Patent Grant
11080048
The field of invention relates generally to computer processor architecture, and, more specifically, to matrix manipulation.
Matrices are increasingly important in many computing tasks such as machine learning and other bulk data processing.
The present invention is illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements and in which:
In the following description, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known circuits, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.
References in the specification to “one embodiment,” “an embodiment,” “an example embodiment,” etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.
In many mainstream processors, handling matrices is a difficult and/or instruction intensive task. For example, rows of a matrix could be put into a plurality of packed data (e.g., SIMD or vector) registers and then operated on individually. For example, an add two 8×2 matrices may require a load or gather into four packed data registers depending upon data sizes. Then a first add of packed data registers corresponding to a first row from each matrix is performed and a second add of packed data registers corresponding to a second row from each matrix is performed. Then the resulting packed data registers are scattered back to memory. While for small matrices this scenario may be acceptable, it is often not acceptable with larger matrices.
I. High-Level Discussion
Described herein are mechanisms to support matrix operations in computer hardware such as central processing units (CPUs), graphic processing units (GPUs), and accelerators. The matrix operations utilize 2-dimensional (2-D) data structures representing one or more packed regions of memory such as registers. Throughout this description, these 2-D data structures are referred to as tiles. Note that a matrix may be smaller than a tile (use less than all of a tile), or utilize a plurality of tiles (the matrix is larger than the size of any one tile). Throughout the description, matrix (tile) language is used to indicate operations performed using tiles that impact a matrix; whether or not that matrix is larger than any one tile is not typically relevant.
Each tile may be acted upon by different operations such as those that are detailed herein and include, but are not limited to: matrix (tile) multiplication, tile add, tile subtract, tile diagonal, tile zero, tile transpose, tile dot product, tile broadcast, tile row broadcast, tile column broadcast, tile multiplication, tile multiplication and accumulation, tile move, etc. Additionally, support for operators such as the use of a scale and/or bias may be used with these operations or in support of non-numeric applications in the future, for instance, OpenCL “local memory,” data compression/decompression, etc.
Portions of storage (such as memory (non-volatile and volatile), registers, cache, etc.) are arranged into tiles of different horizontal and vertical dimensions. For example, a tile may have horizontal dimension of 4 (e.g., four rows of a matrix) and a vertical dimension of 8 (e.g., 8 columns of the matrix). Typically, the horizontal dimension is related to element sizes (e.g., 2-, 4-, 8-, 16-, 32-, 64-, 128-bit, etc.). Multiple datatypes (single precision floating point, double precision floating point, integer, etc.) may be supported.
A. Exemplary Usage of Configured Tiles
In some embodiments, tile parameters are definable. For example, a “palette” is used to provide tile options. Exemplary options include, but are not limited to: the number of tile names, the number of bytes in a row of storage, the number of rows and columns in a tile, etc. For example, a maximum “height” (number of rows) of a tile may be defined as:
Tile Max Rows=Architected Storage/(The Number of Palette Names*The Number of Bytes per row)
As such, an application can be written such that a fixed usage of names will be able to take advantage of different storage sizes across implementations.
Configuration of tiles is done using a tile configuration (“TILECONFIG”) instruction, where a particular tile usage is defined in a selected palette. This declaration includes the number of tile names to be used, the requested number of rows and columns per name (tile), and, in some embodiments, the requested datatype of each tile. In some embodiments, consistency checks are performed during the execution of a TILECONFIG instruction to determine that it matches the restrictions of the palette entry.
B. Exemplary Tile Storage Types
Tile loads from memory and stores to memory are typically strided accesses from the application memory to packed rows of data. Exemplary TILELOAD and TILESTORE instructions, or other instruction references to application memory as a TILE operand in load-op instructions, are, in some embodiments, restartable to handle (up to) 2*rows of page faults, unmasked floating point exceptions, and/or interrupts per instruction.
In (B), a matrix is stored in a tile comprised of a plurality of registers such as packed data registers (single instruction, multiple data (SIMD) or vector registers). In this example, the tile is overlaid on three physical registers. Typically, consecutive registers are used, however, this need not be the case.
In (C), a matrix is stored in a tile in non-register storage accessible to a fused multiple accumulate (FMA) circuit used in tile operations. This storage may be inside of a FMA, or adjacent to it. Additionally, in some embodiments, discussed below, the storage may be for a data element and not an entire row or tile.
The supported parameters for the TMMA architecture are reported via CPUID. In some embodiments, the list of information includes a maximum height and a maximum SIMD dimension. Configuring the TMMA architecture requires specifying the dimensions for each tile, the element size for each tile and the palette identifier. This configuration is done by executing the TILECONFIG instruction.
Successful execution of a TILECONFIG instruction enables subsequent TILE operators. A TILERELEASEALL instruction clears the tile configuration and disables the TILE operations (until the next TILECONFIG instructions executes). In some embodiments, XSAVE, XSTORE, etc. are used in context switching using tiles. In some embodiments, 2 XCR0 bits are used in XSAVE, one for TILECONFIF metadata and one bit corresponding to actual tile payload data.
TILECONFIG not only configures the tile usage, but also sets a state variable indicating that the program is in a region of code with tiles configured. An implementation may enumerate restrictions on other instructions that can be used with a tile region such as no usage of an existing register set, etc.
Exiting a tile region is typically done with the TILERELEASEALL instruction. It takes no parameters and swiftly invalidates all tiles (indicating that the data no longer needs any saving or restoring) and clears the internal state corresponding to being in a tile region.
