[libre-riscv-dev] Some recent documenting of work performed for tape-out
[libre-riscv-dev.git] / 6f / 43ac86b9a244302de1e8121b687f9c06311b9b
1 Return-path: <libre-riscv-dev-bounces@lists.libre-riscv.org>
2 Envelope-to: publicinbox@libre-riscv.org
3 Delivery-date: Tue, 24 Mar 2020 12:23:47 +0000
4 Received: from localhost ([::1] helo=libre-riscv.org)
5 by libre-riscv.org with esmtp (Exim 4.89)
6 (envelope-from <libre-riscv-dev-bounces@lists.libre-riscv.org>)
7 id 1jGiaw-0002QH-KX; Tue, 24 Mar 2020 12:23:46 +0000
8 Received: from isis.lip6.fr ([132.227.60.2])
9 by libre-riscv.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)
10 (Exim 4.89) (envelope-from <Jean-Paul.Chaput@lip6.fr>)
11 id 1jGiav-0002QB-Pb
12 for libre-riscv-dev@lists.libre-riscv.org; Tue, 24 Mar 2020 12:23:45 +0000
13 Received: from asim.lip6.fr (asim.lip6.fr [132.227.86.2])
14 by isis.lip6.fr (8.15.2/8.15.2) with ESMTPS id 02OCNjsu007285
15 (version=TLSv1.2 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO)
16 for <libre-riscv-dev@lists.libre-riscv.org>;
17 Tue, 24 Mar 2020 13:23:45 +0100 (CET)
18 Received: from localhost (melon [132.227.103.13])
19 by asim.lip6.fr (8.15.2/8.14.4) with ESMTP id 02OCNib4011025
20 for <libre-riscv-dev@lists.libre-riscv.org>;
21 Tue, 24 Mar 2020 13:23:44 +0100 (MET)
22 Message-ID: <686f9b58ae6f6a3e11caff9714db66a0406e8b0b.camel@lip6.fr>
23 From: Jean-Paul Chaput <Jean-Paul.Chaput@lip6.fr>
24 To: Libre-RISCV General Development <libre-riscv-dev@lists.libre-riscv.org>
25 Date: Tue, 24 Mar 2020 13:23:36 +0100
26 In-Reply-To: <0F80A1BC-0241-49FE-B374-B4F1D8F3F5BD@gatech.edu>
27 References: <0F80A1BC-0241-49FE-B374-B4F1D8F3F5BD@gatech.edu>
28 Organization: UPMC
29 X-Mailer: Evolution 3.28.5 (3.28.5-5.el7)
30 Mime-Version: 1.0
31 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.4.3
32 (isis.lip6.fr [132.227.60.2]); Tue, 24 Mar 2020 13:23:45 +0100 (CET)
33 X-Scanned-By: MIMEDefang 2.78 on 132.227.60.2
34 X-Content-Filtered-By: Mailman/MimeDel 2.1.23
35 Subject: Re: [libre-riscv-dev] Advanced Topics on RISCV
36 X-BeenThere: libre-riscv-dev@lists.libre-riscv.org
37 X-Mailman-Version: 2.1.23
38 Precedence: list
39 List-Id: Libre-RISCV General Development
40 <libre-riscv-dev.lists.libre-riscv.org>
41 List-Unsubscribe: <http://lists.libre-riscv.org/mailman/options/libre-riscv-dev>,
42 <mailto:libre-riscv-dev-request@lists.libre-riscv.org?subject=unsubscribe>
43 List-Archive: <http://lists.libre-riscv.org/pipermail/libre-riscv-dev/>
44 List-Post: <mailto:libre-riscv-dev@lists.libre-riscv.org>
45 List-Help: <mailto:libre-riscv-dev-request@lists.libre-riscv.org?subject=help>
46 List-Subscribe: <http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev>,
47 <mailto:libre-riscv-dev-request@lists.libre-riscv.org?subject=subscribe>
48 Reply-To: Libre-RISCV General Development
49 <libre-riscv-dev@lists.libre-riscv.org>
50 Content-Type: multipart/mixed; boundary="===============1176392427724861224=="
51 Errors-To: libre-riscv-dev-bounces@lists.libre-riscv.org
52 Sender: "libre-riscv-dev" <libre-riscv-dev-bounces@lists.libre-riscv.org>
53
54
55 --===============1176392427724861224==
56 Content-Type: multipart/signed; micalg="pgp-sha1"; protocol="application/pgp-signature";
57 boundary="=-uMTCeTJLxmVTQeWr/JCW"
58
59
60 --=-uMTCeTJLxmVTQeWr/JCW
61 Content-Type: text/plain; charset="UTF-8"
62 Content-Transfer-Encoding: quoted-printable
63
64
65
66 Hello Immanuel,
67
68 About manycores, we did a lot of work on that topic in our lab
69 (Sorbonne Universit=C3=A9/LIP6). I send you a reference toward the
70 project we developed. This is a huge lot of work and may take
71 a lot of time to understand. But, we made a real chip with
72 16 cores to prove it works (and it do work). I cannot give you
73 more technical information as it not my field of expertise.
