摘要:
A processor (12) to coprocessor (14) interface supporting multiple coprocessors (14, 16) utilizes compiler generatable software type function call and return, instruction execute, and variable load and store interface instructions. Data is moved between the processor (12) and coprocessor (14) on a bi-directional shared bus (28) either implicitly through register snooping and broadcast, or explicitly through function call and return and variable load and store interface instructions. The load and store interface instructions allow selective memory address preincrementation. The bi-directional bus (28) is potentially driven both ways on each clock cycle. The interface separates interface instruction decode and execution. Pipelined operation is provided by indicating decoded instruction discard by negating a decode signal before an execute signal is asserted.
摘要:
Storage circuitry (66) may be used to store the values of fuses (77) so that storage circuitry (66) can be read instead of fuses (77). By accessing the fuse values from storage circuitry (66) rather than from fuses (77), there will be no sense current to fuses (77) that may cause marginal fuse blowage for fuses that have not yet been blown. This helps to prevent the situation in which an unblown fuse is erroneously read as having been blown. The use of storage circuitry (66) thus significantly improves the reliability of fuse module (20). For some embodiments, selection storage circuitry (64) may be used to determine whether storage circuitry (66) may be read or whether one of fuses (77) must be read in order to retrieve the desired current fuse value. The fuse value stored in storage circuitry (66) can also be used as direct hardware signals (80).
摘要:
A method and apparatus is provided for prefetching in a data processing system (10). The data processing system (10) has a bus master (14) and a memory controller (16) coupled to a bus (12). A memory (18) is coupled to the memory controller (16). In the data processing system (14) an address is driven onto the bus (12). Before the address is qualified, data corresponding to the address is prefetched. Prefetching the data before the address is qualified allows prefetches to be accomplished sooner.
摘要:
In current real-time debug systems, debug messages are transmitted through a limited bandwidth port (18) from an integrated circuit (10) to an external development system (25). As some integrated circuits (10) become even more densely packed with multiple bus masters (11, 12) and/or multiple busses (16) capable of generating messages, it is becoming more and more difficult for the limited bandwidth port (18) to sufficiently support the volume of debug messages that are to be transmitted from an integrated circuit (10) to an external development system (25). A plurality of masks (70, 80, 90, 100, 110, 120, 130, 140, 150) and masking circuitry (36) may be used to selectively mask portions (41-45, 51-55) of debug messages (40, 50) in order to significantly improve bandwidth.
摘要:
A method (200) and apparatus (100) for allocating entries in a branch target buffer (BTB) (144) in a pipelined data processing system includes: sequentially fetching instructions; determining that one of the instructions is a branch instruction (210, 215, 220); decoding the branch instruction to determine a branch target address; determining if the branch target address can be obtained without causing a stall condition in the pipelined data processing system; and selectively allocating an entry of the BTB (144) based on the determination. In one embodiment, an entry of the BTB (144) is allocated if the branch instruction is not loaded into a predetermined slot (S1) of a prefetch buffer (102) and no other stall condition will occur. The method (200) and apparatus (100) combine the advantages of using a BTB (144) and branch lookahead to reduce stall conditions in the data processing system.
摘要:
New approaches for providing communication between multiple masters (12, 14) and one or more shared resources (24, 30, 100) are needed. One example of a resource that may need to be shared is circuitry complying with the Universal Serial Bus (USB) standard (100). The USB specification defines the use of USB endpoints as data and control channels that reside in a USB device. In some cases it is desirable to have a certain number of endpoints controlled by one processor, and other endpoints controlled by a different processor, thus providing a shared control of all the endpoints. Circuitry (402, 417, 480) may be used to provide steering for additional signals such as interrupts. Other shared resources (24, 30) may use more centralized circuitry (36) to perform a steering function for additional signals.
摘要:
Various load and store instructions may be used to transfer multiple vector elements between registers in a register file and memory. A cnt parameter may be used to indicate a total number of elements to be transferred to or from memory, and an rcnt parameter may be used to indicate a maximum number of vector elements that may be transferred to or from a single register within a register file. Also, the instructions may use a variety of different addressing modes. The memory element size may be specified independently from the register element size such that source and destination sizes may differ within an instruction. With some instructions, a vector stream may be initiated and conditionally enqueued or dequeued. Truncation or rounding fields may be provided such that source data elements may be truncated or rounded when transferred. Also, source data elements may be sign- or unsigned- extended when transferred.
摘要:
Various load and store instructions may be used to transfer multiple vector elements between registers in a register file and memory. A cnt parameter may be used to indicate a total number of elements to be transferred to or from memory, and an rcnt parameter may be used to indicate a maximum number of vector elements that may be transferred to or from a single register within a register file. Also, the instructions may use a variety of different addressing modes. The memory element size may be specified independently from the register element size such that source and destination sizes may differ within an instruction. With some instructions, a vector stream may be initiated and conditionally enqueued or dequeued. Truncation or rounding fields may be provided such that source data elements may be truncated or rounded when transferred. Also, source data elements may be sign- or unsigned-extended when transferred.
摘要:
A crossbar switch (12) arbitrates for access from multiple bus masters (14, 16, 18, 20 and 22) to multiple addressed slave ports (3 and 4) that have overlapping address ranges. In one form, the address ranges are the same address range. The crossbar switch (12) uses shared slave port control circuitry (48), configuration registers (46) and slave port arbiter logic (34, 36, 38, 40, 42 and 44) to arbitrate for access when all the addressed ports are busy. A determination is made as to whether new access requests are higher or lower in priority than existing accesses. A determination on where to direct a new access request is made based upon a prediction of which of certain multiple accesses will complete first based on various factors including the number of data beats requested as well as wait state information. In one mode, the wait state information is determined dynamically.
摘要:
A protective covering for a horse's hoof is provided which comprises a horseshoe having convex and concave edges and a polymeric fiber fabric embedded in a polymeric resin bonded to the horseshoe. The fabric extends beyond the convex edge of the horseshoe. When the shoe is fitted to the horse's hoof, the fabric extends up over the outside of the hoof. The protective covering is secured to the hoof using an acrylic structural adhesive both between the hoof and the shoe and between the polymeric fiber fabric and the outside of the hoof. The polymeric fiber fabric is preferably a polyolefin, and particularly preferred is woven polyethylene. The polymeric resin is preferably polyurethane.