| /freebsd/sys/contrib/device-tree/Bindings/bus/ |
| H A D | aspeed,ast2600-ahbc.yaml | 1 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
3 ---
4 $id: http://devicetree.org/schemas/bus/aspeed,ast2600-ahbc.yaml#
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
7 title: ASPEED Advanced High-Performance Bus Controller (AHBC)
10 - Neal Liu <neal_liu@aspeedtech.com>
11 - Chia-Wei Wang <chiawei_wang@aspeedtech.com>
14 Advanced High-performance Bus Controller (AHBC) supports plenty of mechanisms
16 to control the overall operations of Advanced High-performance Bus (AHB).
21 - aspeed,ast2600-ahbc
[all …]
|
| /freebsd/libexec/rc/rc.d/ |
| H A D | power_profile | 6 # Arguments: 0x00 (AC offline, economy) or 0x01 (AC online, performance)
19 LOGGER="logger -t power_profile -p daemon.notice"
25 # $value: HIGH for the highest performance value, LOW for the best
27 # $highest_value: maximum value for this sysctl, when $value is "HIGH"
33 if [ -z "$(sysctl -n ${node} 2> /dev/null)" ]; then
37 # Get the new value, checking for special types HIGH or LOW
53 if [ -n "${value}" ]; then
60 if [ $# -ne 1 ]; then
68 # Find the next state (performance or economy).
72 ${LOGGER} "changed to 'performance'"
[all …]
|
| /freebsd/contrib/sendmail/src/ |
| H A D | TUNING | 1 # Copyright (c) 2001-2003, 2014 Proofpoint, Inc. and its suppliers.
8 # $Id: TUNING,v 1.22 2013-11-22 20:51:54 ca Exp $
17 required performance, there are several configuration options that
18 can be changed to accomplish higher performance. However, before
20 performance is not as good as desired. This may also involve hardware
24 the scope of this guide. In almost all other cases performance will
34 * Mailing Lists and Large Aliases (1-n Mailing)
35 * 1-1 Mass Mailing
36 * High Volume Mail
40 to configure sendmail to achieve good performance in all cases, but
[all …]
|
| /freebsd/share/doc/smm/05.fastfs/ |
| H A D | 1.t | 45 The original UNIX system that runs on the PDP-11\(dg
63 When used on the VAX-11 together with other UNIX enhancements,
72 need to have a high throughput from the file system.
73 High throughput rates are also needed by programs
85 its performance.
93 Problems with file system performance have been dealt with
95 Previous work to improve the UNIX file system performance has been
98 a large, high performance operating system [Feiertag71].
|
| /freebsd/sys/contrib/openzfs/man/man7/ |
| H A D | zpool-features.7 | 8 .\" usr/src/OPENSOLARIS.LICENSE or https://opensource.org/licenses/CDDL-1.0.
26 .Nm zpool-features
30 ZFS pool on-disk format versions are specified via
32 which replace the old on-disk format numbers
33 .Pq the last supported on-disk format number is 28 .
37 .Sy feature Ns @ Ns Ar feature-name
47 Since most features can be enabled independently of each other, the on-disk
56 .Ar com.example : Ns Ar feature-name .
70 .Ar com.example : Ns Ar feature-name
72 .Ar feature-name
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/sound/ |
| H A D | cirrus,cs4234.yaml | 1 # SPDX-License-Identifier: (GPL-2.0+ OR BSD-2-Clause)
3 ---
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
10 - patches@opensource.cirrus.com
14 high performance analog to digital conversion, 4 channels of high
15 performance digital to analog conversion for audio, and 1 channel of
19 standard audio grade DAC, with performance specifications identical
22 provide lead time for the external switch-mode power supply, and a
24 low-latency path to the outputs.
29 - cirrus,cs4234
[all …]
|
| /freebsd/share/man/man4/ |
| H A D | mlx4en.4 | 30 .Nd "Mellanox ConnectX-3 10GbE/40GbE network adapter driver"
34 .Bd -ragged -offset indent
40 To load the driver as a module at run-time,
42 .Bd -literal -offset indent
49 .Bd -literal -offset indent
55 solution for Enterprise Data Centers, High-Performance Computing, and
58 services and high-performance embedded I/O applications will achieve
59 significant performance improvements resulting in reduced completion
66 .Bl -bullet -compact
68 Mellanox ConnectX-2 (ETH)
[all …]
|
| H A D | mlx4ib.4 | 30 .Nd "Mellanox ConnectX-3 10GbE/40GbE network adapter driver"
34 .Bd -ragged -offset indent
40 To load the driver as a module at run-time,
42 .Bd -literal -offset indent
49 .Bd -literal -offset indent
55 solution for Enterprise Data Centers, High-Performance Computing, and
58 services and high-performance embedded I/O applications will achieve
59 significant performance improvements resulting in reduced completion
66 .Bl -bullet -compact
68 Mellanox ConnectX-2 (IB)
[all …]
|
| H A D | hv_vmbus.4 | 31 .Nd Hyper-V Virtual Machine Bus (VMBus) Driver
35 .Bd -ragged -offset indent
42 provides a high performance communication interface between
43 guest and root partitions in Hyper-V.