74
75 You must distinguish two case:
76
77 * Multi cores ( < 16) in that case, simpler solutions can be
78 used.
79
80 * Many cores ( > 16) in this case, the TSAR project can be
81 of interest.
82
83 TSAR (Tera-Scale ARchitecture).
84
85 You can see details here:
86 https://www-soc.lip6.fr/trac/tsar
87
88 Best regards,
89
90
91 PS: Already signaled it to Luke.
92
93
94 On Tue, 2020-03-24 at 11:51 +0000, Immanuel, Yehowshua U wrote:
95 > I=E2=80=99ve read through the Spike page and a good portion of the simple=
96 V page.
97 >=20
98 > My two goals at the moment are:
99 > 1. Understand how RISCV handles multiple processes and does page walking
100 > 2. Understand how multicore ROSCV would work
101 >=20
102 > I=E2=80=99m hoping to play with FreeRTOS soon so I can run through its co=
103 debase for setting up
104 > page tables.
105 > Also, do you know if spike tests the special instructions like exception =
106 instructions?
107 > Also, what RISCV instructions would a kernel use to set up the pagetables=
108 ?
109 >=20
110 > Lastly, do you know any good resources for intro to multicore systems? RI=
111 SCV doesn=E2=80=99t
112 > seem to have any multicore specific instructions. My current questions wo=
113 uld include
114 > things like:
115 >=20
116 > 1. How can the kernel assign tasks to a certain core? If you have a proce=
117 ss with
118 > multiple threads, it would make sense to spread out the threads among ava=
119 ilable
120 > processors instead of concentrating them on a single core. How might this=
121 work with
122 > respect to RISCV?
123 >=20
124 > 2. Does the hardware ensure cache coherency - that is - externally - soft=
125 ware sees one
126 > big cache all though I imagine each core would have a local cache that wo=
127 uld have to
128 > communicate with other caches?
129 >=20
130 > Yehowshua
131 > _______________________________________________
132 > libre-riscv-dev mailing list
133 > libre-riscv-dev@lists.libre-riscv.org
134 > http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev
135 --=20
136
137 .-. J e a n - P a u l C h a p u t / Administrateur Systeme
138 /v\ Jean-Paul.Chaput@lip6.fr
139 /(___)\ work: (33) 01.44.27.53.99 =20
140 ^^ ^^ cell: 06.66.25.35.55 home: 09.65.29.83.38
141
142 U P M C Universite Pierre & Marie Curie
143 L I P 6 Laboratoire d'Informatique de Paris VI
144 S o C System On Chip
145
146 --=-uMTCeTJLxmVTQeWr/JCW--
147
148
149
150 --===============1176392427724861224==
151 Content-Type: text/plain; charset="utf-8"
152 MIME-Version: 1.0
153 Content-Transfer-Encoding: base64
154 Content-Disposition: inline
155
156 X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KbGlicmUtcmlz
157 Y3YtZGV2IG1haWxpbmcgbGlzdApsaWJyZS1yaXNjdi1kZXZAbGlzdHMubGlicmUtcmlzY3Yub3Jn
158 Cmh0dHA6Ly9saXN0cy5saWJyZS1yaXNjdi5vcmcvbWFpbG1hbi9saXN0aW5mby9saWJyZS1yaXNj
159 di1kZXYK
160
161 --===============1176392427724861224==--
162
163
164