In some embodiments, tile operations will zero any rows and any columns beyond the dimensions specified by the tile configuration. For example, tile operations will zero the data beyond the configured number of columns (factoring in the size of the elements) as each row is written. For example, with 64 byte rows and a tile configured with 10 rows and 12 columns, an operation writing FP32 elements would write each of the first 10 rows with 12*4 bytes with output/result data and zero the remaining 4*4 bytes in each row. Tile operations also fully zero any rows after the first 10 configured rows. When using 1K tile with 64 byte rows, there would be 16 rows, so in this example, the last 6 rows would also be zeroed.
In some embodiments, a context restore (e.g., XRSTOR), when loading data, enforces that the data beyond the configured rows for a tile will be maintained as zero. If there is no valid configuration, all rows are zeroed. XRSTOR of tile data can load garbage in the columns beyond those configured. It should not be possible for XRSTOR to clear beyond the number of columns configured because there is not an element width associated with the tile configuration.
Context save (e.g., XSAVE) exposes the entire TILE storage area when writing it to memory. If XRSTOR loaded garbage data in to the rightmost part of a tile, that data will be saved by XSAVE. XSAVE will write zeros for rows beyond the number specified for each tile.
In some embodiments, tile instructions are restartable. The operations that access memory allow restart after page faults. The computational instructions that deal with floating point operations also allow for unmasked floating point exceptions, with the masking of the exceptions controlled by a control and/or status register.
To support restarting instructions after these events, the instructions store information in the start registers detailed below.
II. Matrix (Tile) Operation Systems
A. Exemplary Hardware Support
In this example, a coherent memory interface 303 is coupled to the host processor/processing system 301 and matrix operations accelerator 405 such that they can share memory.
The matrix operations accelerator 307 includes a plurality of FMAs 309 coupled to data buffers 305 (in some implementations, one or more of these buffers 305 are stored in the FMAs of the grid as shown). The data buffers 305 buffer tiles loaded from memory and/or tiles to be stored to memory (e.g., using a tileload or tilestore instruction). Data buffers may be, for example, a plurality of registers. Typically, these FMAs are arranged as a grid of chained FMAs 309 which are able to read and write tiles. In this example, the matrix operations accelerator 307 is to perform a matrix multiply operation using tiles T0, T1, and T2. At least one of tiles is housed in the FMA grid 309. In some embodiments, all tiles in an operation are stored in the FMA grid 309. In other embodiments, only a subset are stored in the FMA grid 309. As shown, T1 is housed and T0 and T2 are not. Note that A, B, and C refer to the matrices of these tiles which may or may not take up the entire space of the tile.
The number of rows in the matrix (TILE A 601) matches the number of serial (chained) FMAs comprising the computation's latency. An implementation is free to recirculate on a grid of smaller height, but the computation remains the same.
The source/destination vector comes from a tile of N rows (TILE C 605) and the grid of FMAs 611 performs N vector-matrix operations resulting in a complete instruction performing a matrix multiplication of tiles. Tile B 603 is the other vector source and supplies “broadcast” terms to the FMAs in each stage.
In operation, in some embodiments, the elements of matrix B (stored in a tile B 603) are spread across the rectangular grid of FMAs. Matrix B (stored in tile A 601) has its elements of a row transposed to match up with the columnar dimension of the rectangular grid of FMAs. At each FMA in the grid, an element of A and B are multiplied and added to the incoming summand (from above in the Figure) and the outgoing sum is passed to the next row of FMAs (or the final output).
The latency of a single step is proportional to K (row height of matrix B) and dependent TMMAs typically have enough source-destination rows (either in a single tile or across tile) to hide that latency. An implementation may also split the SIMD (packed data element) dimension M (row height of matrix A) across time steps, but this simply changes the constant that K is multiplied by. When a program specifies a smaller K than the maximum enumerated by the TMACC, an implementation is free to implement this with “masking” or “early outs.”
The latency of an entire TMMA is proportional to N*K. The repeat rate is proportional to N. The number of MACs per TMMA instruction is N*K*M.
A first signed source (source 1701) and a second signed source (source 2703) each have four packed data elements. Each of these packed data elements stores signed data such as floating point data. A third signed source (source 3709) has two packed data elements, each of which stores signed data. The sizes of the first and second signed sources 701 and 703 are half that of the third signed source (initial value or previous result) 709. For example, the first and second signed sources 701 and 703 could have 32-bit packed data elements (e.g., single precision floating point) while the third signed source 709 could have 64-bit packed data elements (e.g., double precision floating point).
In this illustration, only the two most significant packed data element positions of the first and second signed sources 701 and 703 and the most significant packed data element position of the third signed source 709 are shown. Of course, the other packed data element positions would also be processed.
As illustrated, packed data elements are processed in pairs. For example, the data of the most significant packed data element positions of the first and second signed sources 701 and 703 are multiplied using a multiplier circuit 705, and the data from second most significant packed data element positions of the first and second signed sources 701 and 703 are multiplied using a multiplier circuit 707. In some embodiments, these multiplier circuits 705 and 707 are reused for other packed data elements positions. In other embodiments, additional multiplier circuits are used so that the packed data elements are processed in parallel. In some contexts, parallel execution is done using lanes that are the size of the signed third source 709. The results of each of the multiplications are added using addition circuitry 711.
The result of the addition of the results of the multiplications is added to the data from most significant packed data element position of the signed source 3709 (using a different adder 713 or the same adder 711).
Finally, the result of the second addition is either stored into the signed destination 715 in a packed data element position that corresponds to the packed data element position used from the signed third source 709, or passed on to the next iteration, if there is one. In some embodiments, a writemask is applied to this storage such that if a corresponding writemask (bit) is set, the storage happens, and, if not set, the storage does not happen.
