发明名称 |
Processor to execute shift right merge instructions |
摘要 |
Method, apparatus, and program means for performing bitstream buffer manipulation with a SIMD merge instruction. The method of one embodiment comprises determining whether any unprocessed data bits for a partial variable length symbol exist in a first data block is made. A shift merge operation is performed to merge the unprocessed data bits from the first data block with a second data block. A merged data block is formed. A merged variable length symbol comprised of the unprocessed data bits and a plurality of data bits from the second data block is extracted from the merged data block. |
申请公布号 |
US8782377(B2) |
申请公布日期 |
2014.07.15 |
申请号 |
US201213477544 |
申请日期 |
2012.05.22 |
申请人 |
Intel Corporation |
发明人 |
Sebot Julien;Macy William W.;Debes Eric;Nguyen Huy V. |
分类号 |
G06F9/30;G06F9/44;G06F15/00 |
主分类号 |
G06F9/30 |
代理机构 |
Blakely, Sokoloff, Taylor & Zafman LLP |
代理人 |
Blakely, Sokoloff, Taylor & Zafman LLP |
主权项 |
1. A system on a chip comprising:
a memory; a memory controller coupled with the memory; a graphics controller; and a plurality of processors, one of the processors comprising: a plurality of registers; a cache; an instruction decoder to decode a shift right merge instruction indicating a first 32-bit source operand and a second 32-bit source operand, the first 32-bit source operand including a first four 8-bit byte data elements, the second 32-bit source operand including a second four 8-bit byte data elements, wherein the 8-bit byte data elements are integers; and an execution unit that is part of a digital signal processor coupled with the instruction decoder and the plurality, of registers, the execution unit in response to the shift right merge instruction to: shift the second 32-bit source operand right by one byte, wherein the one byte amount to shift the second 32-bit source operand right by is fixed for a type of the shift right merge instruction; merge a least significant 8-bit byte data element of the first 32-bit source operand into a most significant byte position of the shifted second 32-bit source operand to generate a result; and store the result in a 32-bit destination indicated by the shift right merge instruction, wherein the system on the chip implements a combination of instruction sets including a very long instruction word (VLIW) instruction set that includes the shift right merge instruction. |
地址 |
Santa Clara CA US |