From nobody Wed Apr 9 23:06:21 2025 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; 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=linaro.org ARC-Seal: i=1; a=rsa-sha256; t=1684886622; cv=none; d=zohomail.com; s=zohoarc; b=C4gKIZp+7r2lMMbtTfOizDL+a3U12zrP7ODJQViWkMH4YoquwJ3ZV4hOjD7d6zbAsZS2TbXX0AWg/TpSfcZz0vTYxjmarTHTxPIkxTgixFtIiwGlcczhLpfyTAmR+le15NiJVdmj/q/5l5WWJFbf3DAYok1taiaW5GSojjE4sac= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1684886622; h=Content-Type: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=vatX/eqgfBkmzTBE7D9o3RP4GGfUvt6lQl1eSLzfC3w=; b=Sse3k2OLkf0CvMKISo9Lew4pmBMaFbPXjjidOnUa6w+FuxyOGTm/H1FNBUEqnF9KbptRSVxCPd03R/L87xf/vML2sUPpc0UwZCEyXr9Q61lf2HczkteCWz8aHVMZvjet31U8RF4AnGuEONp7vBw75oP0UJNOLe4MbeDuVzoHgAE= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; 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 1684886622383727.0899693691541; Tue, 23 May 2023 17:03:42 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1q1btV-0004Be-Hk; Tue, 23 May 2023 19:58:21 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1q1btQ-0004AY-OY for qemu-devel@nongnu.org; Tue, 23 May 2023 19:58:17 -0400 Received: from mail-pf1-x430.google.com ([2607:f8b0:4864:20::430]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1q1btN-0001mr-NB for qemu-devel@nongnu.org; Tue, 23 May 2023 19:58:16 -0400 Received: by mail-pf1-x430.google.com with SMTP id d2e1a72fcca58-64d5b4c400fso155746b3a.1 for ; Tue, 23 May 2023 16:58:13 -0700 (PDT) Received: from stoup.. ([2602:ae:1598:4c01:c13a:d73:4f88:3654]) by smtp.gmail.com with ESMTPSA id p18-20020aa78612000000b0063b7c42a070sm6285041pfn.68.2023.05.23.16.58.11 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 23 May 2023 16:58:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1684886292; x=1687478292; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=vatX/eqgfBkmzTBE7D9o3RP4GGfUvt6lQl1eSLzfC3w=; b=H/tRtZyINE/1jWeKxNKpBBykoUyxlcsd9ARYEjukjaZIheadhRtXQqXD6xht2Ge8I4 x89pkoKsEeo0Rhw3YHGL1UT5q/itr39fDLHgYNVB46+STRB56/q+7yOmMFM5zKeNR+H/ T2JCvDrXRyDdcbusXB2PYtmEKuoZTjtgFcL3gCKtAgVRWpDgmtQxCrX1Yeeuf8ovlFiu +pG6DMc2wKOi0Insilrmj95GNQbcVxA4/Fqp5HDdkDmaLBrpXAbbE1lDL9QozP9LEKm+ GvXEHR74go/wt3P3qEVQuvXklV/ffy0XKNkpZQa1BAaA34uMaSu+D1OXKXEaBheOgl8C EdVw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684886292; x=1687478292; 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=vatX/eqgfBkmzTBE7D9o3RP4GGfUvt6lQl1eSLzfC3w=; b=NQiZXmIKH6fcS28ZVMmW2oq+nOHQ+Y/HmtH2tg2DZft1YhQtcCJw1C7Dqv3681ihpu 3ZlTLqq66ViCGv+eQLbj5YhIPcE85j02j3qhzs1VZn4YNK8OjQoo1es0SynE3RI88l/S VajrnkuPOR7geRiciokXCW7k91mG4a9QKDTXDy3+/7VVtejxyGxx8u0y7oUkSYU98Pbd q3/ewE8RCqp7n2CurWizLxyFM58cN8S5Sr9yO3As7rI8zUJ6tXP5CrcKHRcjAH3PtFRV //E1uCrh/qWGKZoXfCsek2HwDprYMPBttDq5F661fVwuZy1aTpZAHn9+haMnMJqfY/jb OApw== X-Gm-Message-State: AC+VfDz4QOY6PExliP1PQM3u2ekqHUl4BXnQQdZisnUzaBPzAM/6K+bk /vL4gUzraKl6mEmOCPgOOZKJByV3mCAwnMxXU1g= X-Google-Smtp-Source: ACHHUZ5YebWULZv/IjOqavF7WmDKWKOQoo2wdPiBG9b2LLghf2ClSKg8st2QW/fn3uQhU08/bLiIYw== X-Received: by 2002:a05:6a00:2389:b0:636:e52f:631e with SMTP id f9-20020a056a00238900b00636e52f631emr847911pfc.1.1684886292152; Tue, 23 May 2023 16:58:12 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Cc: =?UTF-8?q?Alex=20Benn=C3=A9e?