From patchwork Mon Feb 13 02:29:02 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Juan Quintela X-Patchwork-Id: 13137713 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 57C81C05027 for ; Mon, 13 Feb 2023 02:31:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229828AbjBMCbO (ORCPT ); Sun, 12 Feb 2023 21:31:14 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44706 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229869AbjBMCa7 (ORCPT ); Sun, 12 Feb 2023 21:30:59 -0500 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EC2B5FF2C for ; Sun, 12 Feb 2023 18:29:38 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1676255378; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=hhzdc6EJT0N0Bv1boe7/qcEnx6KstP3OPe2f+kkOVWo=; b=IT4hhlhcZC9CTxrqDBbMBJ+JsEMKzmEGNNp4uUWF4s6yyKu0ZS//KtcTGFOznNsJuTQ0ZA 24g1ekyHAqD/1NxWU+vKeywSPM4mImPFE3XDrIGec7+c2JIk0ykAJLOdmVXS21erTNwk6y mONhopGRK6rYGvdKxp5uwaU54xFTQyM= Received: from mail-wm1-f72.google.com (mail-wm1-f72.google.com [209.85.128.72]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_128_GCM_SHA256) id us-mta-140-j59RDBjuOgSvVciilq9Gbg-1; Sun, 12 Feb 2023 21:29:36 -0500 X-MC-Unique: j59RDBjuOgSvVciilq9Gbg-1 Received: by mail-wm1-f72.google.com with SMTP id e38-20020a05600c4ba600b003dc434dabbdso8365669wmp.6 for ; Sun, 12 Feb 2023 18:29:36 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; 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=hhzdc6EJT0N0Bv1boe7/qcEnx6KstP3OPe2f+kkOVWo=; b=nap1J+oa229RjqbowDv78MMqQbf0Cx5vpMtHkh+r2/XLJk4QoAsJrRXQLFOwhivB9k vuQqXP2ZiIiaWNqVPx8oX+xzLZIF8Kwjw038yT2cF3ihr7JxBTFUnXO/RbEEt1hwWCJo t8e1tu+K9MvklTw7zDbG3/EQ6qQwAhi0LNCGcmSr5nqBpCWeK++SBAioPgIy5IBZ37fw OcGM7oYeSGaao1kiQU/z7VOHvX4vgZxjuREU/u6bNsAYboqtxI3V618KvOgmN8o1AAHR wM9PfDnX1ZgQO4QCp+PJF3LA4g3XsgPfqMP5ZVpNIfExl1NquGVFWhaiY/neW8yLNnRU 1POg== X-Gm-Message-State: AO0yUKVHjlow7dnv7fk5GG2iVO4BdMQ2a3nESM55fj3YybgVAnEnaG6s nz7YtsF2PUWS4d7nJG/k0GthfHAfyhYjIpDDYx64XjnLvcgtN83PB2DFW8mqYMhjILVF/57sOw1 d9CneAXNLg1VD X-Received: by 2002:a05:600c:807:b0:3dc:eaef:c1bb with SMTP id k7-20020a05600c080700b003dceaefc1bbmr17747243wmp.35.1676255375468; Sun, 12 Feb 2023 18:29:35 -0800 (PST) X-Google-Smtp-Source: AK7set+HRn39XPbz+We7XDXZ8pC6Lva0i+CXOixUrg9uDH6YJtB8bYiRhhCXYcds8gfBqJt4XY0dIA== X-Received: by 2002:a05:600c:807:b0:3dc:eaef:c1bb with SMTP id k7-20020a05600c080700b003dceaefc1bbmr17747234wmp.35.1676255375211; Sun, 12 Feb 2023 18:29:35 -0800 (PST) Received: from redhat.com ([46.136.252.173]) by smtp.gmail.com with ESMTPSA id j37-20020a05600c1c2500b003daf6e3bc2fsm22711207wms.1.2023.02.12.18.29.34 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 12 Feb 2023 18:29:34 -0800 (PST) From: Xxx Xx X-Google-Original-From: Xxx Xx To: qemu-devel@nongnu.org Cc: =?utf-8?q?Philippe_Mathieu-Daud=C3=A9?= , Thomas Huth , Juan Quintela , =?utf-8?q?Daniel_P=2E_Berrang=C3=A9?= , Cornelia Huck , "Dr. David Alan Gilbert" , kvm@vger.kernel.org, "Michael S. Tsirkin" , Paolo Bonzini , =?utf-8?q?Marc-Andr=C3=A9_Lureau?