From patchwork Mon Aug 8 07:48:36 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Xu, Ling1" X-Patchwork-Id: 1664445 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: bilbo.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.a=rsa-sha256 header.s=Intel header.b=b6Ix0OGT; dkim-atps=neutral Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org (client-ip=209.51.188.17; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by bilbo.ozlabs.org (Postfix) with ESMTPS id 4M1Szf4LXDz9sFs for ; Mon, 8 Aug 2022 17:50:21 +1000 (AEST) Received: from localhost ([::1]:56126 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1oKxWk-0004Kb-9n for incoming@patchwork.ozlabs.org; Mon, 08 Aug 2022 03:50:18 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:44048) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1oKxVS-0004KA-Tw for qemu-devel@nongnu.org; Mon, 08 Aug 2022 03:48:58 -0400 Received: from mga05.intel.com ([192.55.52.43]:46926) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1oKxVO-0007gH-PD for qemu-devel@nongnu.org; Mon, 08 Aug 2022 03:48:57 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1659944934; x=1691480934; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=3fyRcdV607T8tj7zj8UMdNF/cX+XV/5F3DxiHUwkcYE=; b=b6Ix0OGTFGHZ1GH99AkFsyt72AFnFsakuTWuBWEhsuK5+whko91+ZZUo OClusWWDYjP6/U2W91YII5BIFSHsW+y41mYWTqPSPePhywc+DdUpqL4A8 1Na+jOMzAi1nHe/4ktGqJA1VtcN57NhYZa7Se+Iii4GGmbo3bkpfcZm41 C7pQu4RPLm5m0OCCmPi2D7vdzx2NAM+l93uSYbJ1518R3cGAjunoWg8WI yJ0c9IifuJdUyqaviWOXebQQWmT/5w6FbteMiB9pWctdhpn9S82Dbxp+n 1sijLIQ14a67TcSv/DsIY2XHhQhVYsqjWOkLXXdh1ApPTiWonJY0lkzFK g==; X-IronPort-AV: E=McAfee;i="6400,9594,10432"; a="376822960" X-IronPort-AV: E=Sophos;i="5.93,221,1654585200"; d="scan'208";a="376822960" Received: from orsmga007.jf.intel.com ([10.7.209.58]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Aug 2022 00:48:52 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.93,221,1654585200"; d="scan'208";a="600993117" Received: from xuling-b360m-d3h.sh.intel.com ([10.239.82.110]) by orsmga007.jf.intel.com with ESMTP; 08 Aug 2022 00:48:46 -0700 From: ling xu To: qemu-devel@nongnu.org Cc: quintela@redhat.com, dgilbert@redhat.com, ling xu , Zhou Zhao , Jun Jin Subject: [PATCH v3 1/2] Update AVX512 support for xbzrle_encode_buffer function Date: Mon, 8 Aug 2022 15:48:36 +0800 Message-Id: <20220808074837.1484760-2-ling1.xu@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220808074837.1484760-1-ling1.xu@intel.com> References: <20220808074837.1484760-1-ling1.xu@intel.com> MIME-Version: 1.0 Received-SPF: pass client-ip=192.55.52.43; envelope-from=ling1.xu@intel.com; helo=mga05.intel.com X-Spam_score_int: -44 X-Spam_score: -4.5 X-Spam_bar: ---- X-Spam_report: (-4.5 / 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_MED=-2.3, 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+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" This commit update runtime check of AVX512, and implements avx512 of xbzrle_encode_buffer function to accelerate xbzrle encoding speed. Compared with C version of xbzrle_encode_buffer function, avx512 version can achieve almost 60%-70% performance improvement on unit test provided by Qemu. In addition, we provide one more unit test called "test_encode_decode_random", in which dirty data are randomly located in 4K page, and this case can achieve almost 140% performance gain. Signed-off-by: ling xu Co-authored-by: Zhou Zhao Co-authored-by: Jun Jin --- meson.build | 16 ++++ meson_options.txt | 2 + migration/ram.c | 41 ++++++++++ migration/xbzrle.c | 181 +++++++++++++++++++++++++++++++++++++++++++++ migration/xbzrle.h | 4 + 5 files changed, 244 insertions(+) diff --git a/meson.build b/meson.build index 294e9a8f32..4222b77e9f 100644 --- a/meson.build +++ b/meson.build @@ -2262,6 +2262,22 @@ config_host_data.set('CONFIG_AVX512F_OPT', get_option('avx512f') \ int main(int argc, char *argv[]) { return bar(argv[0]); } '''), error_message: 'AVX512F not available').allowed()) +config_host_data.set('CONFIG_AVX512BW_OPT', get_option('avx512bw') \ + .require(have_cpuid_h, error_message: 'cpuid.h not available, cannot enable AVX512BW') \ + .require(cc.links(''' + #pragma GCC push_options + #pragma GCC target("avx512bw") + #include + #include + static int bar(void *a) { + + __m512i x = *(__m512i *)a; + __m512i res= _mm512_abs_epi8(x); + return res[1]; + } + int main(int argc, char *argv[]) { return bar(argv[0]); } + '''), error_message: 'AVX512BW not available').allowed()) + have_pvrdma = get_option('pvrdma') \ .require(rdma.found(), error_message: 'PVRDMA requires OpenFabrics libraries') \ .require(cc.compiles(gnu_source_prefix + ''' diff --git a/meson_options.txt b/meson_options.txt index e58e158396..07194bf680 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -104,6 +104,8 @@ option('avx2', type: 'feature', value: 'auto', description: 'AVX2 optimizations') option('avx512f', type: 'feature', value: 'disabled', description: 'AVX512F optimizations') +option('avx512bw', type: 'feature', value: 'auto', + description: 'AVX512BW optimizations') option('keyring', type: 'feature', value: 'auto', description: 'Linux keyring support') diff --git a/migration/ram.c b/migration/ram.c index dc1de9ddbc..d9c1ac2f7a 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -83,6 +83,35 @@ /* 0x80 is reserved in migration.h start with 0x100 next */ #define RAM_SAVE_FLAG_COMPRESS_PAGE 0x100 +#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 = __get_cpuid_max(0, NULL); + int a, b, c, d; + IS_CPU_SUPPORT_AVX512BW = false; + if (max >= 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 >= 7) { + int bv; + __asm("xgetbv" : "=a"(bv), "=d"(d) : "c"(0)); + __cpuid_count(7, 0, a, b, c, d); + /* 0xe6: + * XCR0[7:5] = 111b (OPMASK state, upper 256-bit of ZMM0-ZMM15 + * and ZMM16-ZMM31 state are enabled by OS) + * XCR0[2:1] = 11b (XMM state and YMM state are enabled by OS) + */ + if ((bv & 0xe6) == 0xe6 && (b & bit_AVX512BW)) { + IS_CPU_SUPPORT_AVX512BW = true; + } + } + } + return ; +} +#endif + XBZRLECacheStats xbzrle_counters; /* struct contains XBZRLE cache and a static page @@ -802,9 +831,21 @@ static int save_xbzrle_page(RAMState *rs, uint8_t **current_data, memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE); /* XBZRLE encoding (if there is no overflow) */ + #if defined(CONFIG_AVX512BW_OPT) + if (likely(IS_CPU_SUPPORT_AVX512BW)) { + encoded_len = xbzrle_encode_buffer_512(prev_cached_page, XBZRLE.current_buf, + TARGET_PAGE_SIZE, XBZRLE.encoded_buf, + TARGET_PAGE_SIZE); + } else { + encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf, + TARGET_PAGE_SIZE, XBZRLE.encoded_buf, + TARGET_PAGE_SIZE); + } + #else encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE, XBZRLE.encoded_buf, TARGET_PAGE_SIZE); + #endif /* * Update the cache contents, so that it corresponds to the data diff --git a/migration/xbzrle.c b/migration/xbzrle.c index 1ba482ded9..4db09fdbdb 100644 --- a/migration/xbzrle.c +++ b/migration/xbzrle.c @@ -174,3 +174,184 @@ int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen) return d; } + +#if defined(CONFIG_AVX512BW_OPT) +#pragma GCC push_options +#pragma GCC target("avx512bw") + +#include +#include +#define SET_ZERO512(r) r = _mm512_set1_epi32(0) +int xbzrle_encode_buffer_512(uint8_t *old_buf, uint8_t *new_buf, int slen, + uint8_t *dst, int dlen) +{ + uint32_t zrun_len = 0, nzrun_len = 0; + int d = 0, i = 0, num = 0; + uint8_t *nzrun_start = NULL; + int count512s = (slen >> 6); + int res = slen % 64; + bool never_same = true; + while (count512s--) { + if (d + 2 > dlen) { + return -1; + } + __m512i old_data = _mm512_mask_loadu_epi8(old_data, + 0xffffffffffffffff, old_buf + i); + __m512i new_data = _mm512_mask_loadu_epi8(new_data, + 0xffffffffffffffff, new_buf + i); + /* in mask bit 1 for same, 0 for diff */ + __mmask64 comp = _mm512_cmpeq_epi8_mask(old_data, new_data); + + int bytesToCheck = 64; + bool is_same = (comp & 0x1); + while (bytesToCheck) { + if (is_same) { + if (nzrun_len) { + d += uleb128_encode_small(dst + d, nzrun_len); + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + } + if (comp == 0xffffffffffffffff) { + i += 64; + zrun_len += 64; + break; + } + never_same = false; + num = __builtin_ctzl(~comp); + num = (num < bytesToCheck) ? num : bytesToCheck; + zrun_len += num; + bytesToCheck -= num; + comp >>= num; + i += num; + if (bytesToCheck) { + /* still has different data after same data */ + d += uleb128_encode_small(dst + d, zrun_len); + zrun_len = 0; + } else { + break; + } + } + if (never_same || zrun_len) { + /* + * never_same only acts if + * data begins with diff in first count512s + */ + d += uleb128_encode_small(dst + d, zrun_len); + zrun_len = 0; + never_same = false; + } + /* has diff */ + if ((bytesToCheck == 64) && (comp == 0x0)) { + i += 64; + nzrun_len += 64; + break; + } + num = __builtin_ctzl(comp); + num = (num < bytesToCheck) ? num : bytesToCheck; + nzrun_len += num; + bytesToCheck -= num; + comp >>= num; + i += num; + if (bytesToCheck) { + /* mask like 111000 */ + d += uleb128_encode_small(dst + d, nzrun_len); + /* overflow */ + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + is_same = true; + } + } + } + if (res) { + /* the number of data is less than 64 */ + unsigned long long mask = pow(2, res); + mask -= 1; + __m512i r = SET_ZERO512(r); + __m512i old_data = _mm512_mask_loadu_epi8(r, mask, old_buf + i); + __m512i new_data = _mm512_mask_loadu_epi8(r, mask, new_buf + i); + __mmask64 comp = _mm512_cmpeq_epi8_mask(old_data, new_data); + + int bytesToCheck = res; + bool is_same = (comp & 0x1); + while (bytesToCheck) { + if (is_same) { + if (nzrun_len) { + d += uleb128_encode_small(dst + d, nzrun_len); + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + } + never_same = false; + num = __builtin_ctzl(~comp); + num = (num < bytesToCheck) ? num : bytesToCheck; + zrun_len += num; + bytesToCheck -= num; + comp >>= num; + i += num; + if (bytesToCheck) { + /* diff after same */ + d += uleb128_encode_small(dst + d, zrun_len); + zrun_len = 0; + } else { + break; + } + } + + if (never_same || zrun_len) { + d += uleb128_encode_small(dst + d, zrun_len); + zrun_len = 0; + never_same = false; + } + /* has diff */ + num = __builtin_ctzl(comp); + num = (num < bytesToCheck) ? num : bytesToCheck; + nzrun_len += num; + bytesToCheck -= num; + comp >>= num; + i += num; + if (bytesToCheck) { + d += uleb128_encode_small(dst + d, nzrun_len); + /* overflow */ + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + is_same = true; + } + } + } + + if (zrun_len) { + return (zrun_len == slen) ? 