From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-ej1-f45.google.com (mail-ej1-f45.google.com [209.85.218.45]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E060D43802C for ; Fri, 31 Jul 2026 16:11:27 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.218.45 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1785514289; cv=none; b=sEMQy0nEwwsUm46fUu+ldLt0GfpkSFDMxbTZWBM+YJLLVQIIoaVkNdJ0db6I8UB7ihBobvBqVfkXnBCIUsvOkB8ABXygIeqJvN/FqlP/RFFHqb/V6A5HNmODaCqIlYunTnGPT8oVp9ivr7mr0Jm51C+wsAVpFXeiS6AFVbqVwEY= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1785514289; c=relaxed/simple; bh=lJBNukzCfSn494RM7h5Yt33NGkT8WA+QrxJx+dmL1xM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=odclnDRhQmg7cuJQJFed1LS6AZaXG/twIEy6gjR4z+fqJkvfyiruyUZReZi2TBfnHB7G4dfkqVqHGc9j9Qv17r7zbRtKXIUDW8j0ZZ9fOCmQo0sG+ig2ws8+7tqhI8CjXZsdlbcZaduys9GtgolIU6WbuVJi7osI74kydAQlfP0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=EVX4Mbei; arc=none smtp.client-ip=209.85.218.45 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="EVX4Mbei" Received: by mail-ej1-f45.google.com with SMTP id a640c23a62f3a-c16111a9b8dso15886566b.1 for ; Fri, 31 Jul 2026 09:11:27 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1785514286; x=1786119086; darn=vger.kernel.org; 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:content-type; bh=wNXKFZWI3u+GyO4UBU10scwv+ImHf9jHPS32+l+/nu8=; b=EVX4MbeiUjLoTCcrOAser4mKKCe5uXTNlxCS9M+dYse7P6fqHP6Dn5d9xZXdtzvcoz fOP9hxAFmFMwsiWZNd8YUNeeLdknwxq+GmoMdKTGr8/K5mC6OVjUipqD4K/zZ9j91/jx M1iDjusK+tM42BW2MpJ3/o0ZSoEE2qUAH6Yh8tJz2ijc88sosrJkEvvbgs737b6+oKPd ohXqb90zTk9xq/LaL9xt7rMYRrSmPs9AEmoll1LCoAe+bZlBWlZQVeTYw/qmYrdLKlAu FIZ8wcpEJTIIQRdugQFg4hkhn2629oz/XsXzf8pJOdGyOuEbCSf+ZIvuH+ZvqqoQaaoK czzw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1785514286; x=1786119086; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to:content-type; bh=wNXKFZWI3u+GyO4UBU10scwv+ImHf9jHPS32+l+/nu8=; b=o1WMRpdZHwUlHopcnDSDTB1C8Wp8fZVIHZfgD+qPxEzHb/Ymc+6eFFlF4vOyeVTD6E n3j4asksxUlB6BrCAga8CtOE1O8jpRoWhycbIANfIWxog1yIzTRukmTeTXspCQsZOriS zTROjpt9E+MK5T7efSweN3xx9KWTjXthqzntvsnBtebA/m3gziNMpkOrgtPPH4Nx9goq 1NeAUrjie8q0o6O5PJyUUpCrZ2Hp72fWsEyc6Ug0wPsOx2OErDVOGm80ithrsfz+6mte bMbrEl+Q1BW4nB62F92/wdvTMsGXS/DLeOpWl5rXzgWxVJ4O3ngcuB79+PBmFeAdvAMS H7zQ== X-Forwarded-Encrypted: i=1; AHgh+RprxIPRIDyhwrLw97Zh6fpH70xnKP80aUr3dBcsxpE7cp9DoNnh5cbPQPEikVDDtcO6t/aSzWtjA2n/G88=@vger.kernel.org X-Gm-Message-State: AOJu0Yxelpk4rJsrnr2MoqP98BkIrZcBqVm4nacZ9PIVK6Ew5bkQqm/U /goyMTYsVILXGDXss0nBXOJAHsZlGHQr1f/Ffr0gASRZyHtDzCSg4oQB X-Gm-Gg: AR+sD13oqxdtA5SzwSVBys49PbrRhiza5BVvhCEnuWuQBAtEX+iJL0TmTInFi0WXT45 b6nCdMU2uYHqbOv4Ey95xN/04pNjWuNxHocvjwIMGStjbMT95tIlYs6b+1W5TRJjMvk24Q+wH09 PMozy0bLzhB9kQjfTiMXi+l0FbtxxI5san6h1FqFOSKX8vBj0s2nvmGraN30gX8Hj0YMPTGrj2X TECD7PYWy6rNxORHwg/t60bGkqOrbbuUx81mkZXhpj7tU64qO6u9W5qHpDnN6qxHfaYH9moAVuL XzGO9yx8FLJdUle4YSlLSiYrRzsEeniTSWMFXIfVqCE921c3dIHjURNb7RWVapdfENizGp/+4X2 tYIz0APa1Ye8YxZE6meeWvwdHzxhZXi1gvXZeOzu5cRQubZWlyDpM/2Wi8/RVcO5alspahxaH6W gYYa1oayXOPX/N1REbZ6mWrrNWEoC6IptCD6DjbF42YlJdUuCxky/DnrYpu+oiSmE+01LyFgE/T jbD/DT9a8aNy8TfwGJNMrw5EEgkdMPLBP6uHO8Nrrp1HWj1R59rTISNciAGyLWTt0f+QDGziuFW o3M= X-Received: by 