= , ling xu , Zhou Zhao , Jun Jin Subject: [PULL 13/22] Update bench-code for addressing CI problem Date: Mon, 13 Feb 2023 03:29:02 +0100 Message-Id: <20230213022911.68490-14-xxx.xx@gmail.com> X-Mailer: git-send-email 2.39.1 In-Reply-To: <20230213022911.68490-1-xxx.xx@gmail.com> References: <20230213022911.68490-1-xxx.xx@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org From: ling xu Unit test code is in test-xbzrle.c, and benchmark code is in xbzrle-bench.c for performance benchmarking. we have modified xbzrle-bench.c to address CI problem. Signed-off-by: ling xu Co-authored-by: Zhou Zhao Co-authored-by: Jun Jin Reviewed-by: Juan Quintela Signed-off-by: Juan Quintela --- tests/bench/xbzrle-bench.c | 469 +++++++++++++++++++++++++++++++++++++ tests/unit/test-xbzrle.c | 39 ++- tests/bench/meson.build | 6 + 3 files changed, 509 insertions(+), 5 deletions(-) create mode 100644 tests/bench/xbzrle-bench.c diff --git a/tests/bench/xbzrle-bench.c b/tests/bench/xbzrle-bench.c new file mode 100644 index 0000000000..8848a3a32d --- /dev/null +++ b/tests/bench/xbzrle-bench.c @@ -0,0 +1,469 @@ +/* + * 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 ef951b6e54..547046d093 100644 --- a/tests/unit/test-xbzrle.c +++ b/tests/unit/test-xbzrle.c @@ -16,6 +16,35 @@ #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; @@ -54,7 +83,7 @@ static void test_encode_decode_zero(void) buffer[1000 + diff_len + 5] = 105; /* encode zero page */ - dlen = xbzrle_encode_buffer(buffer, buffer, XBZRLE_PAGE_SIZE, compressed, + dlen = xbzrle_encode_buffer_func(buffer, buffer, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == 0); @@ -78,7 +107,7 @@ static void test_encode_decode_unchanged(void) test[1000 + diff_len + 5] = 109; /* test unchanged buffer */ - dlen = xbzrle_encode_buffer(test, test, XBZRLE_PAGE_SIZE, compressed, + dlen = xbzrle_encode_buffer_func(test, test, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == 0); @@ -96,7 +125,7 @@ static void test_encode_decode_1_byte(void) test[XBZRLE_PAGE_SIZE - 1] = 1; - dlen = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, + dlen = xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); g_assert(dlen == (uleb128_encode_small(&buf[0], 4095) + 2)); @@ -121,7 +150,7 @@ static void test_encode_decode_overflow(void) } /* encode overflow */ - rc = xbzrle_encode_buffer(buffer, test, XBZRLE_PAGE_SIZE, compressed, + rc = xbzrle_encode_buffer_func(buffer, test, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); g_assert(rc == -1); @@ -152,7 +181,7 @@ static void encode_decode_range(void) test[1000 + diff_len + 5] = 109; /* test encode/decode */ - dlen = xbzrle_encode_buffer(test, buffer, XBZRLE_PAGE_SIZE, compressed, + dlen = xbzrle_encode_buffer_func(test, buffer, XBZRLE_PAGE_SIZE, compressed, XBZRLE_PAGE_SIZE); rc = xbzrle_decode_buffer(compressed, dlen, test, XBZRLE_PAGE_SIZE); diff --git a/tests/bench/meson.build b/tests/bench/meson.build index 279a8fcc33..7477a1f401 100644 --- a/tests/bench/meson.build +++ b/tests/bench/meson.build @@ -3,6 +3,12 @@ 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 + executable('atomic_add-bench', sources: files('atomic_add-bench.c'), dependencies: [qemuutil],