Kandou Labs, S.a.

Brian Holden

Amin Shokrollahi

Richard D Simpson

Anant Singh

John Fox

Giuseppe Surace

Andrew Kevin John Stewart

Peter Hunt

John D Keay

Roger Ulrich

Ali Hormati

Harm Stefan Cronie

David Robert Stauffer

Andrew Stewart

Richard Simpson

John Keay

A pair of ground planes arranged in parallel, a dielectric medium disposed in between the pair of ground planes, and a set of at least four signal conductors disposed in the dielectric medium, the set of at least four signal conductors having (i) a first pair of signal conductors arranged proximate to a first ground plane of the pair of ground planes and (ii) a second pair of signal conductors arranged proximate to a second ground plane of the pair of ground planes, each signal conductor of the set of at least four signal conductors configured to carry a respective signal corresponding to a symbol of a codeword of a vector signaling code.

Methods and systems for high bandwidth communications interface

Orthogonal differential vector signalling (ODVS) techniques are described. The ODVS encoding schemes described herein generate one sub-channel for each bit by multiplying each bit by a different row in a transmitter encoding matrix to produce a set of sub-channels. Each wire carries a signal that is a superposition of elements from all of the sub-channels in the set. The transmitter encoding matrix is selected such that its rows (i.e. sub-channels) are mutual orthogonal. This means that the receiver can decode the signals received from all wires in concert to reliably recover the original bits. The transmitter encoding matrix applies weights to each sub-channel of the set, with the absolute magnitude of the weights decreasing as the number of wires associated with the respective sub-channel increases.

Pre-scaler for orthogonal differential vector signalling

Methods are described allowing a vector signaling code to encode multi-level data without the significant alphabet size increase known to cause symbol dynamic range compression and thus increased noise susceptibility. By intentionally restricting the number of codewords used, good pin efficiency may be maintained along with improved system signal-to-noise ratio.

Vector signaling code with improved noise margin

Pre-scaled orthogonal differential vector signalling (ODVS) techniques are described. The ODVS encoding schemes described herein generate one sub-channel for each bit by multiplying each bit by a different row in a transmitter encoding matrix to produce a set of sub-channels. Each wire carries a signal that is a superposition of elements from all of the sub-channels in the set. The transmitter encoding matrix is selected such that its rows (i.e. sub-channels) are mutual orthogonal. This means that the receiver can decode the signals received from all wires in concert to reliably recover the original bits. The transmitter encoding matrix is a Hadamard matrix in some cases. This disclosure is particularly focussed on ODVS techniques that apply a scaling factor, termed a 'pre-scaler', to a weaker sub-channel or sub-channels within the set of sub-channels so as to boost that/those sub-channel(s) relative to the other sub-channels.

Vector signaling codes providing guaranteed numbers of transitions per unit transmission interval are described, along with methods and systems for their generation and use. The described architecture may include multiple communications sub-systems, each having its own communications wire group or sub-channel, clock-embedded signaling code, pre- and post-processing stages to guarantee the desired code transition density, and global encoding and decoding stages to first distribute data elements among the sub-systems, and then to reconstitute the received data from its received sub-system elements.

Clock-embedded vector signaling codes

Orthogonal differential vector signaling codes are described which support encoded sub-channels allowing transport of distinct but temporally aligned data and clocking signals over the same transport medium. Embodiments providing enhanced LPDDR interfaces are described which are suitable for implementation in both conventional high-speed CMOS and DRAM integrated circuit processes.

Orthogonal differential vector signaling codes with embedded clock

Advanced detectors for vector signaling codes are disclosed which utilize multi-input comparators, generalized on-level slicing, reference generation based on maximum swing, and reference generation based on recent values. Vector signaling codes communicate information as groups of symbols which, when transmitted over multiple communications channels, may be received as mixed sets of symbols from different transmission groups due to propagation time variations between channels. Systems and methods are disclosed which compensate receivers and transmitters for these effects and/or utilize codes having increased immunity to such variations, and circuits are described that efficiently implement their component functions.

Methods and systems for skew tolerance in and advanced detectors for vector signaling codes for chip-to-chip communication

Systems and methods for an Enhanced High Bandwidth Memory (EHBM) are described, utilizing fewer physical wires than a HBM interface with each wire operating at a much higher signaling rate. The same logical signals and commands of HBM are supported over this higher-speed transport, with the resulting lower wire count and reduced signal density allowing use of lower-cost interconnection such as an organic rather than a silicon interposer between GPU and DRAM stack.

High speed memory interface

Systems and methods are described for transmitting data over physical channels to provide a high speed, low latency interface such as between a memory controller and memory devices. Controller-side and memory-side embodiments of such channel interfaces are disclosed which require a low pin count and have low power utilization. In some embodiments of the invention, different voltage, current, etc. levels are used for signaling and more than two levels may be used, such as a vector signaling code wherein each wire signal may take on one of four signal values.

Methods and systems for pin-efficient memory controller interface using vector signaling codes for chip-to-chip communication

Systems and methods are described for transmitting data over physical channels to provide a high bandwidth, low latency interface between a transmitting device and a receiving device operating at high speed with low power utilization. Communication is performed using group signaling over sets of four wires using a vector signaling code, where each wire of a set carries a low-swing signal that may take on one of four signal values. Topologies and designs of wire sets are disclosed with preferred characteristics for group signaling communications.

Growing community of inventors

Monte Sereno, CA, United States of America

Brian Holden