| /freebsd/share/doc/papers/diskperf/ |
| H A D | motivation.ms | 39 cost competitive
46 Winchester disk drive represents the lowest cost-per-byte disk storage
52 In addition to the direct motivation of developing an effective
67 Is the access optimization as effective as that already provided
|
| H A D | conclusions.ms | 41 Perhaps in some I/O-intensive applications such as
47 Cost, reliability, availability, and support are some of these
54 The first is that buffering can be effective in smoothing
66 (about 10-14%).
105 the National Science Foundation under grant MCS80-05144,
108 Contract No. N00039-82-C-0235.
119 pp 181-197, August 1984.
|
| /freebsd/contrib/jemalloc/include/jemalloc/internal/ |
| H A D | rtree_tsd.h | 10 * that this cache can directly cover, the cache will become less effective if
14 * The L1 direct mapped cache offers consistent and low cost on cache hit.
16 * combining with a L2 LRU cache, which requires linear search and re-ordering
18 * cache misses if made overly large, plus the cost of linear search in the LRU
|
| H A D | arena_structs_b.h | 18 /* Synchronizes all non-atomic fields. */
53 * advancement we use the delta between arena->decay_*.nunpurged and
54 * extents_npages_get(&arena->extents_*) to determine how many dirty
80 * two distinct assignments, one for application-serving allocation, and
97 * When percpu_arena is enabled, to amortize the cost of reading /
160 * used when allocating extents, in an attempt to re-use address space.
169 * Decay-based purging state, responsible for scheduling extent state
174 arena_decay_t decay_dirty; /* dirty --> muzzy */
175 arena_decay_t decay_muzzy; /* muzzy --> retained */
181 * be effective even if multiple arenas' extent allocation requests are
[all …]
|
| /freebsd/share/doc/papers/kerntune/ |
| H A D | 3.t | 115 The cost of doing name translation in the original 4.2BSD
161 The cost of the cache is about 20 lines of code
167 cache we ran ``ls \-l''
169 Before the per-process cache this command
195 Figure 4. Call times for \fInamei\fP with per-process cache.
201 Although the cache was 90% effective when hit,
225 then the per-process cache may still be useful in
229 The cost of the name cache is about 200 lines of code
234 using 10-44 kilobytes of physical memory.
237 After adding the system wide name cache we reran ``ls \-l''
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/net/ |
| H A D | davicom,dm9051.yaml | 1 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
3 ---
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
10 - Joseph CHANG <josright123@gmail.com>
13 The DM9051 is a fully integrated and cost-effective low pin count single
17 - $ref: ethernet-controller.yaml#
26 spi-max-frequency:
32 local-mac-address: true
34 mac-address: true
37 - compatible
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/nds32/ |
| H A D | andestech-boards | 2 -----------------------------------------------------------------------------
7 - compatible = "andestech,ae3xx";
10 /dts-v1/;
13 #address-cells = <1>;
14 #size-cells = <1>;
15 interrupt-parent = <&intc>;
19 -----------------------------------------------------------------------------
21 processors to provide a cost-effective and high performance solution for
28 system environment for early prototyping and software/hardware co-development.
34 /dts-v1/;
[all …]
|
| /freebsd/share/doc/smm/05.fastfs/ |
| H A D | 4.t | 37 been effective.
68 The systems were running multi-user but were otherwise quiescent.
95 Table 2a \- Reading rates of the old and new UNIX file systems.
110 Table 2b \- Writing rates of the old and new UNIX file systems.
126 of the effective utilization of the disk by the file system.
133 able to use about 3\-5% of the disk bandwidth,
144 The net effect is that the cost per byte allocated is about
172 non-optimal seek order in which they are requested.
185 The cost of allocation is the factor in the new system that
|
| /freebsd/contrib/llvm-project/llvm/lib/Transforms/Vectorize/ |
| H A D | LoopVectorizationPlanner.h | 1 //===- LoopVectorizationPlanner.h - Planner for LoopVectorization ---------===//
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
7 //===----------------------------------------------------------------------===//
12 /// LoopVectorizationPlanner - drives the vectorization process after having
16 /// control-flow of the vectorized version, the replication of instructions that
19 /// Also provides a VPlan-based builder utility analogous to IRBuilder.