44 Hyper-V is a hypervisor-based virtualization technology from Microsoft.
45 Hyper-V supports isolation in terms of a partition.
64 The VMBus is a logical inter-partition communication channel.
71 The Hyper-V VMBus driver defines and implements
72 the interface that facilitate high performance bi-directional communication
87 .An -nosplit
|
| H A D | ppbus.4 | 42 system provides a uniform, modular and architecture-independent
48 .Bl -bullet -offset indent
50 architecture-independent macros or functions to access parallel ports
57 with kernel-in drivers.
61 and non-standard software:
63 .Bl -column "Driver" -compact
67 .It Sy lpbb Ta "Philips official parallel port I2C bit-banging interface"
73 .Bl -column "Driver" -compact
100 .Bl -bullet -offset indent
104 bidirectional 8/4-bits mode, also called NIBBLE mode
[all …]
|
| /freebsd/lib/libc/stdlib/ |
| H A D | rand.3 | 51 .Bf -symbolic
61 function computes a sequence of pseudo-random integers in the range
85 is implemented using the same 128-byte state LFSR generator algorithm as
93 implements the historical, poor-quality Park-Miller 32-bit LCG and should not
101 so the low-order bits should no longer be significantly worse than the
102 high-order bits.
114 .St -isoC .
119 .St -isoC
121 .St -p1003.1-2008 .
127 used the historical Park-Miller generator with 32 bits of state and produced
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/regulator/ |
| H A D | richtek,rt5759-regulator.yaml | 1 # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
3 ---
4 $id: http://devicetree.org/schemas/regulator/richtek,rt5759-regulator.yaml#
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
7 title: Richtek RT5759 High Performance DCDC Converter
10 - ChiYuan Huang <cy_huang@richtek.com>
13 The RT5759 is a high-performance, synchronous step-down DC-DC converter that
15 voltage can be programmable with I2C controlled 7-Bit VID.
18 https://www.richtek.com/assets/product_file/RT5759/DS5759-00.pdf
23 - richtek,rt5759
[all …]
|
| H A D | renesas,raa215300.yaml | 1 # SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
3 ---
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
10 - Biju Das <biju.das.jz@bp.renesas.com>
13 The RAA215300 is a high-performance, low-cost 9-channel PMIC designed for
14 32-bit and 64-bit MCU and MPU applications. It supports DDR3, DDR3L, DDR4,
16 built-in Real-Time Clock (RTC), 32kHz crystal oscillator, and coin cell
18 ideal for System-On-Module (SOM) applications. A spread spectrum feature
19 provides an ease-of-use solution for noise-sensitive audio or RF applications.
25 …-power-management/multi-channel-power-management-ics-pmics/ssdsoc-power-management-ics-pmic-and-pm…
[all …]
|
| H A D | fixed-regulator.yaml | 1 # SPDX-License-Identifier: GPL-2.0
3 ---
4 $id: http://devicetree.org/schemas/regulator/fixed-regulator.yaml#
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
10 - Liam Girdwood <lgirdwood@gmail.com>
11 - Mar
[all...] |
| /freebsd/share/doc/papers/sysperf/ |
| H A D | 2.t | 32 There are many tools available for monitoring the performance
54 out at 25-35 tps in practice), and the user cpu utilization (us) should
55 be high (above 50%).
60 be non-zero). It is healthy for the paging demon to free pages when
70 is overloaded or imbalanced. If you have several non-dma
72 that are doing high-speed non-buffered input/output, then the system
73 time may go high (60-80% or higher).
74 It is often possible to pin down the cause of high system time by
118 non-zero average seek times. Most modern disk drives should
119 exhibit an average seek time of 25-35 ms.
[all …]
|
| H A D | 4.t | 30 Performance Improvements
41 Performance Improvements in the Kernel
43 Our goal has been to optimize system performance
62 translating path names to inodes\u\s-21\s0\d\**.
64 \** \u\s-21\s0\d Inode is an abbreviation for ``Index node''.
78 To improve performance for processes doing directory scans,
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.
133 The small performance improvement
[all …]
|
| /freebsd/sys/x86/cpufreq/ |
| H A D | hwpstate_intel.c | 1 /*-
2 * SPDX-License-Identifier: BSD-2-Clause
96 uint8_t high; member
114 "Set 1 (default) to enable package-level control, 0 to disable");
127 dev = sc->dev; in intel_hwp_dump_sysctl_handler()
136 sched_bind(curthread, pc->pc_cpuid); in intel_hwp_dump_sysctl_handler()
140 sbuf_printf(sb, "CPU%d: HWP %sabled\n", pc->pc_cpuid, in intel_hwp_dump_sysctl_handler()
149 sbuf_printf(sb, "\tHighest Performance: %03ju\n", data & 0xff); in intel_hwp_dump_sysctl_handler()
150 sbuf_printf(sb, "\tGuaranteed Performance: %03ju\n", (data >> 8) & 0xff); in intel_hwp_dump_sysctl_handler()
151 sbuf_printf(sb, "\tEfficient Performance: %03ju\n", (data >> 16) & 0xff); in intel_hwp_dump_sysctl_handler()
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/nds32/ |
| H A D | atl2c.txt | 3 The level-2 cache controller plays an important role in reducing memory latency
4 for high performance systems, such as thoese designs with AndesCore processors.