A first signed source (source 1801) and a second signed source (source 2803) each have four packed data elements. Each of these packed data elements stores signed data such as integer data. A third signed source (source 3809) has two packed data elements, each of which stores signed data. The sizes of the first and second signed sources 801 and 803 are half that of the third signed source 809. For example, the first and second signed sources 801 and 803 could have 32-bit packed data elements (e.g., single precision floating point) the third signed source 809 could have 64-bit packed data elements (e.g., double precision floating point).
In this illustration, only the two most significant packed data element positions of the first and second signed sources 801 and 803 and the most significant packed data element position of the third signed source 809 are shown. Of course, the other packed data element positions would also be processed.
As illustrated, packed data elements are processed in pairs. For example, the data of the most significant packed data element positions of the first and second signed sources 801 and 803 are multiplied using a multiplier circuit 805, and the data from second most significant packed data element positions of the first and second signed sources 801 and 803 are multiplied using a multiplier circuit 807. In some embodiments, these multiplier circuits 805 and 807 are reused for other packed data elements positions. In other embodiments, additional multiplier circuits are used so that the packed data elements are processed in parallel. In some contexts, parallel execution is done using lanes that are the size of the signed third source (initial value or previous iteration result) 809. The results of each of the multiplications are added to the signed third source 809 using addition/saturation circuitry 811.
Addition/saturation (accumulator) circuitry 811 preserves a sign of an operand when the addition results in a value that is too big. In particular, saturation evaluation occurs on the infinite precision result between the multi-way-add and the write to the destination or next iteration. When the accumulator 811 is floating point and the input terms are integer, the sum of products and the floating point accumulator input value are turned into infinite precision values (fixed point numbers of hundreds of bits), the addition of the multiplication results and the third input is performed, and a single rounding to the actual accumulator type is performed.
Unsigned saturation means the output values are limited to a maximum unsigned number for that element width (all 1s). Signed saturation means a value is limited to the be in the range between a minimum negative number and a max positive number for that element width (for bytes for example, the range is from −128 (=−2{circumflex over ( )}7) to 127(=2{circumflex over ( )}7−1)).
The result of the addition and saturation check is stored into the signed result 815 in a packed data element position that corresponds to the packed data element position used from the signed third source 809, or passed on to the next iteration if there is one. In some embodiments, a writemask is applied to this storage such that if a corresponding writemask (bit) is set, the storage happens, and, if not set, the storage does not happen.
A first signed source (source 1901) and a second unsigned source (source 2903) each have four packed data elements. Each of these packed data elements has data such as floating point or integer data. A third signed source (initial value or result 915) has a packed data element of which stores signed data. The sizes of the first and second sources 901 and 903 are a quarter of the third signed source 915. For example, the first and second sources 901 and 903 could have 16-bit packed data elements (e.g., word) and the third signed source 915 could have 64-bit packed data elements (e.g., double precision floating point or 64-bit integer).
In this illustration, the four most significant packed data element positions of the first and second sources 901 and 903 and the most significant packed data element position of the third signed source 915 are shown. Of course, other packed data element positions would also be processed if there are any.
As illustrated, packed data elements are processed in quadruplets. For example, the data of the most significant packed data element positions of the first and second sources 901 and 903 are multiplied using a multiplier circuit 907, data from second most significant packed data element positions of the first and second sources 901 and 903 are multiplied using a multiplier circuit 907, data from third most significant packed data element positions of the first and second sources 901 and 903 are multiplied using a multiplier circuit 909, and data from the least significant packed data element positions of the first and second sources 901 and 903 are multiplied using a multiplier circuit 911. In some embodiments, the signed packed data elements of the first source 901 are sign extended and the unsigned packed data elements of the second source 903 are zero extended prior to the multiplications.
In some embodiments, these multiplier circuits 905-911 are reused for other packed data elements positions. In other embodiments, additional multiplier circuits are used so that the packed data elements are processed in parallel. In some contexts, parallel execution is done using lanes that are the size of the signed third source 915. The results of each of the multiplications are added using addition circuitry 911.
The result of the addition of the results of the multiplications is added to the data from most significant packed data element position of the signed source 3915 (using a different adder 913 or the same adder 911).
Finally, the result 919 of the second addition is either stored into the signed destination in a packed data element position that corresponds to the packed data element position used from the signed third source 915, or passed to the next iteration. In some embodiments, a writemask is applied to this storage such that if a corresponding writemask (bit) is set, the storage happens, and, if not set, the storage does not happen.
A first signed source (source 11001) and a second unsigned source (source 21003) each have four packed data elements. Each of these packed data elements stores data such as floating point or integer data. A third signed source (initial or previous result 1015) has a packed data element of which stores signed data. The sizes of the first and second sources 1001 and 1003 are a quarter of the third signed source 1015. For example, the first and second sources 1001 and 1003 could have 16-bit packed data elements (e.g., word) and the third signed source 1015 could have 64-bit packed data elements (e.g., double precision floating point or 64-bit integer).
In this illustration, the four most significant packed data element positions of the first and second sources 1001 and 1003 and the most significant packed data element position of the third signed source 1015 are shown. Of course, other packed data element positions would also be processed if there are any.
As illustrated, packed data elements are processed in quadruplets. For example, the data of the most significant packed data element positions of the first and second sources 1001 and 1003 are multiplied using a multiplier circuit 1007, data from second most significant packed data element positions of the first and second sources 1001 and 1003 are multiplied using a multiplier circuit 1007, data from third most significant packed data element positions of the first and second sources 1001 and 1003 are multiplied using a multiplier circuit 1009, and data from the least significant packed data element positions of the first and second sources 1001 and 1003 are multiplied using a multiplier circuit 1011. In some embodiments, the signed packed data elements of the first source 1001 are sign extended and the unsigned packed data elements of the second source 1003 are zero extended prior to the multiplications.
