Home
last modified time | relevance | path

Searched full:compute (Results 1 – 25 of 1342) sorted by relevance

12345678910>>...54

/Linux-v6.6/Documentation/arch/x86/
Dtopology.rst98 AMDs nomenclature for a CMT core is "Compute Unit". The kernel always uses
116 AMDs nomenclature for CMT threads is "Compute Unit Core". The kernel always
185 [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
186 -> [Compute Unit Core 1] -> Linux CPU 1
187 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
188 -> [Compute Unit Core 1] -> Linux CPU 3
226 [node 0] -> [Compute Unit 0] -> [Compute Unit Core 0] -> Linux CPU 0
227 -> [Compute Unit Core 1] -> Linux CPU 1
228 -> [Compute Unit 1] -> [Compute Unit Core 0] -> Linux CPU 2
229 -> [Compute Unit Core 1] -> Linux CPU 3
[all …]
/Linux-v6.6/scripts/coccinelle/misc/
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-v6.6/Documentation/devicetree/bindings/misc/
Dqcom,fastrpc.yaml67 "(compute-)?cb@[0-9]*$":
71 Each subnode of the Fastrpc represents compute context banks available on the dsp.
75 const: qcom,fastrpc-compute-cb
126 compute-cb@1 {
127 compatible = "qcom,fastrpc-compute-cb";
132 compute-cb@2 {
133 compatible = "qcom,fastrpc-compute-cb";
138 compute-cb@3 {
139 compatible = "qcom,fastrpc-compute-cb";
/Linux-v6.6/tools/perf/pmu-events/arch/s390/cf_z16/
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-v6.6/Documentation/gpu/amdgpu/
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 …]
Damdgpu-glossary.rst22 Compute Unit
43 Graphics and Compute
75 Kernel Compute Queue
84 MicroEngine Compute
/Linux-v6.6/drivers/accel/
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-v6.6/drivers/iio/common/inv_sensors/
Dinv_sensors_timestamp.c13 /* compute jitter, min and max following jitter in per mille */
31 /* compute the mean of all stored values, use 0 as empty slot */ in inv_update_acc()
46 /* save chip parameters and compute min and max clock period */ in inv_sensors_timestamp_init()
135 /* update interrupt timestamp and compute chip and sensor periods */ in inv_sensors_timestamp_interrupt()
141 /* compute period: delta time divided by number of samples */ in inv_sensors_timestamp_interrupt()
146 /* no previous data, compute theoritical value from interrupt */ in inv_sensors_timestamp_interrupt()
177 * undertermined (depends when the change occures). So we compute the in inv_sensors_timestamp_apply_odr()
182 /* compute measured fifo period */ in inv_sensors_timestamp_apply_odr()
/Linux-v6.6/Documentation/driver-api/
Ddma-buf.rst239 * Long-running compute command buffers, while still using traditional end of
241 fences which get reattached when the compute job is rescheduled.
288 userspace is allowed to use userspace fencing or long running compute
311 faults on GPUs are limited to pure compute workloads.
314 compute side, like compute units or command submission engines. If both a 3D
315 job with a DMA fence and a compute workload using recoverable page faults are
318 - The 3D workload might need to wait for the compute job to finish and release
321 - The compute workload might be stuck in a page fault, because the memory
327 - Compute workloads can always be preempted, even when a page fault is pending
332 achieved through e.g. through dedicated engines and minimal compute unit
[all …]
/Linux-v6.6/arch/x86/events/amd/
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-v6.6/Documentation/devicetree/bindings/arm/bcm/
Dbcm2835.yaml22 - raspberrypi,4-compute-module
35 - raspberrypi,compute-module
52 - raspberrypi,3-compute-module
53 - raspberrypi,3-compute-module-lite
/Linux-v6.6/Documentation/hwmon/
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-v6.6/tools/perf/Documentation/
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-v6.6/lib/
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 …]
/Linux-v6.6/drivers/hwmon/
Dfam15h_power.c54 /* maximum accumulated power of a compute unit */
56 /* accumulated power of the compute units */
60 /* online/offline status of current compute unit */
