| /dpdk/doc/guides/prog_guide/img/ |
| H A D | dir_24_8_alg.svg | 11 …nt224" x1="-.573" y1="46.345" x2="277.982" y2="46.345" gradientTransform="scale(.65397 1.52912)" g… 12 …t226" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 13 …t228" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 14 …t230" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 15 …t232" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 16 …t234" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 17 …t236" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 18 …t238" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… 19 …240" x1="-.378" y1="309.413" x2="183.201" y2="309.413" gradientTransform="scale(.9923 1.00775)" gr… 20 …t242" x1="-.185" y1="928.807" x2="75.865" y2="928.807" gradientTransform="scale(2.02261 .49441)" g… [all …]
|
| H A D | rib_pic.svg | 7 …<use xlink:href="#lend4" transform="scale(-3.52)" id="use14" x="0" y="0" width="100%" height="100%… 10 …<use xlink:href="#lend4" transform="scale(-3.52)" id="use17" x="0" y="0" width="100%" height="100%… 13 …<use xlink:href="#lend4" transform="scale(-3.52)" id="use20" x="0" y="0" width="100%" height="100%… 16 …<use xlink:href="#lend4" transform="scale(-3.52)" id="use23" x="0" y="0" width="100%" height="100%…
|
| H A D | rib_internals.svg | 7 …<use xlink:href="#lend4" transform="scale(-3.52)" id="use745" x="0" y="0" width="100%" height="100…
|
| /dpdk/lib/sched/ |
| H A D | rte_red.c | 37 double scale = 0.0; in __rte_red_init_tables() local 40 scale = (double)(1 << RTE_RED_SCALING); in __rte_red_init_tables() 46 rte_red_pow2_frac_inv[i] = (uint16_t) round(scale / pow(2, m / table_size)); in __rte_red_init_tables() 49 scale = 1024.0; in __rte_red_init_tables() 58 rte_red_log2_1_minus_Wq[index] = (uint16_t) round(-1.0 * scale * log2(1.0 - Wq)); in __rte_red_init_tables()
|
| /dpdk/lib/ring/ |
| H A D | rte_ring_elem_pvt.h | 134 uint32_t idx, scale, nr_idx, nr_num, nr_size; in __rte_ring_enqueue_elems() local 137 scale = esize / sizeof(uint32_t); in __rte_ring_enqueue_elems() 138 nr_num = num * scale; in __rte_ring_enqueue_elems() 140 nr_idx = idx * scale; in __rte_ring_enqueue_elems() 141 nr_size = r->size * scale; in __rte_ring_enqueue_elems() 264 uint32_t idx, scale, nr_idx, nr_num, nr_size; in __rte_ring_dequeue_elems() local 267 scale = esize / sizeof(uint32_t); in __rte_ring_dequeue_elems() 268 nr_num = num * scale; in __rte_ring_dequeue_elems() 270 nr_idx = idx * scale; in __rte_ring_dequeue_elems() 271 nr_size = r->size * scale; in __rte_ring_dequeue_elems()
|
| H A D | rte_ring_peek_zc.h | 101 uint32_t idx, scale, nr_idx; in __rte_ring_get_elem_addr() local 105 scale = esize / sizeof(uint32_t); in __rte_ring_get_elem_addr() 107 nr_idx = idx * scale; in __rte_ring_get_elem_addr()
|
| /dpdk/doc/guides/prog_guide/ |
| H A D | power_man.rst | 78 So even though an application may request a scale down, the core frequency will 79 remain at the highest frequency until all Hyper-Threads on that core request a scale down. 86 * **Freq up**: Prompt the kernel to scale up the frequency of the specific lcore. 88 * **Freq down**: Prompt the kernel to scale down the frequency of the specific lcore. 90 * **Freq max**: Prompt the kernel to scale up the frequency of the specific lcore to the maximum. 92 * **Freq min**: Prompt the kernel to scale down the frequency of the specific lcore to the minimu… 219 scale the core frequency up/down depending on traffic volume.
