Home
last modified time | relevance | path

Searched full:compute (Results 1 – 25 of 1435) sorted by relevance

12345678910>>...58

/linux/Documentation/arch/x86/
H A Dtopology.rst100 AMDs nomenclature for a CMT core is "Compute Unit". The kernel always uses
108 AMDs nomenclature for CMT threads is "Compute Unit Core". The kernel always
177 [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
178 -> [Compute Unit Core 1] -> Linux CPU 1
179 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
180 -> [Compute Unit Core 1] -> Linux CPU 3
218 [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
219 -> [Compute Unit Core 1] -> Linux CPU 1
220 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
221 -> [Compute Unit Core 1] -> Linux CPU 3
[all …]
/linux/scripts/coccinelle/misc/
H A Darray_size_dup.cocci5 /// 1. An opencoded expression is used before array_size() to compute the same size
6 /// 2. An opencoded expression is used after array_size() to compute the same size
43 msg = "WARNING: array_size is used later (line %s) to compute the same size" % (p2[0].line)
51 msg = "WARNING: array_size is used later (line %s) to compute the same size" % (p2[0].line)
72 msg = "WARNING: array_size is already used (line %s) to compute the same size" % (p1[0].line)
80 msg = "WARNING: array_size is already used (line %s) to compute the same size" % (p1[0].line)
108 msg = "WARNING: array3_size is used later (line %s) to compute the same size" % (p2[0].line)
116 msg = "WARNING: array3_size is used later (line %s) to compute the same size" % (p2[0].line)
138 msg = "WARNING: array3_size is already used (line %s) to compute the same size" % (p1[0].line)
146 msg = "WARNING: array3_size is already used (line %s) to compute the same size" % (p1[0].line)
[all …]
/linux/Documentation/devicetree/bindings/misc/
H A Dqcom,fastrpc.yaml68 "(compute-)?cb@[0-9]*$":
72 Each subnode of the Fastrpc represents compute context banks available on the dsp.
76 const: qcom,fastrpc-compute-cb
129 compute-cb@1 {
130 compatible = "qcom,fastrpc-compute-cb";
135 compute-cb@2 {
136 compatible = "qcom,fastrpc-compute-cb";
141 compute-cb@3 {
142 compatible = "qcom,fastrpc-compute-cb";
/linux/tools/perf/pmu-events/arch/s390/cf_z16/
H A Dpai_crypto.json727 "BriefDescription": "PCC COMPUTE LAST BLOCK CMAC USING DEA",
728 "PublicDescription": "PCC-Compute-Last-Block-CMAC-Using-DEA function ending with CC=0"
734 "BriefDescription": "PCC COMPUTE LAST BLOCK CMAC USING TDEA 128",
735 "PublicDescription": "PCC-Compute-Last-Block-CMAC-Using-TDEA-128 function ending with CC=0"
741 "BriefDescription": "PCC COMPUTE LAST BLOCK CMAC USING TDEA 192",
742 "PublicDescription": "PCC-Compute-Last-Block-CMAC-Using-TDEA-192 function ending with CC=0"
748 "BriefDescription": "PCC COMPUTE LAST BLOCK CMAC USING ENCRYPTED DEA",
749 "PublicDescription": "PCC-Compute-Last-Block-CMAC-Using-Encrypted-DEA function ending with CC=0"
755 "BriefDescription": "PCC COMPUTE LAST BLOCK CMAC USING ENCRYPTED TDEA 128",
756 …"PublicDescription": "PCC-Compute-Last-Block-CMAC-Using-Encrypted-TDEA- 128 function ending with C…
[all …]
/linux/Documentation/gpu/amdgpu/
H A Ddriver-core.rst66 GC (Graphics and Compute)
67 This is the graphics and compute engine, i.e., the block that
79 Graphics and Compute Microcontrollers
84 GFX/Compute pipeline. Consists mainly of a bunch of microcontrollers
86 provides the driver interface to interact with the GFX/Compute engine.
88 MEC (MicroEngine Compute)
89 This is the microcontroller that controls the compute queues on the
90 GFX/compute engine.
96 This is another microcontroller in the GFX/Compute engine. It handles
97 power management related functionality within the GFX/Compute engine.
[all …]
H A Damdgpu-glossary.rst22 Compute Unit
43 Graphics and Compute
75 Kernel Compute Queue
84 MicroEngine Compute
/linux/drivers/gpu/drm/xe/
H A Dxe_vm_doc.h185 * the VM's DMA_RESV_USAGE_KERNEL slot (blocks future jobs / resume compute mode
187 * to execs and compute mode rebind worker. To accomplish this, hold the
213 * until all pending users (jobs or compute mode engines) of the userptr are
219 * Either the next exec (non-compute) or rebind worker (compute mode) will
221 * after the VM dma-resv wait if the VM is in compute mode.
223 * Compute mode
226 * A VM in compute mode enables long running workloads and ultra low latency
231 * are not used when a VM is in compute mode. User fences (TODO: link user fence
422 * evictions, and compute mode rebind worker) in XE.
