Karan Sanghi

20130332764, Dec 12, 2013

Sep 28, 2012

13/631360

Arun G. Mathias - Los Altos CA, US
Karan Sanghi - Mountain View CA, US

APPLE INC. - Cupertino CA

G06F 1/00

713324, 713300, 713320

One embodiment of the present invention provides a system that facilitates intelligent inter-processor communication with power optimization. The system comprises a memory, a first router, a second router, a first physical link coupled between the first router and the second router, and a second physical link coupled between the first router and the second router. Furthermore, the system comprises a first communication bus implemented on the first physical link, as well as a second communication bus implemented on the second physical link. Note that the second communication bus provides lower power consumption and lower bandwidth than the first communication bus. During operation, the system receives a packet at the first router, wherein the packet is destined for the second router. Next, the system selects either the first communication bus or the second communication bus over which to route the packet. Finally, the system routes the packet according to the selection.

20210026715, Jan 28, 2021

Nov 21, 2019

16/691370

- Cupertino CA, US
Karan Sanghi - San Jose CA, US
Saurabh Garg - San Jose CA, US

G06F 9/54
G06F 13/362
H04L 25/00
G06F 9/46
G06F 13/16
G06F 13/42

Methods and apparatus for scheduling time sensitive operations among independent processors. In one embodiment, an application processor (AP) determines transmission timing parameters for a baseband processor (BB). Thereafter, the AP can generate and transact generic time-sensitive RTP data with the BB in time for transmission via a Long Term Evolution (LTE) communication stack. In this manner, the AP's scheduler can coordinate/accommodate digital audio tasks within the context of its other tasks (e.g., to enable intelligent sleep and wake-up operation, load balancing, memory usage, and/or any number of other processor management functions).

20200218326, Jul 9, 2020

Mar 16, 2020

16/820307

- Cupertino CA, US
Karan Sanghi - Cupertino CA, US
Vladislav Petkov - Cupertino CA, US
Richard Solotke - Cupertino CA, US

G06F 1/3234
G06F 13/40
G06F 13/42
G06F 1/3203
G06F 1/3287
G06F 9/30
G06F 9/4401

Methods and apparatus for isolation of sub-system resources (such as clocks, power, and reset) within independent domains. In one embodiment, each sub-system of a system has one or more dedicated power and clock domains that operate independent of other sub-system operation. For example, in an exemplary mobile device with cellular, WLAN and PAN connectivity, each such sub-system is connected to a common memory mapped bus function, yet can operate independently. The disclosed architecture advantageously both satisfies the power consumption limitations of mobile devices, and concurrently provides the benefits of memory mapped connectivity for high bandwidth applications on such mobile devices.

20190377703, Dec 12, 2019

Jun 24, 2019

16/450767

- Cupertino CA, US
Saurabh Garg - San Jose CA, US
Karan Sanghi - San Jose CA, US
Haining Zhang - Cupertino CA, US

G06F 15/17
G06F 13/42
H04W 4/80

Methods and apparatus for data transmissions over an inter-processor communication (IPC) link between two (or more) independently operable processors. In one embodiment, the IPC link is configured to enable an independently operable processor to transact data to another independently operable processor, while obviating transactions (such as via direct memory access) by encapsulating a payload within a data structure. For example, a host processor may insert the payload into a transfer descriptor (TD), and transmit the TD to a peripheral processor. The host processor may also include a head index and/or a tail index within a doorbell message sent to the peripheral processor, obviating another access of memory. The peripheral processor may perform similar types of transactions via a completion descriptor (CD) sent to the host processor. In some variants, the peripheral may be a Bluetooth-enabled device optimized for low-latency, low-power, and/or low-throughput transactions.

