResTime *res) +{ + uint8_t *buffer =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed =3D g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 =3D g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + int i =3D 0, rc =3D 0, rc512 =3D 0; + int dlen =3D 0, dlen512 =3D 0; + + int diff_len =3D g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); + + for (i =3D diff_len; i > 0; i--) { + buffer[1000 + i] =3D i; + test[1000 + i] =3D i + 4; + buffer512[1000 + i] =3D i; + test512[1000 + i] =3D i + 4; + } + + buffer[1000 + diff_len + 3] =3D 103; + test[1000 + diff_len + 3] =3D 107; + + buffer[1000 + diff_len + 5] =3D 105; + test[1000 + diff_len + 5] =3D 109; + + buffer512[1000 + diff_len + 3] =3D 103; + test512[1000 + diff_len + 3] =3D 107; + + buffer512[1000 + diff_len + 5] =3D 105; + test512[1000 + diff_len + 5] =3D 109; + + /* test encode/decode */ + time_t t_start, t_end, t_start512, t_end512; + t_start =3D clock(); + dlen =3D xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compress= ed, + XBZRLE_PAGE_SIZE); + t_end =3D clock(); + float time_val =3D difftime(t_end, t_start); + rc =3D xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); + g_assert(rc < XBZRLE_PAGE_SIZE); + g_assert(memcmp(test, buffer, XBZRLE_PAGE_SIZE) =3D=3D 0); + + t_start512 =3D clock(); + dlen512 =3D xbzrle_encode_buffer_avx512(test512, buffer512, XBZRLE_PAG= E_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 =3D clock(); + float time_val512 =3D difftime(t_end512, t_start512); + rc512 =3D xbzrle_decode_buffer(compressed512, dlen512, test512, XBZRLE= _PAGE_SIZE); + g_assert(rc512 < XBZRLE_PAGE_SIZE); + g_assert(memcmp(test512, buffer512, XBZRLE_PAGE_SIZE) =3D=3D 0); + + res->t_raw =3D time_val; + res->t_512 =3D time_val512; + + g_free(buffer); + g_free(compressed); + g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + +} + +static void test_encode_decode_avx512(void) +{ + int i; + float time_raw =3D 0.0, time_512 =3D 0.0; + struct ResTime res; + for (i =3D 0; i < 10000; i++) { + encode_decode_range_avx512(&res); + time_raw +=3D res.t_raw; + time_512 +=3D res.t_512; + } + printf("Encode decode test:\n"); + printf("Raw xbzrle_encode time is %f ms\n", time_raw); + printf("512 xbzrle_encode time is %f ms\n", time_512); +} + +static void encode_decode_random(struct ResTime *res) +{ + uint8_t *buffer =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed =3D g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 =3D g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test512 =3D g_malloc0(XBZRLE_PAGE_SIZE); + int i =3D 0, rc =3D 0, rc512 =3D 0; + int dlen =3D 0, dlen512 =3D 0; + + int diff_len =3D g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1); + /* store the index of diff */ + int dirty_index[diff_len]; + for (int j =3D 0; j < diff_len; j++) { + dirty_index[j] =3D g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1); + } + for (i =3D diff_len - 1; i >=3D 0; i--) { + buffer[dirty_index[i]] =3D i; + test[dirty_index[i]] =3D i + 4; + buffer512[dirty_index[i]] =3D i; + test512[dirty_index[i]] =3D i + 4; + } + + time_t t_start, t_end, t_start512, t_end512; + t_start =3D clock(); + dlen =3D xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compress= ed, + XBZRLE_PAGE_SIZE); + t_end =3D clock(); + float time_val =3D difftime(t_end, t_start); + rc =3D xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); + g_assert(rc < XBZRLE_PAGE_SIZE); + + t_start512 =3D clock(); + dlen512 =3D xbzrle_encode_buffer_avx512(test512, buffer512, XBZRLE_PAG= E_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 =3D clock(); + float time_val512 =3D difftime(t_end512, t_start512); + rc512 =3D xbzrle_decode_buffer(compressed512, dlen512, test512, XBZRLE= _PAGE_SIZE); + g_assert(rc512 < XBZRLE_PAGE_SIZE); + + res->t_raw =3D time_val; + res->t_512 =3D time_val512; + + g_free(buffer); + g_free(compressed); + g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + +} + +static void