Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2results about How to "Guaranteed dynamic range" patented technology

Method for sampling ultra-wideband signals

ActiveCN114631264BGuaranteed testingguaranteed dynamic rangeAnalogue/digital conversionTransmissionUltra-widebandConverters
A method for sampling an ultra-wideband signal, the method comprising the steps of pre-arranging a GPR antenna comprising at least one transmitter and one receiver, a variable gain amplifier or VGA, an A / D converter and a control unit. Then, the method comprises the steps of transmitting and receiving a primary ultra-wideband signal by the GPR antenna, and sampling a value of the primary ultra-wideband signal by the A / D converter with respect to a first full-scale portion. The method further comprises the steps of transmitting and receiving at least one secondary ultra-wideband signal by the GPR antenna, amplifying the secondary ultra-wideband signal by the variable gain amplifier, and sampling a value of the secondary ultra-wideband signal by the A / D converter with respect to a full-scale portion different from the first portion.
Owner:アイディーエスゲオラダルエスアールエル

Low-bit matrix computation device with floating-point scaling factor and computation method thereof

ActiveCN121350393Bsolve computational puzzlesSolve the complex calculation processAlgorithmFloating point
The application discloses a low-bit matrix calculation device with a floating-point scaling factor and a calculation method thereof. The device comprises a scaling factor processing module, an input module, a matrix calculation module, a floating-point accumulation module and an output module. The method first groups and quantizes weight and eigenvalue matrices to obtain quantization values and floating-point scaling factors; then, the scaling factor product is calculated in advance with a single accumulation length as a grouping unit; then, matrix multiplication and accumulation operation is performed, the result is multiplied by the scaling factor product after being converted into an fp16 or bfp16 format, and then accumulated into a final result; and finally, the result is output after being dequantized. The application simplifies the group-wise calculation process, saves hardware resources, guarantees calculation accuracy, meets different scene requirements and improves calculation efficiency by sharing the scaling factor product and using fp16 or bfp16 as an accumulator.
Owner:JINDIE SPACETIME (BEIJING) TECHNOLOGY CO LTD