/freebsd/share/man/man3/ |
H A D | bitstring.3 | 82 .Nd bit-string manipulation functions and macros 169 clear or set the zero-based numbered bit 179 set or clear the zero-based numbered bits from 189 evaluates to non-zero if the zero-based numbered bit 198 evaluates to non-zero if the zero-based numbered bits from 211 the zero-based number of the first bit not set in the array of 217 is set to \-1. 224 the zero-based number of the first bit set in the array of 230 is set to \-1. 236 the zero-based number of the first bit not set in the array of [all …]
|
/freebsd/contrib/llvm-project/clang/lib/CodeGen/ |
H A D | CGRecordLayout.h | 1 //===--- CGRecordLayout.h - LLVM Record Layout Information ------*- C++ -*-===// 5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception 7 //===----------------------------------------------------------------------===// 27 /// Often we layout a sequence of bitfields as a contiguous sequence of bits. 34 /// into a single integer of that size (i24 or i40 -- may not be power-of-two 38 /// The CGRecordLayout also has a field index which encodes which byte-sequence 49 /// bitfield, and the second is the padding out to a 4-byte alignment. 66 /// The offset within a contiguous run of bitfields that are represented as 70 /// The total size of the bit-field, in bits. 73 /// Whether the bit-field is signed. [all …]
|
/freebsd/contrib/llvm-project/lld/docs/ELF/ |
H A D | linker_script.rst | 47 section-command 48 section-command 52 Each section-command can be a symbol assignment, an output section description, 61 command is followed by ``INSERT``, LLD applies built-in rules which are similar 64 - Align the first section in a ``PT_LOAD`` segment according to 65 ``-z noseparate-code``, ``-z separate-code``, or 66 ``-z separate-loadable-segments`` 67 - Define ``__bss_start``, ``end``, ``_end``, ``etext``, ``_etext``, ``edata``, 69 - Sort ``.ctors.*``/``.dtors.*``/``.init_array.*``/``.fini_array.*`` and 71 - Place input ``.text.*`` into output ``.text``, and handle certain variants [all …]
|
/freebsd/contrib/llvm-project/llvm/lib/Target/AMDGPU/ |
H A D | GCNNSAReassign.cpp | 1 //===-- GCNNSAReassign.cpp - Reassign registers in NSA instructions -------===// 5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception 7 //===----------------------------------------------------------------------===// 10 /// \brief Try to reassign registers on GFX10+ from non-sequential to sequential 14 //===----------------------------------------------------------------------===// 29 #define DEBUG_TYPE "amdgpu-nsa-reassign" 32 "Number of NSA instructions with non-sequential address found"); 62 NON_CONTIGUOUS, // NSA with non-sequential address which we can try 64 CONTIGUOUS // NSA with all sequential address registers 114 if (VRM->hasPhys(Intervals[N]->reg())) in tryAssignRegisters() [all …]
|
/freebsd/share/man/man9/ |
H A D | crypto_buffer.9 | 128 invokes a caller-supplied function 150 returns a non-zero value, 166 attempts to locate a single, virtually-contiguous segment of the data buffer 179 attempts to locate a single, virtually-contiguous segment in the input data 189 .Bl -tag -width " CRYPTO_BUF_CONTIG" 213 The structure also contains the following type-specific fields: 214 .Bl -tag -width " cb_vm_page_offset" 298 returns the start of the virtually-contiguous segment at the current position of 306 return the return value from the caller-supplied callback function. 312 return a pointer to a contiguous segment or [all …]
|
H A D | copy.9 | 65 functions are designed to copy contiguous data from one address space 80 bytes of data from the user-space address 82 to the kernel-space address 91 bytes of data from the kernel-space address 93 to the user-space address 100 functions require that the kernel-space and user-space data be 108 function copies a NUL-terminated string, at most 110 bytes long, from kernel-space address 112 to kernel-space address 120 .No non- Ns Dv NULL ) . [all …]
|
/freebsd/lib/libpmc/pmu-events/arch/arm64/ |