= , Juan Quintela Subject: [PULL 07/28] migration/xbzrle: Use i386 host/cpuinfo.h Date: Tue, 23 May 2023 16:57:43 -0700 Message-Id: <20230523235804.747803-8-richard.henderson@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230523235804.747803-1-richard.henderson@linaro.org> References: <20230523235804.747803-1-richard.henderson@linaro.org> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" 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=2607:f8b0:4864:20::430; envelope-from=richard.henderson@linaro.org; helo=mail-pf1-x430.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, 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-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @linaro.org) X-ZM-MESSAGEID: 1684886623750100009 Perform the function selection once, and only if CONFIG_AVX512_OPT is enabled. Centralize the selection to xbzrle.c, instead of spreading the init across 3 files. Remove xbzrle-bench.c. The benefit of being able to benchmark the different implementations is less important than not peeking into the internals of the implementation. Reviewed-by: Alex Benn=C3=A9e Reviewed-by: Juan Quintela Signed-off-by: Richard Henderson --- migration/xbzrle.h | 5 +- migration/ram.c | 34 +-- migration/xbzrle.c | 26 +- tests/bench/xbzrle-bench.c | 469 ------------------------------------- tests/unit/test-xbzrle.c | 49 +--- tests/bench/meson.build | 6 - 6 files changed, 39 insertions(+), 550 deletions(-) delete mode 100644 tests/bench/xbzrle-bench.c diff --git a/migration/xbzrle.h b/migration/xbzrle.h index 6feb49160a..39e651b9ec 100644 --- a/migration/xbzrle.h +++ b/migration/xbzrle.h @@ -18,8 +18,5 @@ int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_b= uf, int slen, uint8_t *dst, int dlen); =20 int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen); -#if defined(CONFIG_AVX512BW_OPT) -int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int sl= en, - uint8_t *dst, int dlen); -#endif + #endif diff --git a/migration/ram.c b/migration/ram.c index 9fb076fa58..88a6c82e63 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -90,34 +90,6 @@ #define RAM_SAVE_FLAG_MULTIFD_FLUSH 0x200 /* We can't use any flag that is bigger than 0x200 */ =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; - } - } - } -} -#endif - XBZRLECacheStats xbzrle_counters; =20 /* used by the search for pages to send */ @@ -660,9 +632,9 @@ static int save_xbzrle_page(RAMState *rs, PageSearchSta= tus *pss, memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE); =20 /* XBZRLE encoding (if there is no overflow) */ - encoded_len =3D xbzrle_encode_buffer_func(prev_cached_page, XBZRLE.cur= rent_buf, - TARGET_PAGE_SIZE, XBZRLE.encod= ed_buf, - TARGET_PAGE_SIZE); + encoded_len =3D xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_= buf, + TARGET_PAGE_SIZE, XBZRLE.encoded_bu= f, + TARGET_PAGE_SIZE); =20 /* * Update the cache contents, so that it corresponds to the data diff --git a/migration/xbzrle.c b/migration/xbzrle.c index 751b5428f7..3eddcf249b 100644 --- a/migration/xbzrle.c +++ b/migration/xbzrle.c @@ -17,8 +17,9 @@ =20 #if defined(CONFIG_AVX512BW_OPT) #include +#include "host/cpuinfo.h" =20 -int __attribute__((target("avx512bw"))) +static int __attribute__((target("avx512bw"))) xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, uint8_t *dst, int dlen) { @@ -135,6 +136,29 @@ xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t = *new_buf, int slen, } return d; } + +static int xbzrle_encode_buffer_int(uint8_t *old_buf, uint8_t *new_buf, + int slen, uint8_t *dst, int dlen); + +static int (*accel_func)(uint8_t *, uint8_t *, int, uint8_t *, int); + +static void __attribute__((constructor)) init_accel(void) +{ + unsigned info =3D cpuinfo_init(); + if (info & CPUINFO_AVX512BW) { + accel_func =3D xbzrle_encode_buffer_avx512; + } else { + accel_func =3D xbzrle_encode_buffer_int; + } +} + +int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen, + uint8_t *dst, int dlen) +{ + return accel_func(old_buf, new_buf, slen, dst, dlen); +} + +#define xbzrle_encode_buffer xbzrle_encode_buffer_int #endif =20 /* diff --git a/tests/bench/xbzrle-bench.c b/tests/bench/xbzrle-bench.c deleted file mode 100644 index 8848a3a32d..0000000000 --- a/tests/bench/xbzrle-bench.c +++ /dev/null @@ -1,469 +0,0 @@ -/* - * 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" - -#if defined(CONFIG_AVX512BW_OPT) -#define XBZRLE_PAGE_SIZE 4096 -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)) { - is_cpu_support_avx512bw =3D true; - } - } - } - return ; -} - -struct ResTime { - float t_raw; - float t_512; -}; - - -/* Function prototypes -int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int sl= en, - uint8_t *dst, int dlen); -*/ -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); -} -#endif - -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 547046d093..b6996de69a 100644 --- a/tests/unit/test-xbzrle.c +++ b/tests/unit/test-xbzrle.c @@ -16,35 +16,6 @@ =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; @@ -83,8 +54,8 @@ static void test_encode_decode_zero(void) buffer[1000 + diff_len + 5] =3D 105; =20 /* encode zero page */ - dlen =3D xbzrle_encode_buffer_func(buffer, buffer, XBZRLE_PAGE_SIZE, c= ompressed, - XBZRLE_PAGE_SIZE); + dlen =3D xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen =3D=3D 0); =20 g_free(buffer); @@ -107,8 +78,8 @@ static void test_encode_decode_unchanged(void) test[1000 + diff_len + 5] =3D 109; =20 /* test unchanged buffer */ - dlen =3D xbzrle_encode_buffer_func(test, test, XBZRLE_PAGE_SIZE, compr= essed, - XBZRLE_PAGE_SIZE); + dlen =3D xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen =3D=3D 0); =20 g_free(test); @@ -125,8 +96,8 @@ static void test_encode_decode_1_byte(void) =20 test[XBZRLE_PAGE_SIZE - 1] =3D 1; =20 - dlen =3D xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, com= pressed, - XBZRLE_PAGE_SIZE); + dlen =3D xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen =3D=3D (uleb128_encode_small(&buf[0], 4095) + 2)); =20 rc =3D xbzrle_decode_buffer(compressed, dlen, buffer, XBZRLE_PAGE_SIZE= ); @@ -150,8 +121,8 @@ static void test_encode_decode_overflow(void) } =20 /* encode overflow */ - rc =3D xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compr= essed, - XBZRLE_PAGE_SIZE); + rc =3D xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(rc =3D=3D -1); =20 g_free(buffer); @@ -181,8 +152,8 @@ static void encode_decode_range(void) test[1000 + diff_len + 5] =3D 109; =20 /* test encode/decode */ - dlen =3D xbzrle_encode_buffer_func(test, buffer, XBZRLE_PAGE_SIZE, com= pressed, - XBZRLE_PAGE_SIZE); + dlen =3D xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); =20 rc =3D xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); g_assert(rc < XBZRLE_PAGE_SIZE); diff --git a/tests/bench/meson.build b/tests/bench/meson.build index 4e6b469066..3c799dbd98 100644 --- a/tests/bench/meson.build +++ b/tests/bench/meson.build @@ -3,12 +3,6 @@ qht_bench =3D executable('qht-bench', sources: 'qht-bench.c', dependencies: [qemuutil]) =20 -if have_system -xbzrle_bench =3D executable('xbzrle-bench', - sources: 'xbzrle-bench.c', - dependencies: [qemuutil,migration]) -endif - qtree_bench =3D executable('qtree-bench', sources: 'qtree-bench.c', dependencies: [qemuutil]) --=20 2.34.1