2002:a17:907:9616:b0:c15:ccda:26d5 with SMTP id a640c23a62f3a-c1fe8257a96mr18955666b.4.1785514285948; Fri, 31 Jul 2026 09:11:25 -0700 (PDT) Received: from OrangePi5-Plus.BB-HOME (20014C4E1B8B8B002291A327B8340D99.dsl.pool.telekom.hu. [2001:4c4e:1b8b:8b00:2291:a327:b834:d99]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-47fd45a1abfsm5826173f8f.37.2026.07.31.09.11.24 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 31 Jul 2026 09:11:25 -0700 (PDT) From: Igor Paunovic To: Jiaxing Hu Cc: Tomeu Vizoso , Heiko Stuebner , Oded Gabbay , Alexey Charkov , dri-devel@lists.freedesktop.org, linux-rockchip@lists.infradead.org, linux-kernel@vger.kernel.org, Igor Paunovic Subject: Re: [RFC PATCH v3 4/6] accel/rocket: add RK3576 NPU (RKNN) support Date: Fri, 31 Jul 2026 18:10:26 +0200 Message-ID: <20260731161026.22112-1-royalnet026@gmail.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260731043507.1832277-5-gahing@gahingwoo.com> References: <20260731043507.1832277-5-gahing@gahingwoo.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Hi Jiaxing, You mentioned you cannot exercise RK3588, so I ran this one on mine. Tested on RK3588 (Orange Pi 5 Plus, all three rknn cores). Applied on a v7.0-based Rockchip tree rather than next-20260730, so it went in with small offsets in rocket_job.c, but the RK3588 paths it touches are identical there. What I checked: - all three cores probe and report their version, runtime PM suspends and resumes them across a 60 s inference run; - a MobileNetV1 run through the Teflon TFLite delegate is bit-identical to the stock driver - five output tensors hashed every iteration, 4260 iterations, no mismatch; - throughput measured back to back against the unpatched module in the same session: 70.99 vs 71.18 inf/s, i.e. no change. (Both are above my usual ~68 baseline because the firmware happened to be serving the 200 MHz request from a different clock path that session - it is unrelated to your patch, which is why I measured the stock module again straight afterwards rather than reporting the first number.) Tested-by: Igor Paunovic I also went through the RK3588 side of the soc_data conversion, since that is the part your board cannot tell you about. All seven soc-> users keep RK3588 on its old values: num_clks 4 and num_resets 2 match the previous ARRAY_SIZE() results, and multi_power_domain and poll_completion are both false, so both new branches are skipped. Worth noting for anyone reading the diff quickly: growing clks[4] to clks[6] is exactly why num_clks had to become explicit - leaving ARRAY_SIZE() there would have made RK3588 ask for six clocks and fail probe. The conversion looks right to me. I am not commenting on the RK3576-specific parts - no hardware here for that - and I have not tested 2/6 and 3/6, since those are built in and would need a kernel rebuild. Thanks, Igor From mboxrd@z Thu Jan 1 00:00:00 1970 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 bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 13DB9C5516F for ; Fri, 31 Jul 2026 16:11:37 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-ID:Date:Subject:Cc:To:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=1v5v7dfnV8r7icavXUVO6r1i6hohQnsIH1pBYgaBBMQ=; b=FJCBnSM4z0vMVs