From patchwork Sat May 20 16:26:14 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 684297 Delivered-To: patch@linaro.org Received: by 2002:a5d:4e01:0:0:0:0:0 with SMTP id p1csp447640wrt; Sat, 20 May 2023 09:27:57 -0700 (PDT) X-Google-Smtp-Source: ACHHUZ4LBIsP0W5BXUU1CtUWqjFSgY2YeQwM64m1BDYVDDLxlxKVI50qeRLaZH6xzm/EY051QSiB X-Received: by 2002:ac8:7f41:0:b0:3f2:1708:1372 with SMTP id g1-20020ac87f41000000b003f217081372mr9742134qtk.17.1684600077294; Sat, 20 May 2023 09:27:57 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1684600077; cv=none; d=google.com; s=arc-20160816; b=xk2ujeRcHVTAehnMwUVob+wxKYyO/zJos7Ye4ra88+Tt5yzJ7i4nMtfMc/pvBuT/Ce 47rlF1wK6VPRQpQdaOPhj06kB12CdpiufmuRsyLhCuXBgi/v7moJqCl7tvmqTGgwdTBE z6Hw2QjD2Xmeis+zOd9+28PBBnfXhiOmT98+FZvohHCNzdUE9vz/sTADooYdVmiwDD4U nSnvNXdOTm0LpQJLuexjIEb8Kxo8zfav3N+IWoc/X8O7Iz48rKsE+xIz8JujNzWDTpd6 2DFbP/wj3eIhIi4An7mO5BKKFWGFbiZQqti3nqtBJfi5wm/UhmDqbli6rrHCDRJ9CH3V xkRA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:cc:to :from:dkim-signature; bh=ihz9eMnKafBCXMKR5tA0Mrs4r+NsNN8WEkICVzjP6LI=; b=UGkOfurHvoQAbBMjZmdrjImgcN2aCINIU2JfgGlGJi3FT6aF3DrtH73GAa/CNPMca1 R69oFa42s4bdZROutWglrYhfjQhiX7UqGTIc7LSAZQSKOXQU1MNRPDcpQpLIa6jO/zSq W3DDpp/sNejfnBZ8r89rvREeyb1WxF54ptekBXaVDWBG6+UZ8O1st3TqHVks+u5KpJbo EK8RCpfaa5fvzRAVlASKj0A0dWVOfDY7EBv1F7IWP1sOuuvqnWD1RvB4z8eNLLRRlDE0 D9yyMQBWnNFqo6PuzrWH8HOnQjHB2+OifxzxplZTAG6pHxVKfufFJ6nonG82zZq6Hqwb uWdg== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="CVGU/baz"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id f8-20020ae9ea08000000b0074e4a5d1edfsi1013120qkg.706.2023.05.20.09.27.57 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Sat, 20 May 2023 09:27:57 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b="CVGU/baz"; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1q0PPs-0003bm-Jn; Sat, 20 May 2023 12:26:48 -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 1q0PPr-0003b9-84 for qemu-devel@nongnu.org; Sat, 20 May 2023 12:26:47 -0400 Received: from mail-pl1-x635.google.com ([2607:f8b0:4864:20::635]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1q0PPo-000362-5E for qemu-devel@nongnu.org; Sat, 20 May 2023 12:26:47 -0400 Received: by mail-pl1-x635.google.com with SMTP id d9443c01a7336-1ae875bf125so10481895ad.1 for ; Sat, 20 May 2023 09:26:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1684600002; x=1687192002; 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=ihz9eMnKafBCXMKR5tA0Mrs4r+NsNN8WEkICVzjP6LI=; b=CVGU/baz7BSKbPjXBeOzd+AB7MwuhTN/7B3c9xbIc7VTxAYC2U3HHVbGfHVu8ch7/F gtSW33Z65RaQLG3ov8kd6YYomc/w21oyU8d8vd7YxvRi8do1u3u2xMeczTd53a2VDmUO pib4O2bIq1aaTtXKq59Ok0Wjec/Kezj5jRSSM9VNifC6sKMqIwUEzGlbsWK8lnjo6XtJ y3xKGdTTWHa9ljcJHQALLh+0o1mOVxwnsmQ3L/fYyIvL8wmsujXw++wTO06V9juUykor f87M7F1laQ2aG5uQKq99OPkKJcFMjcpqWBeTVSePytyyluoU6wCXthoQ7yJfOOXHzbi5 uIPw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684600002; x=1687192002; 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=ihz9eMnKafBCXMKR5tA0Mrs4r+NsNN8WEkICVzjP6LI=; b=AaPDR2YF40L0WOpuZysha7ihWhauegoiAY+fJN1kRDr8cYKo060hynamSiyuPBMzUp 5+YcNZ1CXCVpG89RN5dkSk70rJTIB40EEol8cQzMnIVFtjtGm6GOjqFZ0JIpF4ycQ+ey jIGOM7uGYCYinfj8WuQA/AHAe/CG8PCAt+5vn8ntcy829EdN9UFqf2WHf5FpeIX/tz2i 0SxGjzyUUHm8jtUB/EQWJYSyCNK669DUM3rXk9pIQdt4kHvneArCGvaTPswFsLmCd2Rv wEFiWXTiTGZLYYiZytmSq33LqgDUyMnggu6zYaBgP7B3ZJromdsrH0q42jxm+j9XfEE/ 9nSQ== X-Gm-Message-State: AC+VfDwx5FbgLyAz8dMUMbnqnMMTnx+4WvYoEuqdlyw2eapCxn7IXQSG vE53/782N2KGHaZa+K1SUDHKvFG0urJFp93euPA= X-Received: by 2002:a17:902:76cb:b0:19f:3797:d8de with SMTP id j11-20020a17090276cb00b0019f3797d8demr5694479plt.9.1684600002505; Sat, 20 May 2023 09:26:42 -0700 (PDT) Received: from stoup.. ([2602:ae:1598:4c01:d078:d94e:cb2b:a055]) by smtp.gmail.com with ESMTPSA id d12-20020a170903230c00b001a5260a6e6csm1697104plh.206.2023.05.20.09.26.41 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 20 May 2023 09:26:42 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Cc: qemu-arm@nongnu.org, Juan Quintela Subject: [PATCH 07/27] migration/xbzrle: Use i386 host/cpuinfo.h Date: Sat, 20 May 2023 09:26:14 -0700 Message-Id: <20230520162634.3991009-8-richard.henderson@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20230520162634.3991009-1-richard.henderson@linaro.org> References: <20230520162634.3991009-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::635; envelope-from=richard.henderson@linaro.org; helo=mail-pl1-x635.