H A D | common-and-microarch.json | 129 "PublicDescription": "Attributable Level 1 data cache write-back", 132 "BriefDescription": "Attributable Level 1 data cache write-back" 147 "PublicDescription": "Attributable Level 2 data cache write-back", 150 "BriefDescription": "Attributable Level 2 data cache write-back" 273 "PublicDescription": "Access to another socket in a multi-socket system", 276 "BriefDescription": "Access to another socket in a multi-socket system" 303 … "PublicDescription": "Attributable memory read access to another socket in a multi-socket system", 306 … "BriefDescription": "Attributable memory read access to another socket in a multi-socket system" 309 …"PublicDescription": "Level 1 data cache long-latency read miss. The counter counts each memory r… 312 "BriefDescription": "Level 1 data cache long-latency read miss" [all …]
|
/freebsd/sys/dev/ice/ |
H A D | ice_resmgr.c | 1 /* SPDX-License-Identifier: BSD-3-Clause */ 39 * It can handle contiguous and scattered resource allocations, and upon 41 * resource IDs to PF-space resource indices. 52 MALLOC_DEFINE(M_ICE_RESMGR, "ice-resmgr", "Intel(R) 100Gb Network Driver resmgr allocations"); 59 * ice_resmgr_init - Initialize a resource manager structure 71 resmgr->resources = bit_alloc(num_res, M_ICE_RESMGR, M_NOWAIT); in ice_resmgr_init() 72 if (resmgr->resource in ice_resmgr_init() [all...] |
/freebsd/sys/contrib/openzfs/man/man4/ |
H A D | spl.4 | 5 .\" usr/src/OPENSOLARIS.LICENSE or https://opensource.org/licenses/CDDL-1.0. 26 .Bl -tag -width Ds 41 .It Sy spl_kmem_cache_max_size Ns = Ns Sy 32 Po 64-bit Pc or Sy 4 Po 32-bit Pc Pq uint 66 preferably just a few pages, since they must by physically contiguous. 87 should still be avoided due to the expense of locating a contiguous range 102 They do this by keeping a per-cpu cache of recently 113 Otherwise magazines will be limited to 2-256 objects per magazine (i.e per cpu). 119 It can be explicitly enabled by placing a unique non-zero value in 124 This value may be overridden for non-standard configurations. 130 Set to a non-zero value to enable. [all …]
|
/freebsd/contrib/elftoolchain/libdwarf/ |
H A D | dwarf_get_ranges.3 | 25 .\" $Id: dwarf_get_ranges.3 3644 2018-10-15 19:55:01Z jkoshy $ 32 .Nd retrieve non-contiguous address ranges 59 retrieves information about the non-contiguous address ranges associated 117 .Bl -tag -width ".Va dwr_addr1" 126 .Bl -tag -width ".Dv DW_RANGES_ENTRY" -compact 178 .Bd -literal -offset indent 244 .Bl -tag -width ".Bq Er DW_DLE_NO_ENTRY"
|
/freebsd/sys/contrib/device-tree/Bindings/arm/ |
H A D | arm,coresight-catu.yaml | 1 # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause 3 --- 4 $id: http://devicetree.org/schemas/arm/arm,coresight-catu.yaml# 5 $schema: http://devicetree.org/meta-schemas/core.yaml# 10 - Mathieu Poirier <mathieu.poirier@linaro.org> 11 - Mike Leach <mike.leach@linaro.org> 12 - Leo Yan <leo.yan@linaro.org> 13 - Suzuki K Poulose <suzuki.poulose@arm.com> 26 translates contiguous Virtual Addresses (VAs) from an AXI master into 27 non-contiguous Physical Addresses (PAs) that are intended for system memory. [all …]
|
/freebsd/tools/tools/ioat/ |
H A D | ioatcontrol.8 | 46 .Ar [ chain-len 64 .Bl -tag -width Ds 69 Test contiguous 8k copy. 71 Test non-contiguous 8k copy. 94 .Bl -tag -width Ds 140 .Ar chain-len
|
/freebsd/contrib/elftoolchain/strings/ |
H A D | strings.1 | 25 .\" $Id: strings.1 3360 2016-01-24 18:34:06Z jkoshy $ 35 .Op Fl a | Fl -all 36 .Op Fl e Ar encoding | Fl -encoding= Ns Ar encoding 37 .Op Fl f | Fl -print-file-name 38 .Op Fl h | Fl -help 39 .Op Fl n Ar number | Fl -bytes= Ns Ar number | Fl Ar number 41 .Op Fl t Ar radix | Fl -radix= Ns Ar radix 42 .Op Fl v | Fl -version 49 utility prints contiguous sequences of printable 62 utility is mainly used for determining the contents of non-text files. [all …]
|
/freebsd/contrib/llvm-project/llvm/lib/Target/AArch64/ |