143 * is compute unit id. in do_read_registers_on_cu()
172 * Choose the first online core of each compute unit, and then in read_registers()
174 * because the MSR value of CPU core represent the compute in read_registers()
187 /* get any CPU on this compute unit */ in read_registers()
211 * compute unit number. in power1_average_show()
233 /* check if current compute unit is online */ in power1_average_show()
422 * determine the ratio of the compute unit power accumulator in fam15h_power_init_data()
[all …]
/Linux-v6.6/arch/x86/include/asm/
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-v6.6/arch/powerpc/kernel/vdso/
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-v6.6/fs/xfs/libxfs/
Dxfs_rtbitmap.c116 * Compute and read in starting bitmap block for starting block. in xfs_rtfind_back()
132 * Compute match value, based on the bit at start: if 1 (free) in xfs_rtfind_back()
196 * Compute difference between actual and desired value. in xfs_rtfind_back()
243 * Compute difference between actual and desired value. in xfs_rtfind_back()
291 * Compute and read in starting bitmap block for starting block. in xfs_rtfind_forw()
307 * Compute match value, based on the bit at start: if 1 (free) in xfs_rtfind_forw()
369 * Compute difference between actual and desired value. in xfs_rtfind_forw()
413 * Compute difference between actual and desired value. in xfs_rtfind_forw()
461 * Compute entry number in the summary file. in xfs_rtmodify_summary_int()
465 * Compute the block number in the summary file. in xfs_rtmodify_summary_int()
[all …]
/Linux-v6.6/drivers/gpu/drm/amd/amdgpu/
Damdgpu_doorbell.h120 /* Compute + GFX: 0~255 */
175 /* 8 compute rings per GC. Max to 0x1CE */
187 /* Compute + GFX: 0~255 */
241 …* All compute related doorbells: kiq, hiq, diq, traditional compute queue, user queue, should loca…
243 * Compute related doorbells are allocated from 0x00 to 0x8a
254 /* Compute engines */
325 /* Compute: 0x08 ~ 0x20 */
/Linux-v6.6/Documentation/devicetree/bindings/interconnect/
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
/Linux-v6.6/drivers/clk/ti/
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-v6.6/Documentation/devicetree/bindings/arm/
Drockchip.yaml98 - description: Edgeble Neural Compute Module 2(Neu2) SoM based boards
100 - const: edgeble,neural-compute-module-2-io # Edgeble Neural Compute Module 2 IO Board
101 - const: edgeble,neural-compute-module-2 # Edgeble Neural Compute Module 2 SoM
104 - description: Edgeble Neural Compute Module 6(Neu6) Model A SoM based boards
106 - const: edgeble,neural-compute-module-6a-io # Edgeble Neural Compute Module 6A IO Board
107 - const: edgeble,neural-compute-module-6a # Edgeble Neural Compute Module 6A SoM
110 - description: Edgeble Neural Compute Module 6(Neu6) Model B SoM based boards
112 - const: edgeble,neural-compute-module-6b-io # Edgeble Neural Compute Module 6B IO Board
113 - const: edgeble,neural-compute-module-6b # Edgeble Neural Compute Module 6B SoM
672 - description: Radxa Compute Module 3(CM3)
/Linux-v6.6/arch/xtensa/lib/
Dstrncpy_user.S94 sub a2, a11, a2 # compute strlen
149 sub a2, a11, a2 # compute strlen
156 sub a2, a11, a2 # compute strlen
164 sub a2, a11, a2 # compute strlen
174 sub a2, a11, a2 # compute strlen
200 sub a2, a11, a2 # compute strlen
/Linux-v6.6/lib/raid6/
Dmktables.c64 /* Compute multiplication table */ in main()
83 /* Compute vector multiplication table */ in main()
108 /* Compute power-of-2 table (exponent) */ in main()
127 /* Compute log-of-2 table */ in main()
147 /* Compute inverse table x^-1 == x^254 */ in main()
162 /* Compute inv(2^x + 1) (exponent-xor-inverse) table */ in main()
/Linux-v6.6/Documentation/accel/
Dintroduction.rst7 The Linux compute accelerators subsystem is designed to expose compute
16 Typically, a compute accelerator will belong to one of the following
61 from trying to use an accelerator as a GPU, the compute accelerators will be
91 to expose both graphics and compute device char files should be handled by

12345678910>>...54