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=unavailable 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+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org 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: 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_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_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, - 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 */ -int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int, - uint8_t *, int) = xbzrle_encode_buffer; -#if defined(CONFIG_AVX512BW_OPT) -#include "qemu/cpuid.h" -static void __attribute__((constructor)) init_cpu_flag(void) -{ - unsigned max = __get_cpuid_max(0, NULL); - int a, b, c, d; - 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)) { - xbzrle_encode_buffer_func = xbzrle_encode_buffer_avx512; - } - } - } -} -#endif - XBZRLECacheStats xbzrle_counters; /* used by the search for pages to send */ @@ -660,9 +632,9 @@ static int save_xbzrle_page(RAMState *rs, PageSearchStatus *pss, memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE); /* XBZRLE encoding (if there is no overflow) */ - encoded_len = xbzrle_encode_buffer_func(prev_cached_page, XBZRLE.current_buf, - TARGET_PAGE_SIZE, XBZRLE.encoded_buf, - TARGET_PAGE_SIZE); + encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf, + TARGET_PAGE_SIZE, XBZRLE.encoded_buf, + TARGET_PAGE_SIZE); /* * 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 @@ #if defined(CONFIG_AVX512BW_OPT) #include +#include "host/cpuinfo.h" -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 = cpuinfo_init(); + if (info & CPUINFO_AVX512BW) { + accel_func = xbzrle_encode_buffer_avx512; + } else { + accel_func = 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 /* 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 later. - * 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 = __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 ; -} - -struct ResTime { - float t_raw; - float t_512; -}; - - -/* Function prototypes -int xbzrle_encode_buffer_avx512(uint8_t *old_buf, uint8_t *new_buf, int slen, - uint8_t *dst, int dlen); -*/ -static void encode_decode_zero(struct ResTime *res) -{ - 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, 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_avx512(buffer512, buffer512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(dlen512 == 0); - - res->t_raw = time_val; - res->t_512 = 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 = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_zero(&res); - time_raw += res.t_raw; - time_512 += 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 = 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, 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_avx512(test512, test512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(dlen512 == 0); - - res->t_raw = time_val; - res->t_512 = 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 = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_unchanged(&res); - time_raw += res.t_raw; - time_512 += 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 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *compressed = g_malloc(XBZRLE_PAGE_SIZE); - 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_avx512(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); - - res->t_raw = time_val; - res->t_512 = 