20 /// It provides an instruction-level API for generating VPInstructions while
22 //===----------------------------------------------------------------------===//
44 /// VPlan-based builder utility analogous to IRBuilder.
52 BB->insert(VPI, InsertPt); in tryInsertInstruction()
[all …]
|
| H A D | LoopVectorize.cpp | 1 //===- LoopVectorize.cpp - A Loop Vectorizer ------------------------------===//
5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
7 //===----------------------------------------------------------------------===//
10 // and generates target-independent LLVM-IR.
20 // 2. LoopVectorizationLegality - A unit that checks for the legality
22 // 3. InnerLoopVectorizer - A unit that performs the actual
24 // 4. LoopVectorizationCostModel - A unit that checks for the profitability
31 // http://lists.llvm.org/pipermail/llvm-dev/2017-December/119523.html). For this
32 // purpose, we temporarily introduced the VPlan-native vectorization path: an
36 //===----------------------------------------------------------------------===//
[all …]
|
| /freebsd/share/doc/smm/18.net/ |
| H A D | e.t | 40 is kept in page-sized units on page-aligned
110 cost effective only when sizable packets are used. The
|
| /freebsd/sys/contrib/vchiq/interface/vchi/ |
| H A D | vchi_cfg.h | 2 * Copyright (c) 2010-2012 Broadcom. All rights reserved.
13 * 3. The names of the above-listed copyright holders may not be used
43 /* Really determined by the message driver, and should be available from a run-time call. */
54 /* Really determined by the message driver, and should be available from a run-time call. */
77 * 1 for host-app, 1 for VMCS, and these are hooked together by a loopback MPHI VCFW
83 /* How many services can we open per connection? Extending this doesn't cost processing time, just …
99 /* How many receive slots do we use. This times VCHI_MAX_MSG_SIZE gives the effective
122 * transmitting with an XOFF message. For this to be effective, the VCHI_NUM_READ_SLOTS
144 /* Maximum size of bulk transmission chunks, for each interface type. A trade-off between
154 * with multiple-line frames. Only use if the receiver can cope. */
[all …]
|
| /freebsd/contrib/ncurses/ncurses/tty/ |
| H A D | hashmap.c | 2 * Copyright 2019-2020,2023 Thomas E. Dickey *
3 * Copyright 1998-2015,2016 Free Software Foundation, Inc. *
31 * Author: Zeyd M. Ben-Halim <zmbenhal@netcom.com> 1992,1995 *
38 hashmap.c -- fill in scramble vector based on text hashes
47 vertical-motion optimizer portion of the update logic (see hardscroll.c).
63 $(CC) -g -DHASHDEBUG hashmap.c hardscroll.c ../objects/lib_trace.o -o hashmap
101 # define OLDNUM(sp,n) (sp)->_oldnum_list[n]
102 # define OLDTEXT(sp,n) CurScreen(sp)->_line[n].text
103 # define NEWTEXT(sp,m) NewScreen(sp)->_line[m].text
104 # define TEXTWIDTH(sp) (CurScreen(sp)->_maxx + 1)
[all …]
|
| H A D | lib_mvcur.c | 2 * Copyright 2018-2022,2023 Thomas E. Dickey *
3 * Copyright 1998-2016,2017 Free Software Foundation, Inc. *
31 * Author: Zeyd M. Ben-Halim <zmbenhal@netcom.com> 1992,1995 *
33 * and: Thomas E. Dickey 1996-on *
54 ** enough, it doesn't use its own hardware-scrolling routine to scroll up
55 ** destination lines for out-of-bounds addresses!