|
| H A D | generic_receive_offload_lib.rst | 103 - lightweight enough to scale fast networking speed
|
| H A D | build-sdk-meson.rst | 90 meson -Dmax_lcores=8 smallbuild # scale build for smaller systems
|
| H A D | efd_lib.rst | 30 fit for CPU cache), EFD can scale to millions of flow keys. Finally, 106 signatures and target values. This doesn't allow this scheme to scale to
|
| H A D | bbdev.rst | 645 "ext_scale","scale factor on extrinsic info (5 bits)"
|
| /dpdk/lib/acl/ |
| H A D | acl_run_avx512x8.h | 42 #define _M_GI_(name, idx, base, scale) _mm256_##name(base, idx, scale) argument
|
| H A D | acl_run_avx512x16.h | 42 #define _M_GI_(name, idx, base, scale) _mm512_##name(idx, base, scale) argument
|
| /dpdk/config/ppc/ |
| H A D | meson.build | 111 # Certain POWER9 systems can scale as high as 1536 LCORES, but setting such a 122 # systems can scale even higher with as many as 32 NUMA nodes.
|
| /dpdk/drivers/event/skeleton/ |
| H A D | skeleton_eventdev.c | 301 uint32_t scale = 1; in skeleton_eventdev_timeout_ticks() local 306 *timeout_ticks = ns * scale; in skeleton_eventdev_timeout_ticks()
|
| /dpdk/doc/guides/sample_app_ug/ |
| H A D | vm_power_management.rst | 40 periods, and the host application can scale up/down the relevant 104 request contains the vCPU and power command (scale up/down/min/max). The 130 counters and scale the core power accordingly. This technique is based 150 core does not scale down in frequency until all of its siblings are 418 that identifies the threshold at which to scale up or down for the 759 The hours of the day in which we scale up the cores for busy times. 863 - TRAFFIC: Use statistics from the NIC and scale up and down accordingly. 865 and scale up and down accordingly. 880 The hours of the day to scale down the cores for quiet times.
|
| H A D | l3_forward_power_man.rst | 51 …d and available Rx packets on recent polls to make a heuristic decision to scale frequency up/down. 129 responsible for checking if it needs to scale down frequency at run time by checking CPU utilizatio… 347 ``scale`` 350 The reaction time of the scale mode is longer 358 …<build_dir>/examples/dpdk-l3fwd-power -l 1-3 -- -p 0x0f --config="(0,0,2),(0,1,3)" --pmd-mgmt=scale
|
| /dpdk/drivers/net/mlx5/ |
| H A D | mlx5_flow_aso.c | 940 profile->reply_dir.scale); in mlx5_aso_ct_sq_enqueue_single() 951 profile->original_dir.scale); in mlx5_aso_ct_sq_enqueue_single() 1275 profile->reply_dir.scale = MLX5_GET(conn_track_aso, wdata, in mlx5_aso_ct_obj_analyze() 1291 profile->original_dir.scale = MLX5_GET(conn_track_aso, wdata, in mlx5_aso_ct_obj_analyze()
|
| /dpdk/drivers/event/dpaa2/ |
| H A D | dpaa2_eventdev.c | 655 uint32_t scale = 1000*1000; in dpaa2_eventdev_timeout_ticks() local 660 *timeout_ticks = ns / scale; in dpaa2_eventdev_timeout_ticks()
|
| /dpdk/lib/bpf/ |
| H A D | bpf_jit_x86.c | 209 emit_sib(struct bpf_jit_state *st, uint32_t scale, uint32_t idx, uint32_t base) in emit_sib() argument 213 v = scale << 6 | (idx & 7) << 3 | (base & 7); in emit_sib()
|
| /dpdk/lib/ethdev/ |
| H A D | rte_flow.h | 3528 uint32_t scale:4; member
|
| /dpdk/doc/guides/howto/ |
| H A D | debug_troubleshoot.rst | 51 A couple of factors that lead the design decision could be the platform, scale
|
| /dpdk/doc/guides/rel_notes/ |
| H A D | release_19_05.rst | 111 * Flow engine re-designed to support large scale deployments. this includes:
|
| H A D | release_17_02.rst | 215 therefore, it can better fit in CPU cache and scale to millions of flow
|
| /dpdk/app/test-pmd/ |
| H A D | config.c | 2023 query.ct.original_dir.scale, in port_action_handle_query() 2035 query.ct.reply_dir.scale, in port_action_handle_query()
|