Image processing apparatus and magnetic-resonance imaging apparatus
US-2015369893-A1 · Dec 24, 2015 · US
US10915319B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10915319-B2 |
| Application number | US-201715595600-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 15, 2017 |
| Priority date | May 15, 2017 |
| Publication date | Feb 9, 2021 |
| Grant date | Feb 9, 2021 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An image processor is described. The image processor includes a two dimensional shift register array that couples certain ones of its array locations to support execution of a shift instruction. The shift instruction is to include mask information. The mask information is to specify which of the array locations are to be written to with information being shifted. The two dimensional shift register array includes masking logic circuitry to write the information being shifted into specified ones of the array locations in accordance with the mask information.
Opening claim text (preview).
The invention claimed is: 1. An image processor, comprising: an array of processing elements; and a two-dimensional shift-register array having circuitry configured to support execution of a masked shift instruction, the masked shift instruction having mask information, wherein the mask information specifies which array locations in the two-dimensional shift-register array are to be written to with data being shifted in the two-dimensional shift-register array, the two-dimensional shift-register array comprising masking logic circuitry configured to write the data being shifted into respective array locations in accordance with the mask information, wherein each processing element of the array of processing elements is configured to receive the masked shift instruction and to decode the masked shift instruction by using the mask information and a respective location of the processing element within the array of processing elements to determine whether or not the processing element should enable writing, to a shift-register dedicated to the processing element, data shifted by a different respective processing element in the array of processing elements. 2. The image processor of claim 1 , wherein the masking logic circuitry is distributed into array locations of the two-dimensional shift-register array. 3. The image processor of claim 1 , wherein the mask information comprises a code that specifies a write pattern over a subset of the two-dimensional shift-register array. 4. The image processor of claim 1 , wherein the mask information specifies which rows of the two-dimensional shift-register array are to be written to with data being shifted. 5. The image processor of claim 1 , wherein the mask information specifies which columns of the two-dimensional shift-register array are to be written to with data being shifted. 6. The image processor of claim 1 , wherein the mask information specifies that every other pair of columns of the two-dimensional shift-register array is to be written to with data being shifted. 7. The image processor of claim 1 , wherein the mask information specifies that every other quartet of columns of the two-dimensional shift-register array is to be written to with data being shifted. 8. One or more non-transitory machine-readable storage media encoded with program code having a masked shift instruction, wherein executing the program code by an image processor comprising an array of processing elements and a two-dimensional shift-register array causes the image processor to perform operations comprising: receiving, by the image processor, the masked shift instruction having mask information, wherein the mask information specifies which of the array locations are to be written to with data being shifted in the two-dimensional shift-register array; providing the masked shift instruction to each processing element of the array of processing elements; decoding, by each processing element of the array of processing elements, the masked shift instruction using the mask information and a respective location of the processing element within the array of processing elements to determine whether or not the processing element should enable writing, to a shift-register dedicated to the processing element, data shifted by a different respective processing element in the array of processing elements; receiving, by each processing element of the array of processing elements, data shifted by a different respective processing element in the array of processing elements; and writing, by each processing element of one or more processing elements, the data shifted by the different respective processing element based on decoding the masked shift instruction. 9. The one or more machine-readable storage media of claim 8 , wherein the two-dimensional shift-register array comprises a halo region and wherein the operations further comprise performing a halo extension emulation method. 10. The one or more machine-readable storage media of claim 8 , wherein the operations further comprise performing a compaction method that reduces an image size. 11. The one or more machine-readable storage media of claim 8 , wherein the operations further comprise performing an expansion method that enlarges an image size. 12. The one or more machine-readable storage media of claim 8 , wherein the operations further comprise performing a broadcast method that repeats a same value across multiple locations of the two-dimensional shift-register array. 13. The one or more machine-readable storage media of claim 8 , wherein the operations further comprise performing a butterfly operation. 14. A computing system, comprising: a plurality of general purpose processing cores; a main memory; a main memory controller coupled between the general purpose processing cores and the main memory; an image processor, the image processor comprising an array of processing elements; and a two-dimensional shift-register array having circuitry configured to support execution of a masked shift instruction, the masked shift instruction having mask information, wherein the mask information specifies which array locations in the two-dimensional shift-register array are to be written to with data being shifted in the two-dimensional shift-register array, the two-dimensional shift-register array comprising masking logic circuitry configured to write the data being shifted into respective array locations in accordance with the mask information, wherein each processing element of the array of processing elements is configured to receive the masked shift instruction and to decode the masked shift instruction by using the mask information and a respective location of the processing element within the array of processing elements to determine whether or not the processing element should enable writing, to a shift-register dedicated to the processing element, data shifted by a different respective processing element in the array of processing elements. 15. The computing system of claim 14 , wherein the masking logic circuitry is distributed into array locations of the two-dimensional shift-register array. 16. The computing system of claim 14 , wherein the mask information comprises a code that specifies a write pattern over a subset of the two-dimensional shift-register array. 17. The computing system of claim 14 , wherein the mask information specifies which rows of the two-dimensional shift-register array are to be written to with data being shifted. 18. The computing system of claim 14 , wherein the mask information specifies which columns of the two-dimensional shift-register array are to be written to with data being shifted. 19. The computing system of claim 14 , wherein the mask information specifies that every other pair of columns of the two-dimensional shift-register array is to be written to with data being shifted. 20. The computing system of claim 19 , wherein the mask information specifies that every other quartet of columns of the two-dimensional shift-register array is to be written to with data being shifted. 21. A method performed by an image processor comprising an array of processing elements and a two-dimensional shift-register array, the method comprising: receiving, by the image processor, a masked shift instruction having mask information, wherein the mask information specifies which array locations in the two-dimensional shift-register array are to be written to with data being shifted in the two-dimensional shift-regist
Processor architectures; Processor configuration, e.g. pipelining · CPC title
Dynamic range modification of images or parts thereof · CPC title
Register stacks; shift registers · CPC title
two-dimensional [2D], e.g. horizontal and vertical shift registers · CPC title
Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.