In some embodiments, these multiplier circuits 1005-1011 are reused for other packed data elements positions. In other embodiments, additional multiplier circuits are used so that the packed data elements are processed in parallel. In some contexts, parallel execution is done using lanes that are the size of the signed third source 1015. The result of the addition of the results of the multiplications is added to the data from most significant packed data element position of the signed source 31015 using addition/saturation circuitry 1013.
Addition/saturation (accumulator) circuitry 1013 preserves a sign of an operand when the addition results in a value that is too big or too small for signed saturation. In particular, saturation evaluation occurs on the infinite precision result between the multi-way-add and the write to the destination. When the accumulator 1013 is floating point and the input terms are integer, the sum of products and the floating point accumulator input value are turned into infinite precision values (fixed point numbers of hundreds of bits), the addition of the multiplication results and the third input is performed, and a single rounding to the actual accumulator type is performed.
The result 1019 of the addition and saturation check is stored into the signed destination in a packed data element position that corresponds to the packed data element position used from the signed third source 1015, or passed to the next iteration. In some embodiments, a writemask is applied to this storage such that if a corresponding writemask (bit) is set, the storage happens, and, if not set, the storage does not happen.
For an accumulator having 4× input sizes (in other words, the accumulator input value is four times the size of the packed data element sizes of the sources), table 1103 illustrates different configurations. For byte sized sources, the accumulator uses 32-bit integer or single-precision floating-point (SPFP) values that are 32-bit in size. For word sized sources, the accumulator uses 64-bit integer or double-precision floating-point (DPFP) values that are 64-bit in size in some embodiments.
For an accumulator having 8× input sizes (in other words, the accumulator input value is eight times the size of the packed data element sizes of the sources), table 1105 illustrates a configuration. For byte sized sources, the accumulator uses 64-bit integer.
As hinted at earlier, matrix operations circuitry may be included in a core, or as an external accelerator.
A plurality of cores 1201, 1203, 1205, and 1207 provide non-tile based instruction support. In some embodiments, matrix operations circuitry is provided in a core 1203, and in other embodiments matrix operations circuitry 1211 and 1213 is accessible on the ring interconnect 1245.
Additionally, one or more memory controllers 1223-1225 are provided to communicate with memory 1233 and 1231 on behalf of the cores and/or matrix operations circuitry.
The branch prediction and decode circuitry 1303 is coupled to a rename/allocator circuitry 1307 which is coupled, in some embodiments, to scheduler circuitry 1309. In some embodiments, these circuits provide register renaming, register allocation, and/or scheduling functionality by performing one or more of: 1) renaming logical operand values to physical operand values (e.g., a register alias table in some embodiments), 2) allocating status bits and flags to the decoded instruction, and 3) scheduling the decoded instruction for execution on execution circuitry out of an instruction pool (e.g., using a reservation station in some embodiments).
The scheduler circuitry 1309 represents any number of different schedulers, including reservations stations, central instruction window, etc. The scheduler unit(s) scheduler circuitry 1309 is coupled to, or includes, physical register file(s) 1315. Each of the physical register file(s) 1315 represents one or more physical register files, different ones of which store one or more different data types, such as scalar integer, scalar floating point, packed integer, packed floating point, vector integer, vector floating point, status (e.g., an instruction pointer that is the address of the next instruction to be executed), tiles, etc. In one embodiment, the physical register file(s) 1315 comprises vector registers circuitry, write mask registers circuitry, and scalar registers circuitry. These register circuits may provide architectural vector registers, vector mask registers, and general purpose registers. The physical register file(s) 1315 is overlapped by a retirement circuit 1317 to illustrate various ways in which register renaming and out-of-order execution may be implemented (e.g., using a reorder buffer(s) and a retirement register file(s); using a future file(s), a history buffer(s), and a retirement register file(s); using a register maps and a pool of registers; etc.). The retirement circuit 1317 and the physical register file(s) 1315 are coupled to the execution circuit(s) 1311.
While register renaming is described in the context of out-of-order execution, it should be understood that register renaming may be used in an in-order architecture. While the illustrated embodiment of the processor may also include separate instruction and data cache units and a shared L2 cache unit, alternative embodiments may have a single internal cache for both instructions and data, such as, for example, a Level 1 (L1) internal cache, or multiple levels of internal cache. In some embodiments, the system may include a combination of an internal cache and an external cache that is external to the core and/or the processor. Alternatively, all of the cache may be external to the core and/or the processor.
The execution circuitry 1311 a set of one or more execution circuits 1321, 1323, and 1327 and a set of one or more memory access circuits 1325. The execution circuits 1321, 1323, and 1327 perform various operations (e.g., shifts, addition, subtraction, multiplication) and on various types of data (e.g., scalar floating point, packed integer, packed floating point, vector integer, vector floating point). While some embodiments may include a number of execution units dedicated to specific functions or sets of functions, other embodiments may include only one execution unit or multiple execution units that all perform all functions. The scalar circuitry 1321 performs scalar operations, the vector/SIMD circuitry 1323 performs vector/SIMD operations, and matrix operations circuitry 1327 performs matrix (tile) operations detailed herein.
The set of memory access units 1364 is coupled to the memory unit 1370, which includes a data TLB unit 1372 coupled to a data cache unit 1374 coupled to a level 2 (L2) cache unit 1376. In one exemplary embodiment, the memory access units 1364 may include a load unit, a store address unit, and a store data unit, each of which is coupled to the data TLB unit 1372 in the memory unit 1370. The instruction cache unit 1334 is further coupled to a level 2 (L2) cache unit 1376 in the memory unit 1370. The L2 cache unit 1376 is coupled to one or more other levels of cache and eventually to a main memory.