56 ** old ncurses optimizer: less accurate cost computations (in fact,
59 ** Compile with -DMAIN to build an interactive tester/timer for the movement
65 ** exercises the non-cup movement capabilities heavily. If you think you've
72 ** cost swamps the computation overhead (and as machines get faster, this
[all …]
|
| /freebsd/contrib/llvm-project/llvm/lib/Target/ARM/ |
| H A D | ARMFeatures.td | 1 //===----------------------------------------------------------------------===//
6 def ModeThumb : SubtargetFeature<"thumb-mode", "IsThumb",
10 def ModeSoftFloat : SubtargetFeature<"soft-float","UseSoftFloat",
14 //===----------------------------------------------------------------------===//
21 string TargetFeatureName, // String used for -target-feature.
32 // FP loads/stores/moves, shared between VFP and MVE (even in the integer-only
37 // 16-bit FP loads/stores/moves, shared between VFP (with the v8.2A FP16
38 // extension) and MVE (even in the integer-only version).
40 "Enable 16-bit FP registers",
44 "Enable 64-bit FP registers",
[all …]
|
| /freebsd/sys/contrib/zstd/ |
| H A D | README.md | 4 targeting real-time compression scenarios at zlib-level and better compression ratios.
8 This repository represents the reference implementation, provided as an open-source dual [BSD](LICE…
11 a list of known ports and bindings is provided on [Zstandard homepage](http://www.zstd.net/#other-l…
21 [travisDevBadge]: https://api.travis-ci.com/facebook/zstd.svg?branch=dev "Continuous Integration te…
22 [travisLink]: https://travis-ci.com/facebook/zstd
24 [AppveyorLink]: https://ci.appveyor.com/project/YannCollet/zstd-p0yf0
27 [CirrusDevBadge]: https://api.cirrus-ci.com/github/facebook/zstd.svg?branch=dev
28 [CirrusLink]: https://cirrus-ci.com/github/facebook/zstd
29 [OSSFuzzBadge]: https://oss-fuzz-build-logs.storage.googleapis.com/badges/zstd.svg
30 [OSSFuzzLink]: https://bugs.chromium.org/p/oss-fuzz/issues/list?sort=-opened&can=1&q=proj:zstd
[all …]
|
| /freebsd/usr.sbin/acpi/acpidump/ |
| H A D | acpidump.8 | 101 .Bl -tag -offset indent -width 12345 -compact
135 .It MCFG PCI Express Memory-mapped Configuration
145 Provides information about the cost of communicating between different
168 the DSDT consists of free-formatted AML data.
172 .Bl -tag -width indent
195 are specified, the last option is effective.
207 .Bl -tag -width /dev/mem
213 .Bd -literal -offset indent
214 # acpidump -dt | gzip -c9 > my_computer.asl.gz
221 .Bd -literal -offset indent
[all …]
|
| /freebsd/contrib/llvm-project/lld/docs/ |
| H A D | NewLLD.rst | 5 ---------------------------
23 ------------
29 We believe that these high-level design choices achieved a right balance
37 Sharing code makes sense if the benefit is worth its cost.
39 to abstract the differences wouldn't be worth its complexity and run-time
40 cost. Elimination of the abstract layer has greatly simplified the
47 Therefore, the high-level design matters more than local optimizations.
48 Since we are trying to create a high-performance linker,
71 - If the linker visits an object file, the linker links object files to the
74 - If the linker visits an archive file, it checks for the archive file's
[all …]
|
| /freebsd/share/doc/papers/sysperf/ |
| H A D | 4.t | 62 translating path names to inodes\u\s-21\s0\d\**.
64 \** \u\s-21\s0\d Inode is an abbreviation for ``Index node''.
95 The cost of the cache is about 20 lines of code
101 cache we ran ``ls \-l''
103 Before the per-process cache this command
129 Table 9. Call times for \fInamei\fP with per-process cache.
135 Although the cache was 90% effective when hit,
161 maintained a simple name-inode association that was used to
194 by a \fIcapability\fP \- a 32-bit number
195 guaranteed to be unique\u\s-22\s0\d \**.