20190332450, Oct 31, 2019

Jul 8, 2019

16/505446

- Cupertino CA, US
Karan Sanghi - San Jose CA, US
Saurabh Garg - San Jose CA, US

G06F 9/54
G06F 13/362
H04L 25/00
G06F 13/16
G06F 9/46
G06F 13/42

Methods and apparatus for time sensitive data transfer between logical domains. In one embodiment, an user equipment (UE) device has an application processor (AP) coupled to a baseband processor (BB) that operate independently of one another normally, but may cooperate in limited hybrid use scenarios. For example, the BB receives audio packets via a cellular network that are converted to pulse code modulated (PCM) digital audio to be played by the AP. Unfortunately, since the AP and the BB are independently clocked, they will experience some clock drift. As a result, the audio playback may have undesirable artifacts if the drift is not otherwise compensated for. To these ends, the AP and/or BB determine a relative clock drift and compensate for playback by e.g., adding, padding, or deleting audio samples and/or audio packets. Techniques for handover scenarios are also disclosed.

20190303204, Oct 3, 2019

Sep 27, 2018

16/144992

- Cupertino CA, US
Karan Sanghi - San Jose CA, US
Mingzhe Zhang - Santa Clara CA, US
Sandeep Nair - San Jose CA, US

G06F 9/50
G06F 3/06

Methods and apparatus for efficient data transfer within a user space network stack. Unlike prior art monolithic networking stacks, the exemplary networking stack architecture described hereinafter includes various components that span multiple domains (both in-kernel, and non-kernel). For example, unlike traditional “socket” based communication, disclosed embodiments can transfer data directly between the kernel and user space domains. Direct transfer reduces the per-byte and per-packet costs relative to socket based communication. A user space networking stack is disclosed that enables extensible, cross-platform-capable, user space control of the networking protocol stack functionality. The user space networking stack facilitates tighter integration between the protocol layers (including TLS) and the application or daemon. Exemplary systems can support multiple networking protocol stack instances (including an in-kernel traditional network stack).

20190303222, Oct 3, 2019

Mar 28, 2019

16/368214

- Cupertino CA, US
KARAN SANGHI - Cupertino CA, US
MINGZHE ZHANG - Cupertino CA, US
JASON MCELRATH - Cupertino CA, US
SANDEEP NAIR - San Jose CA, US

G06F 9/54
G06F 9/48
H04L 12/26

Methods and apparatus for efficient data transfer within a user space network stack. Unlike prior art monolithic networking stacks, the exemplary networking stack architecture described hereinafter includes various components that span multiple domains (both in-kernel, and non-kernel). For example, unlike traditional “socket” based communication, disclosed embodiments can transfer data directly between the kernel and user space domains. Direct transfer reduces the per-byte and per-packet costs relative to socket based communication. A user space networking stack is disclosed that enables extensible, cross-platform-capable, user space control of the networking protocol stack functionality. The user space networking stack facilitates tighter integration between the protocol layers (including TLS) and the application or daemon. Exemplary systems can support multiple networking protocol stack instances (including an in-kernel traditional network stack).

20190306281, Oct 3, 2019

Sep 28, 2018

16/146533

- Cupertino CA, US
Sandeep Nair - Cupertino CA, US
Karan Sanghi - Cupertino CA, US
Mingzhe Zhang - Cupertino CA, US
Jason McElrath - Cupertino CA, US

H04L 29/06
H04L 12/46
G06F 9/54

Methods and apparatus for efficient data transfer within a user space network stack. Unlike prior art monolithic networking stacks, the exemplary networking stack architecture described hereinafter includes various components that span multiple domains (both in-kernel, and non-kernel). For example, unlike traditional “socket” based communication, disclosed embodiments can transfer data directly between the kernel and user space domains. Direct transfer reduces the per-byte and per-packet costs relative to socket based communication. A user space networking stack is disclosed that enables extensible, cross-platform-capable, user space control of the networking protocol stack functionality. The user space networking stack facilitates tighter integration between the protocol layers (including TLS) and the application or daemon. Exemplary systems can support multiple networking protocol stack instances (including an in-kernel traditional network stack).