H A D | AArch64SchedA510.td | 1 //==- AArch64SchedCortexA510.td - ARM Cortex-A510 Scheduling Definitions -*- tablegen -*-=// 5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception 7 //===----------------------------------------------------------------------===// 9 // This file defines the machine model for the ARM Cortex-A510 processor. 11 //===----------------------------------------------------------------------===// 13 // ===---------------------------------------------------------------------===// 14 // The following definitions describe the per-operand machine model. 17 // Cortex-A510 machine model for scheduling and other instruction cost heuristics. 19 let MicroOpBufferSize = 0; // The Cortex-A510 is an in-order processor 20 let IssueWidth = 3; // It dual-issues under most circumstances [all …]
|
H A D | AArch64SchedNeoverseN2.td | 1 //=- AArch64SchedNeoverseN2.td - NeoverseN2 Scheduling Defs --*- tablegen -*-=// 5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception 7 //===----------------------------------------------------------------------===// 11 //===----------------------------------------------------------------------===// 14 let IssueWidth = 10; // Micro-ops dispatched at a time. 15 let MicroOpBufferSize = 160; // Entries in micro-op re-order buffer. 18 let LoopMicroOpBufferSize = 16; // NOTE: Copied from Cortex-A57. 25 //===----------------------------------------------------------------------===// 27 // Instructions are first fetched and then decoded into internal macro-ops 29 // stages. A MOP can be split into two micro-ops further down the pipeline [all …]
|
/freebsd/share/man/man4/ |
H A D | numa.4 | 30 .Nd Non-Uniform Memory Access 35 Non-Uniform Memory Access is a computer architecture design which 46 implements NUMA-aware memory allocation policies. 75 tool is available for starting processes with a non-default 81 Systems with non-uniform access to I/O devices may mark those devices 92 .Bl -tag -width indent -compact 99 A value of -1 means the locality map is not available or no 108 implementation is VM-focused. 111 domains are mapped into a contiguous, non-sparse 126 as a first-touch allocation policy with a fail-over to round-robin allocation [all …]
|
/freebsd/sys/contrib/zstd/lib/compress/ |
H A D | zstd_compress_internal.h | 5 * This source code is licensed under both the BSD-style license (found in the 8 * You may select, at your option, one of the above-listed licenses. 18 /*-************************************* 31 /*-************************************* 41 … benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different … 45 /*-************************************* 88 * Stores Literals Block Type for a super-block in hType, and 99 * Stores symbol compression modes for a super-block in {ll, ol, ml}Type, and 164 /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */ 180 …ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost… [all …]
|
/freebsd/contrib/llvm-project/llvm/lib/Transforms/Scalar/ |
H A D | MergeICmps.cpp | 1 //===- MergeICmps.cpp - Optimize chains of integer comparisons ------------===// 5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception 7 //===----------------------------------------------------------------------===// 14 // from contiguous memory locations into a shorter chain of larger integer 16 // - There are less jumps, and therefore less opportunities for mispredictions 17 // and I-cache misses. 18 // - Code size is smaller, both because jumps are removed and because the 19 // encoding of a 2*n byte compare is smaller than that of two n-byte 40 // Which will later be expanded (ExpandMemCmp) as a single 8-bytes icmp. 42 //===----------------------------------------------------------------------===// [all …]
|
/freebsd/sys/contrib/openzfs/module/zstd/lib/compress/ |
H A D | zstd_compress_internal.h | 2 * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc. 5 * This source code is licensed under both the BSD-style license (found in the 8 * You may select, at your option, one of the above-listed licenses. 18 /*-************************************* 32 /*-************************************* 42 … benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different … 46 /*-************************************* 101 /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */ 117 …ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost… 118 const ZSTD_entropyCTables_t* symbolCosts; /* pre-calculated dictionary statistics */ [all …]
