From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id E620549331 for ; Sat, 8 Jun 2024 11:37:36 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 7D60C68D6B7; Sat, 8 Jun 2024 14:37:25 +0300 (EEST) Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 3956D68D64B for ; Sat, 8 Jun 2024 14:37:18 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id CE62FC02F9 for ; Sat, 8 Jun 2024 14:37:17 +0300 (EEST) From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Sat, 8 Jun 2024 14:37:16 +0300 Message-ID: <20240608113717.1677043-4-remi@remlab.net> X-Mailer: git-send-email 2.45.1 In-Reply-To: <20240608113717.1677043-1-remi@remlab.net> References: <20240608113717.1677043-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 4/4] lavu/riscv: use Zbb CLZ/CTZ/CLZW/CTZW at run-time X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: Zbb static Zbb dynamic I baseline clz 0.668032642 1.336072283 19.552376803 clzl 0.668092643 1.336181786 26.110855571 ctz 1.336208533 3.340209702 26.054869008 ctzl 1.336247784 3.340362457 26.055266290 (seconds for 1 billion iterations on a SiFive-U74 core) --- libavutil/riscv/intmath.h | 101 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 101 insertions(+) diff --git a/libavutil/riscv/intmath.h b/libavutil/riscv/intmath.h index 1f0afbc81d..3e7ab864c5 100644 --- a/libavutil/riscv/intmath.h +++ b/libavutil/riscv/intmath.h @@ -73,6 +73,107 @@ static av_always_inline av_const int av_clip_intp2_rvi(int a, int p) } #if defined (__GNUC__) || defined (__clang__) +static inline av_const int ff_ctz_rv(int x) +{ +#if HAVE_RV && !defined(__riscv_zbb) + if (!__builtin_constant_p(x) && + __builtin_expect(ff_rv_zbb_support(), true)) { + int y; + + __asm__ ( + ".option push\n" + ".option arch, +zbb\n" +#if __riscv_xlen >= 64 + "ctzw %0, %1\n" +#else + "ctz %0, %1\n" +#endif + ".option pop" : "=r" (y) : "r" (x)); + if (y > 32) + __builtin_unreachable(); + return y; + } +#endif + return __builtin_ctz(x); +} +#define ff_ctz ff_ctz_rv + +static inline av_const int ff_ctzll_rv(long long x) +{ +#if HAVE_RV && !defined(__riscv_zbb) && __riscv_xlen == 64 + if (!__builtin_constant_p(x) && + __builtin_expect(ff_rv_zbb_support(), true)) { + int y; + + __asm__ ( + ".option push\n" + ".option arch, +zbb\n" + "ctz %0, %1\n" + ".option pop" : "=r" (y) : "r" (x)); + if (y > 64) + __builtin_unreachable(); + return y; + } +#endif + return __builtin_ctzll(x); +} +#define ff_ctzll ff_ctzll_rv + +static inline av_const int ff_clz_rv(int x) +{ +#if HAVE_RV && !defined(__riscv_zbb) + if (!__builtin_constant_p(x) && + __builtin_expect(ff_rv_zbb_support(), true)) { + int y; + + __asm__ ( + ".option push\n" + ".option arch, +zbb\n" +#if __riscv_xlen >= 64 + "clzw %0, %1\n" +#else + "clz %0, %1\n" +#endif + ".option pop" : "=r" (y) : "r" (x)); + if (y > 32) + __builtin_unreachable(); + return y; + } +#endif + return __builtin_clz(x); +} +#define ff_clz ff_clz_rv + +#if __riscv_xlen == 64 +static inline av_const int ff_clzll_rv(long long x) +{ +#if HAVE_RV && !defined(__riscv_zbb) + if (!__builtin_constant_p(x) && + __builtin_expect(ff_rv_zbb_support(), true)) { + int y; + + __asm__ ( + ".option push\n" + ".option arch, +zbb\n" + "clz %0, %1\n" + ".option pop" : "=r" (y) : "r" (x)); + if (y > 64) + __builtin_unreachable(); + return y; + } +#endif + return __builtin_clzll(x); +} +#define ff_clz ff_clz_rv +#endif + +static inline av_const int ff_log2_rv(unsigned int x) +{ + return 31 - ff_clz_rv(x | 1); +} +#define ff_log2 ff_log2_rv +#define ff_log2_16bit ff_log2_rv + static inline av_const int av_popcount_rv(unsigned int x) { #if HAVE_RV && !defined(__riscv_zbb) -- 2.45.1 _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".