5 Level-2 cache controller in general enhances overall system performance
13 - compatible:
17 - reg : Physical base address and size of cache controller's memory mapped
18 - cache-unified : Specifies the cache is a unified cache.
19 - cache-level : Should be set to 2 for a level 2 cache.
23 cache-controller@e0500000 {
26 cache-unified;
27 cache-level = <2>;
|
| 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
26 system performance of their applications and track bugs of their designs
28 system environment for early prototyping and software/hardware co-development.
[all …]
|
| /freebsd/sys/contrib/device-tree/Bindings/iio/frequency/ |
| H A D | adi,adf4377.yaml | 1 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
3 ---
5 $schema: http://devicetree.org/meta-schemas/core.yaml#
10 - Antoniu Miclaus <antoniu.miclaus@analog.com>
11 - Dragos Bogdan <dragos.bogdan@analog.com>
14 The ADF4377 is a high performance, ultralow jitter, dual output integer-N
24 - adi,adf4377
25 - adi,adf4378
30 spi-max-frequency:
36 clock-names:
[all …]
|
| /freebsd/lib/libpmc/pmu-events/arch/x86/jaketown/ |
| H A D | jkt-metrics.json | 7 …-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into mi…
14 …-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into mi…
18 …"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4…
21 …s for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For…
25 …"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY …
28 …s for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For…
33 …"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUE…
36 …-of-order scheduler dispatches ready uops into their respective execution units; and once complete…
40 …- ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED…
43 …-of-order scheduler dispatches ready uops into their respective execution units; and once complete…
[all …]
|
| /freebsd/contrib/llvm-project/compiler-rt/lib/builtins/i386/ |
| H A D | umoddi3.S | 3 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
10 // both inputs and the output are 64-bit unsigned integers.
14 // This is targeted at 32-bit x86 *only*, as this can be done directly in hardware
15 // on x86_64. The performance goal is ~40 cycles per divide, which is faster than
29 bsrl %ebx, %ecx // If the high word of b is zero, jump to
32 // High word of b is known to be non-zero on this branch
38 notl %ecx // bhi = (high word of b) << (31 - i) |
41 movl 12(%esp), %edx // Load the high and low words of a, and jump
42 movl 8(%esp), %eax // to [2] if the high word is larger than bhi
46 // High word of a is greater than or equal to (b >> (1 + i)) on this branch
[all …]
|
| H A D | udivdi3.S | 3 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
10 // both inputs and the output are 64-bit unsigned integers.
14 // This is targeted at 32-bit x86 *only*, as this can be done directly in hardware
15 // on x86_64. The performance goal is ~40 cycles per divide, which is faster than
28 bsrl %ebx, %ecx // If the high word of b is zero, jump to
31 // High word of b is known to be non-zero on this branch
37 notl %ecx // bhi = (high word of b) << (31 - i) |
40 movl 12(%esp), %edx // Load the high and low words of a, and jump
41 movl 8(%esp), %eax // to [1] if the high word is larger than bhi
45 // High word of a is greater than or equal to (b >> (1 + i)) on this branch
[all …]
|
| /freebsd/lib/libpmc/pmu-events/arch/x86/sandybridge/ |
| H A D | snb-metrics.json | 7 …-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into mi…
14 …-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into mi…
18 …"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4…
21 …s for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For…
25 …"MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * ( INT_MISC.RECOVERY_CYCLES_ANY …
28 …s for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For…
33 …"MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * CPU_CLK_UNHALTED.THREAD)) + (( UOPS_ISSUE…
36 …-of-order scheduler dispatches ready uops into their respective execution units; and once complete…
40 …- ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * ( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED…
43 …-of-order scheduler dispatches ready uops into their respective execution units; and once complete…
[all …]
|
| /freebsd/contrib/ntp/libntp/lib/isc/win32/include/isc/ |
| H A D | offset.h | 15 * PERFORMANCE OF THIS SOFTWARE.
24 * File offsets are operating-system dependent.
33 * types", so the maximum value is all 1s except for the high bit.
37 * shifting 1 to the high bit and then inverting the bits, the SunOS compiler
41 (~(((off_t)-1 >> (sizeof(off_t) * CHAR_BIT - 1)) \
42 << (sizeof(off_t) * CHAR_BIT - 1)))
|