Searched refs:workloads (Results 1 – 25 of 89) sorted by relevance
1234
| /Linux-v6.1/drivers/crypto/qat/ |
| D | Kconfig | 24 for accelerating crypto and compression workloads.
35 for accelerating crypto and compression workloads.
46 for accelerating crypto and compression workloads.
57 for accelerating crypto and compression workloads.
70 Virtual Function for accelerating crypto and compression workloads.
82 Virtual Function for accelerating crypto and compression workloads.
94 Virtual Function for accelerating crypto and compression workloads.
|
| /Linux-v6.1/Documentation/mm/damon/ |
| D | index.rst | 15 of the size of target workloads).
20 In user space, meanwhile, users who have some special workloads can write
22 workloads and systems.
|
| /Linux-v6.1/drivers/misc/habanalabs/ |
| D | Kconfig | 16 designed to accelerate Deep Learning inference and training workloads.
19 the user to submit workloads to the devices.
|
| /Linux-v6.1/Documentation/driver-api/ |
| D | dma-buf.rst | 258 randomly hangs workloads until the timeout kicks in. Workloads, which from
271 workloads. This also means no implicit fencing for shared buffers in these
293 faults on GPUs are limited to pure compute workloads.
309 - Compute workloads can always be preempted, even when a page fault is pending
312 - DMA fence workloads and workloads which need page fault handling have
315 reservations for DMA fence workloads.
318 hardware resources for DMA fence workloads when they are in-flight. This must
323 all workloads must be flushed from the GPU when switching between jobs
327 made visible anywhere in the system, all compute workloads must be preempted
338 Note that workloads that run on independent hardware like copy engines or other
[all …]
|
| /Linux-v6.1/Documentation/timers/ |
| D | no_hz.rst | 26 workloads, you will normally -not- want this option.
39 right approach, for example, in heavy workloads with lots of tasks
42 hundreds of microseconds). For these types of workloads, scheduling
56 are running light workloads, you should therefore read the following
118 computationally intensive short-iteration workloads: If any CPU is
231 aggressive real-time workloads, which have the option of disabling
233 some workloads will no doubt want to use adaptive ticks to
235 options for these workloads:
255 workloads, which have few such transitions. Careful benchmarking
256 will be required to determine whether or not other workloads
|
| /Linux-v6.1/Documentation/admin-guide/pm/ |
| D | intel_uncore_frequency_scaling.rst | 23 Users may have some latency sensitive workloads where they do not want any
24 change to uncore frequency. Also, users may have workloads which require
|
| /Linux-v6.1/drivers/cpuidle/ |
| D | Kconfig | 33 Some workloads benefit from using it and it generally should be safe
45 Some virtualized workloads benefit from using it.
|
| /Linux-v6.1/drivers/crypto/cavium/nitrox/ |
| D | Kconfig | 18 for accelerating crypto workloads.
|
| /Linux-v6.1/drivers/gpu/drm/i915/gvt/ |
| D | scheduler.c | 1329 kmem_cache_destroy(s->workloads); in intel_vgpu_clean_submission()
1421 s->workloads = kmem_cache_create_usercopy("gvt-g_vgpu_workload", in intel_vgpu_setup_submission()
1428 if (!s->workloads) { in intel_vgpu_setup_submission()
1537 kmem_cache_free(s->workloads, workload); in intel_vgpu_destroy_workload()
1546 workload = kmem_cache_zalloc(s->workloads, GFP_KERNEL); in alloc_workload()
1720 kmem_cache_free(s->workloads, workload); in intel_vgpu_create_workload()
1734 kmem_cache_free(s->workloads, workload); in intel_vgpu_create_workload()
1745 kmem_cache_free(s->workloads, workload); in intel_vgpu_create_workload()
|
| /Linux-v6.1/Documentation/accounting/ |
| D | psi.rst | 10 When CPU, memory or IO devices are contended, workloads experience
19 such resource crunches and the time impact it has on complex workloads
23 scarcity aids users in sizing workloads to hardware--or provisioning
|
| /Linux-v6.1/security/ |
| D | Kconfig.hardening | 177 sees a 1% slowdown, other systems and workloads may vary and you
217 your workloads.
238 workloads have measured as high as 7%.
256 synthetic workloads have measured as high as 8%.
273 workloads. Image size growth depends on architecture, and should
|
| /Linux-v6.1/Documentation/filesystems/ext4/ |
| D | orphan.rst | 18 global single linked list is a scalability bottleneck for workloads that result
|
| /Linux-v6.1/drivers/cpufreq/ |
| D | Kconfig.x86 | 173 the CPUs' workloads are. CPU-bound workloads will be more sensitive
175 workloads will be less sensitive -- they will not necessarily perform
|
| /Linux-v6.1/Documentation/scheduler/ |
| D | sched-design-CFS.rst | 100 "server" (i.e., good batching) workloads. It defaults to a setting suitable
101 for desktop workloads. SCHED_BATCH is handled by the CFS scheduler module too.
109 than the previous vanilla scheduler: both types of workloads are isolated much
|
| /Linux-v6.1/kernel/rcu/ |
| D | Kconfig | 246 real-time workloads. It can also be used to offload RCU
250 workloads will incur significant increases in context-switch
305 eliminates such IPIs for many workloads, proper setting
|
| /Linux-v6.1/Documentation/driver-api/md/ |
| D | raid5-cache.rst | 58 completely avoid the overhead, so it's very helpful for some workloads. A
74 mode depending on the workloads. It's recommended to use a cache disk with at
|
| /Linux-v6.1/fs/squashfs/ |
| D | Kconfig | 78 poor performance on parallel I/O workloads when using multiple CPU
92 poor performance on parallel I/O workloads when using multiple CPU
|
| /Linux-v6.1/Documentation/admin-guide/hw-vuln/ |
| D | core-scheduling.rst | 9 workloads may benefit from running on the same core as they don't need the same
24 world workloads. In theory, core scheduling aims to perform at least as good as
30 total number of CPUs. Please measure the performance of your workloads always.
|
| /Linux-v6.1/Documentation/RCU/ |
| D | checklist.rst | 205 to real-time workloads. Use of the expedited primitives should
208 However, real-time workloads can use rcupdate.rcu_normal kernel
218 of the system, especially to real-time workloads running on
372 for some real-time workloads, this is the whole point of using
413 real-time workloads than is synchronize_rcu_expedited().
|
| /Linux-v6.1/Documentation/x86/ |
| D | sgx.rst | 249 SGX workloads, (or just any new workloads), and migrate all valuable
250 workloads. Although a machine reboot can recover all EPC memory, the bug
|
| D | orc-unwinder.rst | 34 Gorman [1]_ have shown a slowdown of 5-10% for some workloads.
46 footprint. That can transform to even higher speedups for workloads
|
| /Linux-v6.1/Documentation/block/ |
| D | writeback_cache_control.rst | 11 behavior obviously speeds up various workloads, but it means the operating
|
| /Linux-v6.1/lib/ |
| D | Kconfig.kfence | 69 evaluated given target workloads and system architectures. Notably,
|
| /Linux-v6.1/tools/perf/Documentation/ |
| D | perf-bench.txt | 204 Suite for evaluating NUMA workloads.
|
| /Linux-v6.1/Documentation/mm/ |
| D | frontswap.rst | 71 Frontswap significantly increases performance in many such workloads by
90 on some workloads under high memory pressure.
106 well-publicized special-case workloads).
|
1234