By way of example, the exemplary register renaming, out-of-order issue/execution core architecture may implement a pipeline as follows: 1) an instruction fetch circuit performs fetch and length decoding stages; 2) the branch and decode circuitry 1303 performs a decode stage; 3) the rename/allocator circuitry 1307 performs an allocation stage and renaming stage; 4) the scheduler circuitry 1309 performs a schedule stage; 5) physical register file(s) (coupled to, or included in, the scheduler circuitry 1307 and rename/allocate circuitry 1307 and a memory unit perform a register read/memory read stage; the execution circuitry 1311 performs an execute stage; 6) a memory unit and the physical register file(s) unit(s) perform a write back/memory write stage; 7) various units may be involved in the exception handling stage; and 8) a retirement unit and the physical register file(s) unit(s) perform a commit stage.
The core may support one or more instructions sets (e.g., the x86 instruction set (with some extensions that have been added with newer versions); the MIPS instruction set of MIPS Technologies of Sunnyvale, Calif.; the ARM instruction set (with optional additional extensions such as NEON) of ARM Holdings of Sunnyvale, Calif.), including the instruction(s) described herein. In one embodiment, the core 1390 includes logic to support a packed data instruction set extension (e.g., AVX1, AVX2), thereby allowing the operations used by many multimedia applications to be performed using packed data.
It should be understood that the core may support multithreading (executing two or more parallel sets of operations or threads), and may do so in a variety of ways including time sliced multithreading, simultaneous multithreading (where a single physical core provides a logical core for each of the threads that physical core is simultaneously multithreading), or a combination thereof (e.g., time sliced fetching and decoding and simultaneous multithreading thereafter such as in the Intel® Hyperthreading technology).
The branch prediction and decode circuitry 1403 is coupled to a rename/allocator circuitry 1407 which is coupled, in some embodiments, to scheduler circuitry 1409. In some embodiments, these circuits provide register renaming, register allocation, and/or scheduling functionality by performing one or more of: 1) renaming logical operand values to physical operand values (e.g., a register alias table in some embodiments), 2) allocating status bits and flags to the decoded instruction, and 3) scheduling the decoded instruction for execution on execution circuitry out of an instruction pool (e.g., using a reservation station in some embodiments).
The scheduler circuitry 1409 represents any number of different schedulers, including reservations stations, central instruction window, etc. The scheduler unit(s) scheduler circuitry 1409 is coupled to, or includes, physical register file(s) 1415. Each of the physical register file(s) 1415 represents one or more physical register files, different ones of which store one or more different data types, such as scalar integer, scalar floating point, packed integer, packed floating point, vector integer, vector floating point, status (e.g., an instruction pointer that is the address of the next instruction to be executed), tiles, etc. In one embodiment, the physical register file(s) 1415 comprises vector registers circuitry, write mask registers circuitry, and scalar registers circuitry. These register circuits may provide architectural vector registers, vector mask registers, and general purpose registers. The physical register file(s) 1415 is overlapped by a retirement circuit 1417 to illustrate various ways in which register renaming and out-of-order execution may be implemented (e.g., using a reorder buffer(s) and a retirement register file(s); using a future file(s), a history buffer(s), and a retirement register file(s); using a register maps and a pool of registers; etc.). The retirement circuit 1417 and the physical register file(s) 1415 are coupled to the execution circuit(s) 1411.
While register renaming is described in the context of out-of-order execution, it should be understood that register renaming may be used in an in-order architecture. While the illustrated embodiment of the processor may also include separate instruction and data cache units and a shared L2 cache unit, alternative embodiments may have a single internal cache for both instructions and data, such as, for example, a Level 1 (L1) internal cache, or multiple levels of internal cache. In some embodiments, the system may include a combination of an internal cache and an external cache that is external to the core and/or the processor. Alternatively, all of the cache may be external to the core and/or the processor.
The execution circuitry 1411 a set of one or more execution circuits 1427 and a set of one or more memory access circuits 1425. The execution circuits 1427 perform matrix (tile) operations detailed herein.
The set of memory access units 1464 is coupled to the memory unit 1470, which includes a data TLB unit 1472 coupled to a data cache unit 1474 coupled to a level 2 (L2) cache unit 1476. In one exemplary embodiment, the memory access units 1464 may include a load unit, a store address unit, and a store data unit, each of which is coupled to the data TLB unit 1472 in the memory unit 1470. The instruction cache unit 1434 is further coupled to a level 2 (L2) cache unit 1476 in the memory unit 1470. The L2 cache unit 1476 is coupled to one or more other levels of cache and eventually to a main memory.
By way of example, the exemplary register renaming, out-of-order issue/execution core architecture may implement a pipeline as follows: 1) an instruction fetch circuit performs fetch and length decoding stages; 2) the branch and decode circuitry 1403 performs a decode stage; 3) the rename/allocator circuitry 1407 performs an allocation stage and renaming stage; 4) the scheduler circuitry 1409 performs a schedule stage; 5) physical register file(s) (coupled to, or included in, the scheduler circuitry 1407 and rename/allocate circuitry 1407 and a memory unit perform a register read/memory read stage; the execution circuitry 1411 performs an execute stage; 6) a memory unit and the physical register file(s) unit(s) perform a write back/memory write stage; 7) various units may be involved in the exception handling stage; and 8) a retirement unit and the physical register file(s) unit(s) perform a commit stage.
The core may support one or more instructions sets (e.g., the x86 instruction set (with some extensions that have been added with newer versions); the MIPS instruction set of MIPS Technologies of Sunnyvale, Calif.; the ARM instruction set (with optional additional extensions such as NEON) of ARM Holdings of Sunnyvale, Calif.), including the instruction(s) described herein. In one embodiment, the core 1490 includes logic to support a packed data instruction set extension (e.g., AVX1, AVX2), thereby allowing the operations used by many multimedia applications to be performed using packed data.