431 * bind path also acquires this lock in write while the exec / compute mode
[all …]
H A Dxe_gt_ccs_mode.c32 * For example, if there are four compute slices available, the in __xe_gt_apply_ccs_mode()
33 * assignment of compute slices to compute engines would be, in __xe_gt_apply_ccs_mode()
115 xe_gt_dbg(gt, "Can't change compute mode when running as %s\n", in ccs_mode_store()
130 xe_gt_dbg(gt, "Invalid compute config, %d engines %d slices\n", in ccs_mode_store()
143 xe_gt_info(gt, "Setting compute mode to %d\n", num_engines); in ccs_mode_store()
174 * number of compute hardware engines to which the available compute slices
177 * The number of available compute slices is exposed to user through a per-gt
H A Dxe_gt_types.h104 * for implementing the graphics, compute, and/or media IP. It encapsulates
109 * A GPU/tile may have a single GT that supplies all graphics, compute, and
110 * media functionality, or the graphics/compute and media may be split into
214 * @ccs_mode: Number of compute engines enabled.
215 * Allows fixed mapping of available compute slices to compute engines.
216 * By default only the first available compute engine is enabled and all
217 * available compute slices are allocated to it.
255 * of compute resources available.
351 /** @fuse_topo.c_dss_mask: dual-subslices usable by compute */
/linux/drivers/accel/
H A DKconfig3 # Compute Acceleration device configuration
5 # This framework provides support for compute acceleration devices, such
12 bool "Compute Acceleration Framework"
14 Framework for device drivers of compute acceleration devices, such
19 This framework is integrated with the DRM subsystem as compute
/linux/Documentation/driver-api/
H A Ddma-buf.rst255 * Long-running compute command buffers, while still using traditional end of
257 fences which get reattached when the compute job is rescheduled.
304 userspace is allowed to use userspace fencing or long running compute
327 faults on GPUs are limited to pure compute workloads.
330 compute side, like compute units or command submission engines. If both a 3D
331 job with a DMA fence and a compute workload using recoverable page faults are
334 - The 3D workload might need to wait for the compute job to finish and release
337 - The compute workload might be stuck in a page fault, because the memory
343 - Compute workloads can always be preempted, even when a page fault is pending
348 achieved through e.g. through dedicated engines and minimal compute unit
[all …]
/linux/arch/x86/events/amd/
H A Dpower.c25 * The ratio of compute unit power accumulator sample period to the
30 /* Maximum accumulated power of a compute unit. */
36 * Accumulated power represents the sum of each compute unit's (CU) power
227 * Find a new CPU on the same compute unit, if was set in cpumask in power_cpu_exit()
228 * and still some CPUs on compute unit. Then migrate event and in power_cpu_exit()
244 * 1) If any CPU is set at cpu_mask in the same compute unit, do in power_cpu_init()
246 * 2) If no CPU is set at cpu_mask in the same compute unit, in power_cpu_init()
276 pr_err("Failed to read max compute unit power accumulator MSR\n"); in amd_power_pmu_init()
/linux/lib/
H A Dsiphash.c112 * siphash_1u64 - compute 64-bit siphash PRF value of a u64
128 * siphash_2u64 - compute 64-bit siphash PRF value of 2 u64
149 * siphash_3u64 - compute 64-bit siphash PRF value of 3 u64
176 * siphash_4u64 - compute 64-bit siphash PRF value of 4 u64
312 * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32
325 * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
342 * hsiphash_3u32 - compute 32-bit hsiphash PRF value of 3 u32
362 * hsiphash_4u32 - compute 32-bit hsiphash PRF value of 4 u32
454 * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32
469 * hsiphash_2u32 - compute 32-bit hsiphash PRF value of 2 u32
[all …]
H A Dbch.c30 * Call bch_encode to compute and store ecc parity bytes to a given buffer.