|
/freebsd/lib/libsys/ |
H A D | shm_open.2 | 157 object is always backed by aligned, physically contiguous chunks of memory. 158 This ensures that the object can be mapped using so-called 169 Largepage shared memory objects behave slightly differently from non-largepage 171 .Bl -bullet -offset indent 188 must be large page size-aligned, and the length of the operation must be a 216 .Bl -tag -offset indent -width SHM_ 218 If the (non-blocking) memory allocation fails because there is insufficient free 219 contiguous memory, the kernel will attempt to defragment physical memory and 250 .Bd -literal 283 .Bl -tag -offset indent -width Er [all …]
|
/freebsd/contrib/ntp/sntp/libevent/include/event2/ |
H A D | buffer.h | 2 * Copyright (c) 2007-2012 Niels Provos and Nick Mathewson 46 - if you already know how much data you are going to add as a result 51 - evbuffer_add_buffer() adds the contents of one buffer to the other 54 - evbuffer_add() and evbuffer_add_buffer() do not mix very well: 58 - For high-performance code, you may want to avoid copying data into and out 69 can be used to force a specified number of bytes to be contiguous. This 72 evbuffer_peek() if you don't require that the memory to be contiguous. 81 #include <event2/event-config.h> 107 that modifies or re-packs the buffer contents may invalidate all 128 direct-access functions. [all …]
|
/freebsd/contrib/libevent/include/event2/ |
H A D | buffer.h | 2 * Copyright (c) 2007-2012 Niels Provos and Nick Mathewson 46 - if you already know how much data you are going to add as a result 51 - evbuffer_add_buffer() adds the contents of one buffer to the other 54 - evbuffer_add() and evbuffer_add_buffer() do not mix very well: 58 - For high-performance code, you may want to avoid copying data into and out 69 can be used to force a specified number of bytes to be contiguous. This 72 evbuffer_peek() if you don't require that the memory to be contiguous. 81 #include <event2/event-config.h> 107 that modifies or re-packs the buffer contents may invalidate all 128 direct-access functions. [all …]
|
/freebsd/contrib/libexecinfo/ |
H A D | backtrace.3 | 75 .Bl -tag -width a -offset indent 89 +0x%tx if non-zero, or nothing if zero. 95 The array of formatted strings is returned as a contiguous memory address which 110 are similar to the non _fd named functions, only instead of returning 111 an array or strings, they print a new-line separated array of strings in 115 .Dv \-1 141 .Bl -enum
|
/freebsd/contrib/llvm-project/llvm/lib/ExecutionEngine/RuntimeDyld/ |
H A D | RuntimeDyldMachO.h | 1 //===-- RuntimeDyldMachO.h - Run-time dynamic linker for MC-JIT ---*- C++ -*-=// 5 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception 7 //===----------------------------------------------------------------------===// 9 // MachO support for MC-JIT runtime dynamic linker. 11 //===----------------------------------------------------------------------===// 55 /// This convenience method uses memcpy to extract a contiguous addend (the 59 /// Given a relocation_iterator for a non-scattered relocation, construct a 62 /// For targets/opcodes with simple, contiguous immediates (e.g. X86) the 70 Obj.getRelocation(RI->getRawDataRefImpl()); in getRelocationEntry() 74 uint64_t Offset = RI->getOffset(); in getRelocationEntry() [all …]
|
/freebsd/sys/dev/nvme/ |
H A D | nvme_ctrlr_cmd.c | 1 /*- 2 * SPDX-License-Identifier: BSD-2-Clause 4 * Copyright (C) 2012-2013 Intel Corporation 42 cmd = &req->cmd; in nvme_ctrlr_cmd_identify_controller() 43 cmd->opc = NVME_OPC_IDENTIFY; in nvme_ctrlr_cmd_identify_controller() 49 cmd->cdw10 = htole32(1); in nvme_ctrlr_cmd_identify_controller() 64 cmd = &req->cmd; in nvme_ctrlr_cmd_identify_namespace() 65 cmd->opc = NVME_OPC_IDENTIFY; in nvme_ctrlr_cmd_identify_namespace() 70 cmd->nsid = htole32(nsid); in nvme_ctrlr_cmd_identify_namespace() 84 cmd = &req->cmd; in nvme_ctrlr_cmd_create_io_cq() [all …]
|