NBTPRUGhGq08fGUsPi73Sb3LIaRmYBX1bH+nmIbJg9onyFtW1fbstHNN6RdudwZEyawARzAMc677q EMG5eX3F+C/dVEd8NFuRNuhVH4W+ZqH2eCsqfrSL+Wp+Blsm4hCoMJkkiUgCLffmdnUeImozlxZDb Fc5te+w1tMYMaTVmjO6tXG13MdCJ2lNwJJHUDpE+A0HxQvmWFDxZ3Gp4A2Dcwty+rTGExMOoSvdoF 1dmKreYPoju9e5YTFN8c2Vt/bXy+NXwXjzESlsxBAktPuDIdDmPuVNFQCo+z5728LqPqmNtHznBXn o/KkOvJZiLHWdZie7qtQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.99.1 #2 (Red Hat Linux)) id 1wpppb-0000000CxqP-2I8B; Fri, 31 Jul 2026 16:11:31 +0000 Received: from mail-ej1-x630.google.com ([2a00:1450:4864:20::630]) by bombadil.infradead.org with esmtps (Exim 4.99.1 #2 (Red Hat Linux)) id 1wpppY-0000000Cxp2-20AB for linux-rockchip@lists.infradead.org; Fri, 31 Jul 2026 16:11:29 +0000 Received: by mail-ej1-x630.google.com with SMTP id a640c23a62f3a-c160875e029so13935566b.3 for ; Fri, 31 Jul 2026 09:11:27 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1785514286; x=1786119086; darn=lists.infradead.org; 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:content-type; bh=wNXKFZWI3u+GyO4UBU10scwv+ImHf9jHPS32+l+/nu8=; b=tOeQw1/Fqi4989jI79/C67yT+2AKXQu0vaoRLs0ILpknGjzM3a94lZlA0hTTYz6tmO LEG63VW1yZNY8LMg00Rxv8YXPl/LEzUZQc279B1gy69+YWRUEpEoHSPc7I0a/331pO6D I1Lz+kLroKlMRNR7Fq6rDHAmPzC9mGve6izWG7PqtsZkhIUZ0gBEtzYqs878/U2Anff1 7e3S5TP+WDH4+aqyIcPXCaun8Ou2KmIdsrZFMrReKGIFHixwkChu085+gt9PjjkR0yHs QTUsuhwRIRgN9UwfdnkaAN9s7wsdyP1qGN1mPsS3+0PcAPuRyPWsJPeP+ipKN5JPW/Gs pktw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1785514286; x=1786119086; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to:content-type; bh=wNXKFZWI3u+GyO4UBU10scwv+ImHf9jHPS32+l+/nu8=; b=r2hhYUH6BjRMBMbz2KTD2hEj6xuPNhE7lkvwJX1t1tcsmG7/ZGmiIWVdzc7RO8rQuI /8ZcmC/I0KfoWY+pk+eEvMhJhmUP3IQSo9E7xOVvMg55kHY1TWrUJbGkBVPsKAIFy2b1 6LqWPPVY1qox1Le6eKMtF3ilpJC9Y383AOuEMtaj0jMS5kzcPGCYq44tH/kUUbBeZTXh +3g70Quzn+bniPoe1JiT77QgWZVEcEOXRdHRU6gO1mKCbw7Rqo3cCwaY2Ys31A3TGbrm BzTx4QFEtv/UrKgcnGLPARc1ddB8rvQgvYBCW+EXxt0YsnyVwFqkqK3Bw1lJO+u8xavC Qk8Q== X-Forwarded-Encrypted: i=1; AHgh+Rp5R1hHuWiwfnm7V5MTDOP++p2oruLqcAQGXY/5JjhHvIU8adDq1V+MAh231TpJGEleZjTfdBaNlvls1Cs2bw==@lists.infradead.org X-Gm-Message-State: AOJu0YwPJfOQy5QvC6Y8nUSsWTIou1pqNjgCRXfPbD6qwrH9BKVjko/u z89G0Af0aw3V0UTM6gs/XtLKyrjSfGHKEFJ2VfFqzahkWpuT5ArdfKLS+N06lNM8 X-Gm-Gg: AR+sD13KJNDW210I6/ZDmdBtp3eO7lAmj4YRS+IaLlJmldRJWIu8o43nQBJ/Ix0fJkY zxMt1cywRcTl1KSJn/SwnwoGSQXiReRoSkVfcE+Fhgw8Waqe84v+RLKrWdZMYzmNGrSeYlE//eW eFeACmxK2nNX2oD1xYjcSTqdemaVKtKbG77ImNq74t/dYBI3oA1JON5zeho3URPndvuuvKw03vD ls/bZboy9hfmAc7DkukJxO3eBi6EMZH1RvxH5Yvg3nHzlSLuzeCkpfLi1jw5VAn175lyXy85zLd UddYmUPr4k9obQl2LJb0GMfxCU/j0piT9h6DbW6dRTpo2Lkl46OSHajBj9dk5D6Dlb3pjcyA0Lz rVaZjH3A4ixbcYVIzA92nYtjwGAEMPgxMOEjZ+jcedJeg0rqXqAigF8sL2oprU6R7otrv+H+BmP FY5ubugWYrrGVfC9KurFEB2MOwOLpyK5LWgyTBoi6Xu3I0wvDGpfZUeVwGFFVyxkG6YhMpXwrlT lJkCfcGsweTwxMIDnH38uxExi7YlkfY7uaENzkbRiup40GyMVsVZbLyslETHVgT3OgWrNKKO5eZ 94w= X-Received: by 2002:a17:907:9616:b0:c15:ccda:26d5 with SMTP id a640c23a62f3a-c1fe8257a96mr18955666b.4.1785514285948; Fri, 31 Jul 2026 09:11:25 -0700 (PDT) Received: from OrangePi5-Plus.BB-HOME (20014C4E1B8B8B002291A327B8340D99.dsl.pool.telekom.hu. [2001:4c4e:1b8b:8b00:2291:a327:b834:d99]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-47fd45a1abfsm5826173f8f.37.2026.07.31.09.11.24 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 31 Jul 2026 09:11:25 -0700 (PDT) From: Igor Paunovic To: Jiaxing Hu Cc: Tomeu Vizoso , Heiko Stuebner , Oded Gabbay , Alexey Charkov , dri-devel@lists.freedesktop.org, linux-rockchip@lists.infradead.org, linux-kernel@vger.kernel.org, Igor Paunovic Subject: Re: [RFC PATCH v3 4/6] accel/rocket: add RK3576 NPU (RKNN) support Date: Fri, 31 Jul 2026 18:10:26 +0200 Message-ID: <20260731161026.22112-1-royalnet026@gmail.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260731043507.1832277-5-gahing@gahingwoo.com> References: <20260731043507.1832277-5-gahing@gahingwoo.com> MIME-Version: 1.0 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.9.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20260731_091128_530836_0A9151F5 X-CRM114-Status: GOOD ( 12.90 ) X-BeenThere: linux-rockchip@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: Upstream kernel work for Rockchip platforms List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "Linux-rockchip" Errors-To: linux-rockchip-bounces+linux-rockchip=archiver.kernel.org@lists.infradead.org Hi Jiaxing, You mentioned you cannot exercise RK3588, so I ran this one on mine. Tested on RK3588 (Orange Pi 5 Plus, all three rknn cores). Applied on a v7.0-based Rockchip tree rather than next-20260730, so it went in with small offsets in rocket_job.c, but the RK3588 paths it touches are identical there. What I checked: - all three cores probe and report their version, runtime PM suspends and resumes them across a 60 s inference run; - a MobileNetV1 run through the Teflon TFLite delegate is bit-identical to the stock driver - five output tensors hashed every iteration, 4260 iterations, no mismatch; - throughput measured back to back against the unpatched module in the same session: 70.99 vs 71.18 inf/s, i.e. no change. (Both are above my usual ~68 baseline because the firmware happened to be serving the 200 MHz request from a different clock path that session - it is unrelated to your patch, which is why I measured the stock module again straight afterwards rather than reporting the first number.) Tested-by: Igor Paunovic I also went through the RK3588 side of the soc_data conversion, since that is the part your board cannot tell you about. All seven soc-> users keep RK3588 on its old values: num_clks 4 and num_resets 2 match the previous ARRAY_SIZE() results, and multi_power_domain and poll_completion are both false, so both new branches are skipped. Worth noting for anyone reading the diff quickly: growing clks[4] to clks[6] is exactly why num_clks had to become explicit - leaving ARRAY_SIZE() there would have made RK3588 ask for six clocks and fail probe. The conversion looks right to me. I am not commenting on the RK3576-specific parts - no hardware here for that - and I have not tested 2/6 and 3/6, since those are built in and would need a kernel rebuild. Thanks, Igor _______________________________________________ Linux-rockchip mailing list Linux-rockchip@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-rockchip