test_encode_decode_random_avx512(void) +{ + int i; + float time_raw =3D 0.0, time_512 =3D 0.0; + struct ResTime res; + for (i =3D 0; i < 10000; i++) { + encode_decode_random(&res); + time_raw +=3D res.t_raw; + time_512 +=3D res.t_512; + } + printf("Random test:\n"); + printf("Raw xbzrle_encode time is %f ms\n", time_raw); + printf("512 xbzrle_encode time is %f ms\n", time_512); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + g_test_rand_int(); + #if defined(CONFIG_AVX512BW_OPT) + if (likely(is_cpu_support_avx512bw)) { + g_test_add_func("/xbzrle/encode_decode_zero", test_encode_decode_z= ero_avx512); + g_test_add_func("/xbzrle/encode_decode_unchanged", + test_encode_decode_unchanged_avx512); + g_test_add_func("/xbzrle/encode_decode_1_byte", test_encode_decode= _1_byte_avx512); + g_test_add_func("/xbzrle/encode_decode_overflow", + test_encode_decode_overflow_avx512); + g_test_add_func("/xbzrle/encode_decode", test_encode_decode_avx512= ); + g_test_add_func("/xbzrle/encode_decode_random", test_encode_decode= _random_avx512); + } + #endif + return g_test_run(); +} diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c index ef951b6e54..547046d093 100644 --- a/tests/unit/test-xbzrle.c +++ b/tests/unit/test-xbzrle.c @@ -16,6 +16,35 @@ =20 #define XBZRLE_PAGE_SIZE 4096 =20 +int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int, + uint8_t *, int) =3D xbzrle_encode_buffer; +#if defined(CONFIG_AVX512BW_OPT) +#include "qemu/cpuid.h" +static void __attribute__((constructor)) init_cpu_flag(void) +{ + unsigned max =3D __get_cpuid_max(0, NULL); + int a, b, c, d; + if (max >=3D 1) { + __cpuid(1, a, b, c, d); + /* We must check that AVX is not just available, but usable. */ + if ((c & bit_OSXSAVE) && (c & bit_AVX) && max >=3D 7) { + int bv; + __asm("xgetbv" : "=3Da"(bv), "=3Dd"(d) : "c"(0)); + __cpuid_count(7, 0, a, b, c, d); + /* 0xe6: + * XCR0[7:5] =3D 111b (OPMASK state, upper 256-bit of ZMM0-ZMM= 15 + * and ZMM16-ZMM31 state are enabled by OS) + * XCR0[2:1] =3D 11b (XMM state and YMM state are enabled by O= S) + */ + if ((bv & 0xe6) =3D=3D 0xe6 && (b & bit_AVX512BW)) { + xbzrle_encode_buffer_func =3D xbzrle_encode_buffer_avx512; + } + } + } + return ; +} +#endif + static void test_uleb(void) { uint32_t i, val; @@ -54,7 +83,7 @@ static void test_encode_decode_zero(void) buffer[1000 + diff_len + 5] =3D 105; =20 /* encode zero page */ - dlen =3D xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, compre= ssed, + dlen =3D xbzrle_encode_buffer_func(buffer, buffer, XBZRLE_PAGE_SIZE, c= ompressed, XBZRLE_PAGE_SIZE); g_assert(dlen =3D=3D 0); =20 @@ -78,7 +107,7 @@ static void test_encode_decode_unchanged(void) test[1000 + diff_len + 5] =3D 109; =20 /* test unchanged buffer */ - dlen =3D xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, compressed, + dlen =3D xbzrle_encode_buffer_func(test, test, XBZRLE_PAGE_SIZE, compr= essed, XBZRLE_PAGE_SIZE); g_assert(dlen =3D=3D 0); =20 @@ -96,7 +125,7 @@ static void test_encode_decode_1_byte(void) =20 test[XBZRLE_PAGE_SIZE - 1] =3D 1; =20 - dlen =3D xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compress= ed, + dlen =3D xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, com= pressed, XBZRLE_PAGE_SIZE); g_assert(dlen =3D=3D (uleb128_encode_small(&buf[0], 4095) + 2)); =20 @@ -121,7 +150,7 @@ static void test_encode_decode_overflow(void) } =20 /* encode overflow */ - rc =3D xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, + rc =3D xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compr= essed, XBZRLE_PAGE_SIZE); g_assert(rc =3D=3D -1); =20 @@ -152,7 +181,7 @@ static void encode_decode_range(void) test[1000 + diff_len + 5] =3D 109; =20 /* test encode/decode */ - dlen =3D xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compress= ed, + dlen =3D xbzrle_encode_buffer_func(test, buffer, XBZRLE_PAGE_SIZE, com= pressed, XBZRLE_PAGE_SIZE); =20 rc =3D xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); --=20 2.25.1