A processor includes: at least one operator; and at least one macro instruction processing unit configured to share the at least one operator, wherein the at least one macro instruction processing unit is configured to execute a macro instruction with respect to input data by using the at least one operator to output result data, and to control the at least one operator to perform an operation included in the macro instruction, and the at least one macro instruction processing unit comprises: a scheduler configured to manage schedules of the at least one operator and output input data and a control signal to the at least one operator; and a controller configured to control the scheduler to execute the macro instruction and to receive the result data from the scheduler.

In an embodiment, a coprocessor may include a bypass indication which identifies execution circuitry that is not used by a given processor instruction, and thus may be bypassed. The corresponding circuitry may be disabled during execution, preventing evaluation when the output of the circuitry will not be used for the instruction. In another embodiment, the coprocessor may implement a grid of processing elements in rows and columns, where a given coprocessor instruction may specify an operation that causes up to all of the processing elements to operate on vectors of input operands to produce results. Implementations of the coprocessor may implement a portion of the processing elements. The coprocessor control circuitry may be designed to operate with the full grid or partial grid, reissuing instructions in the partial grid case to perform the requested operation. In still another embodiment, the coprocessor may be able to fuse vector mode operations.

Aspects include circuitry that includes a first global generation counter (GGC) that is increased upon decoding of a branch instruction and a second GGC that is increased upon a completion of the branch instruction. Upon a triggered rollback, the first GGC is reset. The circuitry also includes a generation tag memory associated with a register that receives loads during a side-channel attacks which is set to the first GGC upon a first load, and a determination unit to determine, for a second load from an address depending on the register of the first load, a generation tag value associated with the register of the second load as a function of the first GGC, the second GGC, and the generation tag value associated with the register of the first load. A wait queue is configured to block the second load, if the generation tag is larger than the second GGC.

Apparatus and methods are disclosed for implementing block-based processors having custom function blocks, including field-programmable gate array (FPGA) implementations. In some examples of the disclosed technology, a dynamically configurable scheduler is configured to issue at least one block-based processor instruction. A custom function block is configured to receive input operands for the instruction and generate ready state data indicating completion of a computation performed for the instruction by the respective custom function block.

Examples described herein relate to a decompression engine that can request compressed data to be transferred over a memory bus. In some cases, the memory bus is a width that requires multiple data transfers to transfer the requested data. In a case that requested data is to be presented in-order to the decompression engine, a re-order buffer can be used to store entries of data. When a head-of-line entry is received, the entry can be provided to the decompression engine. When a last entry in a group of one or more entries is received, all entries in the group are presented in-order to the decompression engine. In some examples, a decompression engine can borrow memory resources allocated for use by another memory client to expand a size of re-order buffer available for use. For example, a memory client with excess capacity and a slowest growth rate can be chosen to borrow memory resources from.

A processor and an instruction scheduling method for X-channel interleaved multi-threading, where X is an integer greater than one. The processor includes a decoding unit and a processing unit. The decoding unit is configured to obtain one instruction from each of Z predefined threads in each cyclic period, decode the Z obtained instructions to obtain Z decoding results, and send the Z decoding results to the processing unit, where each cyclic period includes X sending periods, one decoding result is sent to the processing unit in each sending period, a decoding result of the Z decoding results may be repeatedly sent by the decoding unit in a plurality of sending periods, wherein 1≤Z<X or Z=X, and wherein Z is an integer. The processing unit (32) is configured to execute the instruction based on the decoding result.

Embodiments of systems, apparatuses, and methods for fused multiple add. In some embodiments, a decoder decodes a single instruction having an opcode, a destination field representing a destination operand, and fields for a first, second, and third packed data source operand, wherein packed data elements of the first and second packed data source operand are of a first, different size than a second size of packed data elements of the third packed data operand. Execution circuitry then executes the decoded single instruction to perform, for each packed data element position of the destination operand, a multiplication of a M N-sized packed data elements from the first and second packed data sources that correspond to a packed data element position of the third packed data source, add of results from these multiplications to a full-sized packed data element of a packed data element position of the third packed data source, and storage of the addition result in a packed data element position destination corresponding to the packed data element position of the third packed data source, wherein M is equal to the full-sized packed data element divided by N.

Technologies for data decompression include a computing device that reads a symbol tag byte from an input stream. The computing device determines whether the symbol can be decoded using a fast-path routine, and if not, executes a slow-path routine to decompress the symbol. The slow-path routine may include data-dependent branch instructions that may be unpredictable using branch prediction hardware. For the fast-path routine, the computing device determines a next symbol increment value, a literal increment value, a data length, and an offset based on the tag byte, without executing an unpredictable branch instruction. The computing device sets a source pointer to either literal data or reference data as a function of the tag byte, without executing an unpredictable branch instruction. The computing device may set the source pointer using a conditional move instruction. The computing device copies the data and processes remaining symbols. Other embodiments are described and claimed.

In an embodiment, a coprocessor may include a bypass indication which identifies execution circuitry that is not used by a given processor instruction, and thus may be bypassed. The corresponding circuitry may be disabled during execution, preventing evaluation when the output of the circuitry will not be used for the instruction. In another embodiment, the coprocessor may implement a grid of processing elements in rows and columns, where a given coprocessor instruction may specify an operation that causes up to all of the processing elements to operate on vectors of input operands to produce results. Implementations of the coprocessor may implement a portion of the processing elements. The coprocessor control circuitry may be designed to operate with the full grid or partial grid, reissuing instructions in the partial grid case to perform the requested operation. In still another embodiment, the coprocessor may be able to fuse vector mode operations.

In response to determining an operation is a dependent operation, a mapper of a processor determines the source registers of the operation from which the dependent operation depends. The mapper translates the dependent operation to a new operation that uses as its source operands at least one of the determined source registers and a source register of the dependent operation. The new operation is independent of other pending operations and therefore can be executed without waiting for execution of other operations, thus reducing execution latency.