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 = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_1_byte(&res); - time_raw += res.t_raw; - time_512 += 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 = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *test = g_malloc0(XBZRLE_PAGE_SIZE); - uint8_t *buffer = g_malloc0(XBZRLE_PAGE_SIZE); - 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_avx512(buffer512, test512, XBZRLE_PAGE_SIZE, - compressed512, XBZRLE_PAGE_SIZE); - t_end512 = clock(); - float time_val512 = difftime(t_end512, t_start512); - g_assert(rc512 == -1); - - res->t_raw = time_val; - res->t_512 = 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 = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_overflow(&res); - time_raw += res.t_raw; - time_512 += 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 = 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 - 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; - test[1000 + diff_len + 3] = 107; - - 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_avx512(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); - - res->t_raw = time_val; - res->t_512 = 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 = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_range_avx512(&res); - time_raw += res.t_raw; - time_512 += 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 = 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_avx512(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); - - res->t_raw = time_val; - res->t_512 = 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 = 0.0, time_512 = 0.0; - struct ResTime res; - for (i = 0; i < 10000; i++) { - encode_decode_random(&res); - time_raw += res.t_raw; - time_512 += 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_zero_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 @@ #define XBZRLE_PAGE_SIZE 4096 -int (*xbzrle_encode_buffer_func)(uint8_t *, uint8_t *, int, - uint8_t *, int) = xbzrle_encode_buffer; -#if defined(CONFIG_AVX512BW_OPT) -#include "qemu/cpuid.h" -static void __attribute__((constructor)) init_cpu_flag(void) -{ - unsigned max = __get_cpuid_max(0, NULL); - int a, b, c, d; - 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)) { - xbzrle_encode_buffer_func = 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] = 105; /* encode zero page */ - dlen = xbzrle_encode_buffer_func(buffer, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == 0); g_free(buffer); @@ -107,8 +78,8 @@ static void test_encode_decode_unchanged(void) test[1000 + diff_len + 5] = 109; /* test unchanged buffer */ - dlen = xbzrle_encode_buffer_func(test, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == 0); g_free(test); @@ -125,8 +96,8 @@ static void test_encode_decode_1_byte(void) test[XBZRLE_PAGE_SIZE - 1] = 1; - dlen = xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == (uleb128_encode_small(&buf[0], 4095) + 2)); rc = xbzrle_decode_buffer(compressed, dlen, buffer, XBZRLE_PAGE_SIZE); @@ -150,8 +121,8 @@ static void test_encode_decode_overflow(void) } /* encode overflow */ - rc = xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + rc = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); g_assert(rc == -1); g_free(buffer); @@ -181,8 +152,8 @@ static void encode_decode_range(void) test[1000 + diff_len + 5] = 109; /* test encode/decode */ - dlen = xbzrle_encode_buffer_func(test, buffer, XBZRLE_PAGE_SIZE, compressed, - XBZRLE_PAGE_SIZE); + dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, + compressed, XBZRLE_PAGE_SIZE); rc = 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 = executable('qht-bench', sources: 'qht-bench.c', dependencies: [qemuutil]) -if have_system -xbzrle_bench = executable('xbzrle-bench', - sources: 'xbzrle-bench.c', - dependencies: [qemuutil,migration]) -endif - qtree_bench = executable('qtree-bench', sources: 'qtree-bench.c', dependencies: [qemuutil])