0 : d; + } + if (nzrun_len != 0) { + d += uleb128_encode_small(dst + d, nzrun_len); + /* overflow */ + if (d + nzrun_len > dlen) { + return -1; + } + nzrun_start = new_buf + i - nzrun_len; + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + } + return d; +} +#pragma GCC pop_options +#endif \ No newline at end of file diff --git a/migration/xbzrle.h b/migration/xbzrle.h index a0db507b9c..6247de5f00 100644 --- a/migration/xbzrle.h +++ b/migration/xbzrle.h @@ -18,4 +18,8 @@ int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen, uint8_t *dst, int dlen); int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen); +#if defined(CONFIG_AVX512BW_OPT) +int xbzrle_encode_buffer_512(uint8_t *old_buf, uint8_t *new_buf, int slen, + uint8_t *dst, int dlen); +#endif #endif From patchwork Mon Aug 8 07:48:37 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Xu, Ling1" X-Patchwork-Id: 1664446 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: bilbo.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.a=rsa-sha256 header.s=Intel header.b=K9cd+aEO; dkim-atps=neutral Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org (client-ip=209.51.188.17; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by bilbo.ozlabs.org (Postfix) with ESMTPS id 4M1Szf3XB8z9sCD for ; Mon, 8 Aug 2022 17:50:21 +1000 (AEST) Received: from localhost ([::1]:56130 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1oKxWl-0004Kj-CT for incoming@patchwork.ozlabs.org; Mon, 08 Aug 2022 03:50:19 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:44058) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1oKxVV-0004KP-Ug for qemu-devel@nongnu.org; Mon, 08 Aug 2022 03:49:01 -0400 Received: from mga05.intel.com ([192.55.52.43]:46931) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1oKxVR-0007gT-2J for qemu-devel@nongnu.org; Mon, 08 Aug 2022 03:49:00 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1659944937; x=1691480937; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=izRSuqmrhdUJtl9TRuv6UJbVZUY5BeHrsSHJql5h38s=; b=K9cd+aEOaR//ZlmSgsqVA+sewaemT/5d/+0JLrlQN8hZ/qxuK5YAzlB8 KwMDsuLnZjScACQsNvZY6LXIgIhpnApHpZAgxwzi6URmqy25As5zhbrzU bCi8zxzY71mmuDpmxKkgQwjYbHp8/KN3cbPiTFlfg2K2k/QmXD22CL0hR Hg5y/czbBotWhMDhRKV9xLuSVjtnTtsjMhO7VUgxuxQ21vO+p0nATNYVY VzXDHKOgQ+rvaGFvTZCwreYOudAmjEm846HpsC9ad9c+3XRu6jK2d7A2J o8AVuSxO39LYXFOadCmAiwQXJznuV6wzgVnUM1cUM16OlKLoubn9giad9 A==; X-IronPort-AV: E=McAfee;i="6400,9594,10432"; a="376822973" X-IronPort-AV: E=Sophos;i="5.93,221,1654585200"; d="scan'208";a="376822973" Received: from orsmga007.jf.intel.com ([10.7.209.58]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Aug 2022 00:48:55 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.93,221,1654585200"; d="scan'208";a="600993125" Received: from xuling-b360m-d3h.sh.intel.com ([10.239.82.110]) by orsmga007.jf.intel.com with ESMTP; 08 Aug 2022 00:48:52 -0700 From: ling xu To: qemu-devel@nongnu.org Cc: quintela@redhat.com, dgilbert@redhat.com, ling xu , Zhou Zhao , Jun Jin Subject: [PATCH v3 2/2] Test code for AVX512 support for xbzrle_encode_buffer Date: Mon, 8 Aug 2022 15:48:37 +0800 Message-Id: <20220808074837.1484760-3-ling1.xu@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220808074837.1484760-1-ling1.xu@intel.com> References: <20220808074837.1484760-1-ling1.xu@intel.com> MIME-Version: 1.0 Received-SPF: pass client-ip=192.55.52.43; envelope-from=ling1.xu@intel.com; helo=mga05.intel.com X-Spam_score_int: -44 X-Spam_score: -4.5 X-Spam_bar: ---- X-Spam_report: (-4.5 / 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_MED=-2.3, 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+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" Signed-off-by: ling xu Co-authored-by: Zhou Zhao Co-authored-by: Jun Jin --- tests/unit/test-xbzrle.c | 307 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 290 insertions(+), 17 deletions(-) diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c index ef951b6e54..653016826f 100644 --- a/tests/unit/test-xbzrle.c +++ b/tests/unit/test-xbzrle.c @@ -38,111 +38,280 @@ static void test_uleb(void) g_assert(val == 0); } -static void