It should be understood that the core may support multithreading (executing two or more parallel sets of operations or threads), and may do so in a variety of ways including time sliced multithreading, simultaneous multithreading (where a single physical core provides a logical core for each of the threads that physical core is simultaneously multithreading), or a combination thereof (e.g., time sliced fetching and decoding and simultaneous multithreading thereafter such as in the Intel® Hyperthreading technology).
B. Layout
Throughout this description, data is expressed using row major data layout.
Column major users should translate the terms according to their orientation.
In some embodiments, row-major semantics are utilized in hardware, and column major data is to swap the operand order with the result being transposes of matrix, but for subsequent column-major reads from memory it is the correct, non-transposed matrix.
For example, if there are two column-major matrices to multiply:
The input matrices would be stored in linear memory (column-major) as:
acebdf
and
ghijkl.
Reading those matrices as row-major with dimensions 2×3 and 3×2, they would appear as:
Swapping the order and matrix multiplying:
the transpose matrix is out and can then be stored in row-major order:
ag+bh cg+dh eg+fh ai+bj ci+dj ei+fj ak+bl ck+dl ek+fl
and used in subsequent column major computations, it is the correct un-transposed matrix:
III. Exemplary Usage
The exemplary code as shown includes the usage of a tile configuration instruction and is executed to configure tile usage, load tiles, a loop to process the tiles, store tiles to memory, and release tile usage.
IV. Exemplary Instructions
A. Tile Configuration
As discussed above, tile usage typically needs to be configured prior to use. For example, full usage of all rows and columns may not be needed. Not only does not configuring these rows and columns save power in some embodiments, but the configuration may be used to determine if an operation will generate an error. For example, a matrix multiplication of the form (N×M)*(L*N) will typically not work if M and L are not the same.
Detailed herein are embodiments of a matrix (tile) configuration (“TILECONFIG”) instruction and its execution. Prior to using matrices using tiles, in some embodiments, tile support is to be configured. For example, how many rows and columns per tile, tiles that are to be used, etc. are configured. A TILECONFIG instruction is an improvement to a computer itself as it provides for support to configure the computer to use a matrix accelerator (either as a part of a processor core, or as an external device). In particular, an execution of the TILECONFIG instruction causes a configuration to be retrieved from memory and applied to matrix (tile) settings within a matrix accelerator.
As illustrated, the TILECONFIG instruction uses the address as a pointer to a memory 1801 location containing the description of the matrices (tiles) to be supported 1803.
Execution circuitry 1811 of a processor/core 1805 performs the TILECONFIG by retrieving the description 1803 from memory 1801 via a memory controller 1815, configuring tiles for a palette (setting the number of rows and columns) in a tile configuration 1817, and marking that matrix support is in use. In particular, instruction execution resources 1811 are configured to use tiles as specified by setting tile configurations 1817. The instruction execution resources may also include a machine specific register or configuration register to indicate tile usage.
Tile configurations 1817 are set to indicate parameters per tile as indicated by the tile description 1803 via the execution of the TILECONFIG instruction. The set parameters are the number of rows and columns per tile. Additional values such as in-use and start values are also set. The tile configurations 1817 utilize one or more registers 1819 to store tile usage and configuration information.
Other combinations are contemplated such as combining the start registers into a single register where they are shown separately, etc.
Bytes 8-9 store a value for a “startM” register 2003 and bytes 10-11 store a value for a “startK” register 2005. To support restarting instructions after these events, the instructions store information these registers. The startM indicates a row that should be used for restart. The startK indicates a position in the inner-product for relevant operations. The position in the row (the column) is not needed. Two-dimensional operations like the element-wise addition/subtraction/multiplication only use startM. Three-dimensional operations use values from both startM and startK. Typically, operations that only require startM will zero startK when writing startM.
Any time an interrupted tile instruction is not restarted, in some embodiments, it is the responsibility of software to zero the startM and startK values. For example, unmasked floating point exception handlers might decide to finish the operation in software and change the program counter value to another instruction, usually the next instruction. In this case the software exception handler must zero the startM and startK values in the exception frame presented to it by the operating system before resuming the program. The operating system will subsequently reload those values.
Bytes 16-17 store the number of rows 2013 and columns 2015 for tile 0, bytes 18-19 store the number of rows and columns for tile 1, etc. In other words, each 2 byte group specifies a number of rows and columns for a tile. If a group of 2 bytes is not used to specify tile parameters, they should have the value zero. Specifying tile parameters for more tiles than the implementation limit or the palette limit results in a fault. Unconfigured tiles are set to the INIT state with 0 rows, 0 columns.
Finally, the configuration in memory typically ends with an ending delineation such as all zeros for several consecutive bytes.
An embodiment of a format for a TILECONFIG instruction is TILECONFIG Address. In some embodiments, TILECONFIG is the opcode mnemonic of the instruction. Address is a pointer to a matrix (tile) description in memory. In some embodiments, the address field is a R/M value (such as 2446).
In embodiments, encodings of the instruction include a scale-index-base (SIB) type memory addressing operand that indirectly identifies multiple indexed destination locations in memory (e.g., field 2450). In one embodiment, an SIB type memory operand may include an encoding identifying a base address register. The contents of the base address register may represent a base address in memory from which the addresses of the particular destination locations in memory are calculated. For example, the base address may be the address of the first location in a block of potential destination locations for an extended vector instruction. In one embodiment, an SIB type memory operand may include an encoding identifying an index register. Each element of the index register may specify an index or offset value usable to compute, from the base address, an address of a respective destination location within a block of potential destination locations. In one embodiment, an SIB type memory operand may include an encoding specifying a scaling factor to be applied to each index value when computing a respective destination address. For example, if a scaling factor value of four is encoded in the SIB type memory operand, each index value obtained from an element of the index register may be multiplied by four and then added to the base address to compute a destination address.
