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 ED05F4B553 for ; Sat, 8 Jun 2024 11:37:53 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 1C50C68D6DA; Sat, 8 Jun 2024 14:37:28 +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 487F468D6A1 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 6F272C006C 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 14:37:14 +0300 Message-ID: <20240608113717.1677043-2-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 2/4] lavu/riscv: use Zbb REV8 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: This adds runtime support to use Zbb REV8 for 32- and 64-bit byte-wise swaps. The result is about five times slower than if targetting Zbb statically, but still a lot faster than the default bespoke C code or a call to GCC run-time functions. For 16-bit swap, this is however unsurprisingly a lot worse, and so this sticks to the baseline. In fact, even using REV8 statically does not seem to be beneficial in that case. Zbb static Zbb dynamic I baseline bswap16: 0.668184765 3.340764069 0.668029012 bswap32: 0.668174014 3.340763319 9.353855435 bswap64: 0.668221765 3.340496313 14.698672283 (seconds for 1 billion iterations on a SiFive-U74 core) --- libavutil/riscv/bswap.h | 44 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 42 insertions(+), 2 deletions(-) diff --git a/libavutil/riscv/bswap.h b/libavutil/riscv/bswap.h index ce75de974e..886893e241 100644 --- a/libavutil/riscv/bswap.h +++ b/libavutil/riscv/bswap.h @@ -22,11 +22,51 @@ #include #include "config.h" #include "libavutil/attributes.h" +#include "libavutil/riscv/cpu.h" #if defined (__GNUC__) || defined (__clang__) #define av_bswap16 __builtin_bswap16 -#define av_bswap32 __builtin_bswap32 -#define av_bswap64 __builtin_bswap64 + +static av_always_inline av_const uint32_t av_bswap32_rv(uint32_t x) +{ +#if HAVE_RV && !defined(__riscv_zbb) + if (!__builtin_constant_p(x) && + __builtin_expect(ff_rv_zbb_support(), 1)) { + uintptr_t y; + + __asm__ ( + ".option push\n" + ".option arch, +zbb\n" + "rev8 %0, %1\n" + ".option pop" : "=r" (y) : "r" (x)); + return y >> (__riscv_xlen - 32); + } +#endif + return __builtin_bswap32(x); +} +#define av_bswap32 av_bswap32_rv + +#if __riscv_xlen >= 64 +static av_always_inline av_const uint64_t av_bswap64_rv(uint64_t x) +{ +#if HAVE_RV && !defined(__riscv_zbb) + if (!__builtin_constant_p(x) && + __builtin_expect(ff_rv_zbb_support(), 1)) { + uintptr_t y; + + __asm__ ( + ".option push\n" + ".option arch, +zbb\n" + "rev8 %0, %1\n" + ".option pop" : "=r" (y) : "r" (x)); + return y >> (__riscv_xlen - 64); + } +#endif + return __builtin_bswap64(x); +} +#define av_bswap64 av_bswap64_rv +#endif + #endif #endif /* AVUTIL_RISCV_BSWAP_H */ -- 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".