109 /* given its degree, compute a polynomial size in bytes */
368 * compute 2t syndromes of ecc polynomial, i.e. ecc(a^j) for j=1..2t
386 /* compute v(a^j) for j=1 .. 2t-1 */ in compute_syndromes()
441 /* compute l[i+1] = max(l[i]->c[l[p]+2*(i-p]) */ in compute_error_locator_polynomial()
523 /* compute unique solution */ in solve_linear_system()
573 * compute root r of a degree 1 polynomial over GF(2^m) (returned as log(1/r))
588 * compute roots of a degree 2 polynomial over GF(2^m)
605 * let u = sum(li.a^i) i=0..m-1; then compute r = sum(li.xi): in find_poly_deg2_roots()
619 /* reverse z=a/bX transformation and compute log(1/r) */ in find_poly_deg2_roots()
[all …]
/linux/tools/perf/Documentation/
H A Dperf-diff.txt92 --compute::
95 diff.compute config option. See COMPARISON METHODS section for
113 Specify compute sorting column number. 0 means sorting by baseline
211 baseline/A compute/B compute/C samples
222 baseline/B compute/A compute/C samples
233 baseline/C compute/B compute/A samples
/linux/Documentation/hwmon/
H A Dfam15h_power.rst67 compute unit power accumulator sample period
76 the ratio of compute unit power accumulator sample period to the
80 max compute unit accumulated power which is indicated by
84 compute unit accumulated power which is indicated by
110 v. Calculate the average power consumption for a compute unit over
/linux/drivers/hwmon/
H A Dfam15h_power.c55 /* maximum accumulated power of a compute unit */
57 /* accumulated power of the compute units */
61 /* online/offline status of current compute unit */
142 * is compute unit id. in do_read_registers_on_cu()
171 * Choose the first online core of each compute unit, and then in read_registers()
173 * because the MSR value of CPU core represent the compute in read_registers()
186 /* get any CPU on this compute unit */ in read_registers()
210 * compute unit number. in power1_average_show()
232 /* check if current compute unit is online */ in power1_average_show()
421 * determine the ratio of the compute unit power accumulator in fam15h_power_init_data()
[all …]
/linux/Documentation/devicetree/bindings/arm/bcm/
H A Dbcm2835.yaml22 - raspberrypi,4-compute-module
41 - raspberrypi,compute-module
58 - raspberrypi,3-compute-module
59 - raspberrypi,3-compute-module-lite
/linux/fs/xfs/libxfs/
H A Dxfs_rtbitmap.c196 * Compute and read in starting bitmap block for starting block. in xfs_rtfind_back()
210 * Compute match value, based on the bit at start: if 1 (free) in xfs_rtfind_back()
266 * Compute difference between actual and desired value. in xfs_rtfind_back()
305 * Compute difference between actual and desired value. in xfs_rtfind_back()
352 * Compute and read in starting bitmap block for starting block. in xfs_rtfind_forw()
366 * Compute match value, based on the bit at start: if 1 (free) in xfs_rtfind_forw()
421 * Compute difference between actual and desired value. in xfs_rtfind_forw()
458 * Compute difference between actual and desired value. in xfs_rtfind_forw()
588 * Compute starting bitmap block number. in xfs_rtmodify_range()
599 * Compute the starting word's address, and starting bit. in xfs_rtmodify_range()
[all …]
/linux/drivers/gpu/drm/amd/amdgpu/
H A Damdgpu_doorbell.h121 /* Compute + GFX: 0~255 */
176 /* 8 compute rings per GC. Max to 0x1CE */
188 /* Compute + GFX: 0~255 */
244 …* All compute related doorbells: kiq, hiq, diq, traditional compute queue, user queue, should loca…
246 * Compute related doorbells are allocated from 0x00 to 0x8a
257 /* Compute engines */
328 /* Compute: 0x08 ~ 0x20 */
/linux/arch/x86/include/asm/
H A Dchecksum_64.h41 * ip_fast_csum - Compute the IPv4 header checksum efficiently.
76 * csum_tcpup_nofold - Compute an IPv4 pseudo header checksum.
102 * csum_tcpup_magic - Compute an IPv4 pseudo header checksum.
120 * csum_partial - Compute an internet checksum.
139 * ip_compute_csum - Compute an 16bit IP checksum.
149 * csum_ipv6_magic - Compute checksum of an IPv6 pseudo header.
/linux/drivers/clk/ti/
H A Ddpll44xx.c79 * omap4_dpll_lpmode_recalc - compute DPLL low-power setting
104 * omap4_dpll_regm4xen_recalc - compute DPLL rate, considering REGM4XEN bit
105 * @hw: pointer to the clock to compute the rate for
108 * Compute the output rate for the OMAP4 DPLL represented by @clk.
142 * Compute the rate that would be programmed into the DPLL hardware
165 * First try to compute the DPLL configuration for in omap4_dpll_regm4xen_round_rate()
/linux/tools/perf/
H A Dbuiltin-diff.c112 COMPUTE_STREAM, /* After COMPUTE_MAX to avoid use current compute arrays */
123 static int compute = COMPUTE_DELTA_ABS; variable
204 pr_debug("compute wdiff w1(%" PRId64 ") w2(%" PRId64 ")\n", in setup_compute_opt_wdiff()
218 if (compute == COMPUTE_WEIGHTED_DIFF) in setup_compute_opt()
351 switch (compute) { in formula_fprintf()
425 switch (compute) { in diff__process_sample_event()
691 if (compute == COMPUTE_CYCLES) { in hists__precompute()
702 switch (compute) { in hists__precompute()
939 if (compute == COMPUTE_CYCLES) in hists__process()
1210 if (compute == COMPUTE_STREAM) { in __cmd_diff()
[all …]
/linux/arch/powerpc/kernel/vdso/
H A Dcacheflush.S45 subf r8,r6,r4 /* compute length */
49 PPC_SRL. r8,r8,r9 /* compute line count */
72 subf r8,r6,r4 /* compute length */
75 PPC_SRL. r8,r8,r9 /* compute line count */
/linux/Documentation/devicetree/bindings/interconnect/
H A Dqcom,rpmh.yaml30 - qcom,sc7180-compute-noc
42 - qcom,sc8180x-compute-noc
75 - qcom,sm8150-compute-noc
84 - qcom,sm8250-compute-noc
101 - qcom,sm8350-compute-noc

12345678910>>...58