test_encode_decode_zero(void) +static float *test_encode_decode_zero(void) { uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE); int i = 0; - int dlen = 0; + int dlen = 0, dlen512 = 0; int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); for (i = diff_len; i > 0; i--) { buffer[1000 + i] = i; + buffer512[1000 + i] = i; } buffer[1000 + diff_len + 3] = 103; buffer[1000 + diff_len + 5] = 105; + buffer512[1000 + diff_len + 3] = 103; + buffer512[1000 + diff_len + 5] = 105; + /* encode zero page */ + time_t t_start, t_end, t_start512, t_end512; + t_start = clock(); dlen = xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); + t_end = clock(); + float time_val = difftime(t_end, t_start); g_assert(dlen == 0); + t_start512 = clock(); + dlen512 = xbzrle_encode_buffer_512(buffer512, buffer512, XBZRLE_PAGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 = clock(); + float time_val512 = difftime(t_end512, t_start512); + g_assert(dlen512 == 0); + + static float result_zero[2]; + result_zero[0] = time_val; + result_zero[1] = time_val512; + g_free(buffer); g_free(compressed); + g_free(buffer512); + g_free(compressed512); + + return result_zero; +} + +static void test_encode_decode_zero_range(void) +{ + int i; + float time_raw = 0.0, time_512 = 0.0; + float *res; + for (i = 0; i < 10000; i++) { + res = test_encode_decode_zero(); + time_raw += res[0]; + time_512 += res[1]; + } + 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 test_encode_decode_unchanged(void) +static float *test_encode_decode_unchanged(void) { uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); int i = 0; - int dlen = 0; + int dlen = 0, dlen512 = 0; int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); for (i = diff_len; i > 0; i--) { test[1000 + i] = i + 4; + test512[1000 + i] = i + 4; } test[1000 + diff_len + 3] = 107; test[1000 + diff_len + 5] = 109; + test512[1000 + diff_len + 3] = 107; + test512[1000 + diff_len + 5] = 109; + /* test unchanged buffer */ + time_t t_start, t_end, t_start512, t_end512; + t_start = clock(); dlen = xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); + t_end = clock(); + float time_val = difftime(t_end, t_start); g_assert(dlen == 0); + t_start512 = clock(); + dlen512 = xbzrle_encode_buffer_512(test512, test512, XBZRLE_PAGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 = clock(); + float time_val512 = difftime(t_end512, t_start512); + g_assert(dlen512 == 0); + + static float result_unchanged[2]; + result_unchanged[0] = time_val; + result_unchanged[1] = time_val512; + g_free(test); g_free(compressed); + g_free(test512); + g_free(compressed512); + + return result_unchanged; } -static void test_encode_decode_1_byte(void) +static void test_encode_decode_unchanged_range(void) +{ + int i; + float time_raw = 0.0, time_512 = 0.0; + float *res; + for (i = 0; i < 10000; i++) { + res = test_encode_decode_unchanged(); + time_raw += res[0]; + time_512 += res[1]; + } + 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 float *test_encode_decode_1_byte(void) { uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); - int dlen = 0, rc = 0; + uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 = g_malloc(XBZRLE_PAGE_SIZE); + int dlen = 0, rc = 0, dlen512 = 0, rc512 = 0; uint8_t buf[2]; + uint8_t buf512[2]; test[XBZRLE_PAGE_SIZE - 1] = 1; + test512[XBZRLE_PAGE_SIZE - 1] = 1; + time_t t_start, t_end, t_start512, t_end512; + t_start = clock(); dlen = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); + t_end = clock(); + float time_val = difftime(t_end, t_start); g_assert(dlen == (uleb128_encode_small(&buf[0], 4095) + 2)); rc = xbzrle_decode_buffer(compressed, dlen, buffer, XBZRLE_PAGE_SIZE); g_assert(rc == XBZRLE_PAGE_SIZE); g_assert(memcmp(test, buffer, XBZRLE_PAGE_SIZE) == 0); + t_start512 = clock(); + dlen512 = xbzrle_encode_buffer_512(buffer512, test512, XBZRLE_PAGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 = clock(); + float time_val512 = difftime(t_end512, t_start512); + g_assert(dlen512 == (uleb128_encode_small(&buf512[0], 4095) + 2)); + + rc512 = xbzrle_decode_buffer(compressed512, dlen512, buffer512, + XBZRLE_PAGE_SIZE); + g_assert(rc512 == XBZRLE_PAGE_SIZE); + g_assert(memcmp(test512, buffer512, XBZRLE_PAGE_SIZE) == 0); + + static float result_1_byte[2]; + result_1_byte[0] = time_val; + result_1_byte[1] = time_val512; + g_free(buffer); g_free(compressed); g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + + return result_1_byte; } -static void test_encode_decode_overflow(void) +static void test_encode_decode_1_byte_range(void) +{ + int i; + float time_raw = 0.0, time_512 = 0.0; + float *res; + for (i = 0; i < 10000; i++) { + res = test_encode_decode_1_byte(); + time_raw += res[0]; + time_512 += res[1]; + } + 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 float *test_encode_decode_overflow(void) { uint8_t *compressed = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0, rc = 0; + uint8_t *compressed512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); + int i = 0, rc = 0, rc512 = 0; for (i = 0; i < XBZRLE_PAGE_SIZE / 2 - 1; i++) { test[i * 2] = 1; + test512[i * 2] = 1; } /* encode overflow */ + time_t t_start, t_end, t_start512, t_end512; + t_start = clock(); rc = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); + t_end = clock(); + float time_val = difftime(t_end, t_start); g_assert(rc == -1); + t_start512 = clock(); + rc512 = xbzrle_encode_buffer_512(buffer512, test512, XBZRLE_PAGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 = clock(); + float time_val512 = difftime(t_end512, t_start512); + g_assert(rc512 == -1); + + static float result_overflow[2]; + result_overflow[0] = time_val; + result_overflow[1] = time_val512; + g_free(buffer); g_free(compressed); g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + + return result_overflow; +} + +static void test_encode_decode_overflow_range(void) +{ + int i; + float time_raw = 0.0, time_512 = 0.0; + float *res; + for (i = 0; i < 10000; i++) { + res = test_encode_decode_overflow(); + time_raw += res[0]; + time_512 += res[1]; + } + 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(void) +static float *encode_decode_range(void) { uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - int i = 0, rc = 0; - int dlen = 0; + uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 = g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); + int i = 0, rc = 0, rc512 = 0; + int dlen = 0, dlen512 = 0; int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1006); for (i = diff_len; i > 0; i--) { buffer[1000 + i] = i; test[1000 + i] = i + 4; + buffer512[1000 + i] = i; + test512[1000 + i] = i + 4; } buffer[1000 + diff_len + 3] = 103; @@ -151,26 +320,129 @@ static void encode_decode_range(void) buffer[1000 + diff_len + 5] = 105; test[1000 + diff_len + 5] = 109; + buffer512[1000 + diff_len + 3] = 103; + test512[1000 + diff_len + 3] = 107; + + buffer512[1000 + diff_len + 5] = 105; + test512[1000 + diff_len + 5] = 109; + /* test encode/decode */ + time_t t_start, t_end, t_start512, t_end512; + t_start = clock(); dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); - + t_end = clock(); + float time_val = difftime(t_end, t_start); rc = xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); g_assert(rc < XBZRLE_PAGE_SIZE); g_assert(memcmp(test, buffer, XBZRLE_PAGE_SIZE) == 0); + t_start512 = clock(); + dlen512 = xbzrle_encode_buffer_512(test512, buffer512, XBZRLE_PAGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 = clock(); + float time_val512 = difftime(t_end512, t_start512); + rc512 = xbzrle_decode_buffer(compressed512, dlen512, test512, XBZRLE_PAGE_SIZE); + g_assert(rc512 < XBZRLE_PAGE_SIZE); + g_assert(memcmp(test512, buffer512, XBZRLE_PAGE_SIZE) == 0); + + static float result_range[2]; + result_range[0] = time_val; + result_range[1] = time_val512; + g_free(buffer); g_free(compressed); g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + + return result_range; } static void test_encode_decode(void) { int i; + float time_raw = 0.0, time_512 = 0.0; + float *res; + for (i = 0; i < 10000; i++) { + res = encode_decode_range(); + time_raw += res[0]; + time_512 += res[1]; + } + 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 float *encode_decode_random(void) +{ + uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *buffer512 = g_malloc0(XBZRLE_PAGE_SIZE); + uint8_t *compressed512 = g_malloc(XBZRLE_PAGE_SIZE); + uint8_t *test512 = g_malloc0(XBZRLE_PAGE_SIZE); + int i = 0, rc = 0, rc512 = 0; + int dlen = 0, dlen512 = 0; + + int diff_len = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1); + /* store the index of diff */ + int dirty_index[diff_len]; + for (int j = 0; j < diff_len; j++) { + dirty_index[j] = g_test_rand_int_range(0, XBZRLE_PAGE_SIZE - 1); + } + for (i = diff_len - 1; i >= 0; i--) { + buffer[dirty_index[i]] = i; + test[dirty_index[i]] = i + 4; + buffer512[dirty_index[i]] = i; + test512[dirty_index[i]] = i + 4; + } + + time_t t_start, t_end, t_start512, t_end512; + t_start = clock(); + dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compressed, + XBZRLE_PAGE_SIZE); + t_end = clock(); + float time_val = difftime(t_end, t_start); + rc = xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); + g_assert(rc < XBZRLE_PAGE_SIZE); + + t_start512 = clock(); + dlen512 = xbzrle_encode_buffer_512(test512, buffer512, XBZRLE_PAGE_SIZE, + compressed512, XBZRLE_PAGE_SIZE); + t_end512 = clock(); + float time_val512 = difftime(t_end512, t_start512); + rc512 = xbzrle_decode_buffer(compressed512, dlen512, test512, XBZRLE_PAGE_SIZE); + g_assert(rc512 < XBZRLE_PAGE_SIZE); + + static float result_random[2]; + result_random[0] = time_val; + result_random[1] = time_val512; + + g_free(buffer); + g_free(compressed); + g_free(test); + g_free(buffer512); + g_free(compressed512); + g_free(test512); + + return result_random; +} + +static void test_encode_decode_random(void) +{ + int i; + float time_raw = 0.0, time_512 = 0.0; + float *res; for (i = 0; i < 10000; i++) { - encode_decode_range(); + res = encode_decode_random(); + time_raw += res[0]; + time_512 += res[1]; } + 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) @@ -178,13 +450,14 @@ int main(int argc, char **argv) g_test_init(&argc, &argv, NULL); g_test_rand_int(); g_test_add_func("/xbzrle/uleb", test_uleb); - g_test_add_func("/xbzrle/encode_decode_zero", test_encode_decode_zero); + g_test_add_func("/xbzrle/encode_decode_zero", test_encode_decode_zero_range); g_test_add_func("/xbzrle/encode_decode_unchanged", - test_encode_decode_unchanged); - g_test_add_func("/xbzrle/encode_decode_1_byte", test_encode_decode_1_byte); + test_encode_decode_unchanged_range); + g_test_add_func("/xbzrle/encode_decode_1_byte", test_encode_decode_1_byte_range); g_test_add_func("/xbzrle/encode_decode_overflow", - test_encode_decode_overflow); + test_encode_decode_overflow_range); g_test_add_func("/xbzrle/encode_decode", test_encode_decode); + g_test_add_func("/xbzrle/encode_decode_random", test_encode_decode_random); return g_test_run(); }