In one embodiment, an SIB type memory operand of the form vm32{x,y,z} may identify a vector array of memory operands specified using SIB type memory addressing. In this example, the array of memory addresses is specified using a common base register, a constant scaling factor, and a vector index register containing individual elements, each of which is a 32-bit index value. The vector index register may be a 128-bit register (e.g., XMM) register (vm32x), a 256-bit (e.g., YMM) register (vm32y), or a 512-bit (e.g., ZMM) register (vm32z). In another embodiment, an SIB type memory operand of the form vm64{x,y,z} may identify a vector array of memory operands specified using SIB type memory addressing. In this example, the array of memory addresses is specified using a common base register, a constant scaling factor, and a vector index register containing individual elements, each of which is a 64-bit index value. The vector index register may be a 128-bit register (e.g., XMM) register (vm64x), a 256-bit (e.g., YMM) register (vm64y) or a 512-bit (e.g., ZMM) register (vm64z).
At 2101, an instruction is fetched. For example, a TILECONFIG instruction is fetched. An embodiment of the TILECONFIG instruction includes fields for an opcode and a memory address operand.
The fetched instruction is decoded at 2103. For example, the fetched TILECONFIG instruction is decoded by decode circuitry such as that detailed herein.
A description found at the memory address of the memory address operand is are retrieved at 2105 and the decoded instruction is scheduled (as needed).
At 2107, the decoded instruction is executed by execution circuitry (hardware) such as that detailed herein. For the TILECONFIG instruction, the execution will cause execution circuitry to configure usage of tiles in a tile configuration (setting the number of rows and columns) and marking that matrix (tile) support is in use (active). For example, configuration one or more registers 1819. Tile support usage (e.g., “TILES_CONFIGURED”) is typically indicated by setting a bit in a status, control, or machine specific register. In particular, instruction execution resources 1811 are configured to use tiles as specified by the retrieved configuration.
In some embodiments, the instruction is committed or retired at 2109.
At 2201, a determination of if the palette ID is supported is made. For example, does the CPUID state that this ID is supported? If not, then a general protection fault occurs at 2203.
At 2205, a first tile specific grouping is read. For example, the number of rows and columns for tile 0 (T0) is read.
A determination of if the read grouping is valid is made at 2207. For example, if one the number of rows or columns (not both) is set 0, then the grouping is not valid and the configuration halts and tiles are not considered to be in use at 2203. Invalid groups occur, for example, when one of rows or columns (not both) are zero. Additionally, when a value for the number of rows is greater than the maximum of rows supported (this is found by dividing the tile byte size of the palette ID with the number of bytes per row for the palette ID as found in the palette table) as fault occurs. Another potential fault is when there are more names than supported.
If the read grouping is valid, then the tile associated with the read grouping is configured to use the number of rows and columns specified by the grouping in a tile configuration at 2211. The size of the elements in the tile are set by the palette table entry for the palette ID.
A determination of if all tiles of the retrieved configuration have been configured is made at 2213. For example, have all of the possible tile names been processed? In some embodiments, when the rows and columns for a particular tile are both 0, then all tiles have been processed.
When all tiles have not been configured, at 2215, the tile number is incremented such that the next tile in the configuration will be evaluated.
At 2217, the incremented tile's grouping is read. For example, the number of rows and columns for tile 1 (T1) is read. A determination of if the read grouping is valid is made at 2207, etc.
When all tiles have been configured, then the instruction completes at 2209. The tiles will be marked as being in use for matrix operations, for example, by setting an in-use indicator in a register.
A processor comprising decode circuitry to decode an instruction having fields for an opcode and a memory address; and execution circuitry to execute the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers.
The processor of example 1, wherein the configuration comprises a palette identifier and details regarding a number of rows and columns per tile of the palette.
The processor of example 1, wherein the palette identifier is an index into a palette table defining a number of bytes per tile and bytes per row of the tile.
The processor of any of examples 1-4, wherein the configuration is stored in a single packed data register.
The processor of any of examples 1-4, wherein the configuration is stored in a plurality of packed data registers, one packed data register per configured tile.
The processor of any of examples 1-5, wherein the execution circuitry to general a fault upon a value of a number of rows for a tile being zero and a number of columns for the row being non-zero.
The processor of any of examples 1-6, wherein the description is 64 bytes in size.
A method comprising: decoding an instruction having fields for an opcode and a memory address; and executing the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers.
The method of example 8, wherein the configuration comprises a palette identifier and details regarding a number of rows and columns per tile of the palette.
The method of example 8, wherein the palette identifier is an index into a palette table defining a number of bytes per tile and bytes per row of the tile.
The method of any of examples 8-10, wherein the configuration is stored in a single packed data register.
The method of any of examples 8-10, wherein the configuration is stored in a plurality of packed data registers, one packed data register per configured tile.
The method of any of examples 8-12, further comprising:
faulting upon a value of a number of rows for a tile being zero and a number of columns for the row being non-zero.
The method of any of examples 8-13, wherein the description is 64 bytes in size.
A non-transitory machine-readable medium storing an instruction which causes a processor to perform a method, the method comprising: decoding an instruction having fields for an opcode and a memory address; and executing the decoded instruction to set a tile configuration for the processor to utilize tiles in matrix operations based on a description retrieved from the memory address, wherein a tile a set of 2-dimensional registers.
The non-transitory machine-readable medium of example 15, wherein the configuration comprises a palette identifier and details regarding a number of rows and columns per tile of the palette.
The non-transitory machine-readable medium of example 15, wherein the palette identifier is an index into a palette table defining a number of bytes per tile and bytes per row of the tile.