[all …]
|
| /freebsd/sys/contrib/openzfs/ |
| H A D | LICENSE | 5 --------------------------------------------------------------------
84 Developer hereby grants You a world-wide, royalty-free,
85 non-exclusive license:
100 effective on the date Initial Developer first distributes
115 Contributor hereby grants You a world-wide, royalty-free,
116 non-exclusive license:
137 effective on the date Contributor first distributes or
265 PURPOSE OR NON-INFRINGING. THE ENTIRE RISK AS TO THE QUALITY AND
268 INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE COST OF ANY
328 C.F.R. 252.227-7014(a)(1)) and "commercial computer software
[all …]
|
| /freebsd/sys/cddl/contrib/opensolaris/ |
| H A D | OPENSOLARIS.LICENSE | 5 --------------------------------------------------------------------
84 Developer hereby grants You a world-wide, royalty-free,
85 non-exclusive license:
100 effective on the date Initial Developer first distributes
115 Contributor hereby grants You a world-wide, royalty-free,
116 non-exclusive license:
137 effective on the date Contributor first distributes or
265 PURPOSE OR NON-INFRINGING. THE ENTIRE RISK AS TO THE QUALITY AND
268 INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE COST OF ANY
328 C.F.R. 252.227-7014(a)(1)) and "commercial computer software
[all …]
|
| /freebsd/cddl/contrib/opensolaris/ |
| H A D | OPENSOLARIS.LICENSE | 5 --------------------------------------------------------------------
84 Developer hereby grants You a world-wide, royalty-free,
85 non-exclusive license:
100 effective on the date Initial Developer first distributes
115 Contributor hereby grants You a world-wide, royalty-free,
116 non-exclusive license:
137 effective on the date Contributor first distributes or
265 PURPOSE OR NON-INFRINGING. THE ENTIRE RISK AS TO THE QUALITY AND
268 INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE COST OF ANY
328 C.F.R. 252.227-7014(a)(1)) and "commercial computer software
[all …]
|
| /freebsd/contrib/ntp/html/ |
| H A D | audio.html | 1 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
4 <meta http-equiv="content-type" content="text/html;charset=iso-8859-1">
11 <img src="pic/radio2.jpg" alt="jpg" align="left">ICOM R-72 shortwave receiver and Sure audio mixer
13 <!-- #BeginDate format:En2m -->11-Sep-2010 05:55<!-- #EndDate -->
31 and decoding techniques, including maximum-likelihood and soft-decision methods.
32 The documentation page for each driver contains an in-depth discussion on
36 …, the signal level must be in the range where the audio gain control is effective. In general, thi…
38 …e flag 2</tt> command selects the microphone port if set to zero or the line-in port if set to one…
40 …l shortwave radio with the radio output - speaker or headphone jack - connected to either the micr…
41 …- even 15 feet is enough if it is located outside of a metal frame building, preferably on the roo…
[all …]
|
| /freebsd/crypto/libecc/src/nn/ |
| H A D | nn.c | 2 * Copyright (C) 2017 - This file is part of libecc project
7 * Jean-Pierre FLORI <jean-pierre.flori@ssi.gouv.fr>
41 * Due to its performance cost, this consistency check is used
44 * (error in -Werror) is triggered at compilation time.
52 for (i = A->wlen; i < NN_MAX_WORD_LEN; i++) { in __nn_is_wlen_consistent()
53 val |= (A)->val[i]; in __nn_is_wlen_consistent()
62 * received as parameter. Returns 0 on success, -1 on error.
69 MUST_HAVE((A->magic == NN_MAGIC), ret, err); in nn_check_initialized()
70 MUST_HAVE((A->wlen <= NN_MAX_WORD_LEN), ret, err); in nn_check_initialized()
82 * on success, -1 on error.
[all …]
|
| /freebsd/sbin/routed/ |
| H A D | routed.8 | 84 deletes all pre-existing
85 non-static routes in kernel table.
87 included in RIP responses if they have a valid RIP -hopcount
118 is an effective way to steer traffic.
127 .Em split-horizon .
167 .Em black-holes .
181 to the destination address on point-to-point links, and to the router's
201 a good Advertisement and it is not multi-homed,
208 if multi-homed to ensure all interfaces are used.
230 Thus, multi-homed hosts running with
[all …]
|