The non-transitory machine-readable medium of any of examples 15-17, wherein the configuration is stored in a single packed data register.
The non-transitory machine-readable medium of any of examples 15-17, wherein the configuration is stored in a plurality of packed data registers, one packed data register per configured tile.
The non-transitory machine-readable medium of any of examples 15-19, further comprising: faulting upon a value of a number of rows for a tile being zero and a number of columns for the row being non-zero.
The non-transitory machine-readable medium of any of examples 15-20, wherein the description is 64 bytes in size.
V. Detailed Exemplary Systems, Processors, and Emulation
Detailed herein are examples of hardware, software, etc. to execute the above described instructions. For example, what is described below details aspects of instruction execution including various pipeline stages such as fetch, decode, schedule, execute, retire, etc.
An instruction set includes one or more instruction formats. A given instruction format defines various fields (number of bits, location of bits) to specify, among other things, the operation to be performed (opcode) and the operand(s) on which that operation is to be performed. Some instruction formats are further broken down though the definition of instruction templates (or subformats). For example, the instruction templates of a given instruction format may be defined to have different subsets of the instruction format's fields (the included fields are typically in the same order, but at least some have different bit positions because there are less fields included) and/or defined to have a given field interpreted differently. Thus, each instruction of an ISA is expressed using a given instruction format (and, if defined, in a given one of the instruction templates of that instruction format) and includes fields for specifying the operation and the operands. For example, an exemplary ADD instruction has a specific opcode and an instruction format that includes an opcode field to specify that opcode and operand fields to select operands (source1/destination and source2); and an occurrence of this ADD instruction in an instruction stream will have specific contents in the operand fields that select specific operands.
A. Exemplary Instruction Formats
Embodiments of the instruction(s) described herein may be embodied in different formats. Additionally, exemplary systems, architectures, and pipelines are detailed below. Embodiments of the instruction(s) may be executed on such systems, architectures, and pipelines, but are not limited to those detailed.
VEX Instruction Format
VEX encoding allows instructions to have more than two operands, and allows SIMD vector registers to be longer than 128 bits. The use of a VEX prefix provides for three-operand (or more) syntax. For example, previous two-operand instructions performed operations such as A=A+B, which overwrites a source operand. The use of a VEX prefix enables operands to perform nondestructive operations such as A=B+C.
VEX Prefix (Bytes 0-2) 2402 is encoded in a three-byte form. The first byte is the Format Field 2490 (VEX Byte 0, bits [7:0]), which contains an explicit C4 byte value (the unique value used for distinguishing the C4 instruction format). The second-third bytes (VEX Bytes 1-2) include a number of bit fields providing specific capability. Specifically, REX field 2405 (VEX Byte 1, bits [7-5]) consists of a VEX.R bit field (VEX Byte 1, bit [7]-R), VEX.X bit field (VEX byte 1, bit [6]-X), and VEX.B bit field (VEX byte 1, bit[5]-B). Other fields of the instructions encode the lower three bits of the register indexes as is known in the art (rrr, xxx, and bbb), so that Rrrr, Xxxx, and Bbbb may be formed by adding VEX.R, VEX.X, and VEX.B. Opcode map field 2415 (VEX byte 1, bits [4:0]-mmmmm) includes content to encode an implied leading opcode byte. W Field 2464 (VEX byte 2, bit [7]-W)—is represented by the notation VEX.W, and provides different functions depending on the instruction. The role of VEX.vvvv 2420 (VEX Byte 2, bits [6:3]-vvvv) may include the following: 1) VEX.vvvv encodes the first source register operand, specified in inverted (1s complement) form and is valid for instructions with 2 or more source operands; 2) VEX.vvvv encodes the destination register operand, specified in 1s complement form for certain vector shifts; or 3) VEX.vvvv does not encode any operand, the field is reserved and should contain 1111b. If VEX.L 2468 Size field (VEX byte 2, bit [2]-L)=0, it indicates 128 bit vector; if VEX.L=1, it indicates 256 bit vector. Prefix encoding field 2425 (VEX byte 2, bits [1:0]-pp) provides additional bits for the base operation field 2441.
Real Opcode Field 2430 (Byte 3) is also known as the opcode byte. Part of the opcode is specified in this field.
MOD R/M Field 2440 (Byte 4) includes MOD field 2442 (bits [7-6]), Reg field 2444 (bits [5-3]), and R/M field 2446 (bits [2-0]). The role of Reg field 2444 may include the following: encoding either the destination register operand or a source register operand (the rrr of Rrrr), or be treated as an opcode extension and not used to encode any instruction operand. The role of R/M field 2446 may include the following: encoding the instruction operand that references a memory address, or encoding either the destination register operand or a source register operand.
Scale, Index, Base (SIB)—The content of Scale field 2450 (Byte 5) includes SS2452 (bits [7-6]), which is used for memory address generation. The contents of SIB.xxx 2454 (bits [5-3]) and SIB.bbb 2456 (bits [2-0]) have been previously referred to with regard to the register indexes Xxxx and Bbbb.
The Displacement Field 2462 and the immediate field (IMM8) 2472 contain data.
B. Exemplary Register Architecture
General-purpose registers 2525—in the embodiment illustrated, there are sixteen 64-bit general-purpose registers that are used along with the existing x86 addressing modes to address memory operands. These registers are referenced by the names RAX, RBX, RCX, RDX, RBP, RSI, RDI, RSP, and R8 through R15.
Scalar floating point stack register file (x87 stack) 2545, on which is aliased the MMX packed integer flat register file 2550—in the embodiment illustrated, the x87 stack is an eight-element stack used to perform scalar floating-point operations on 32/64/80-bit floating point data using the x87 instruction set extension; while the MMX registers are used to perform operations on 64-bit packed integer data, as well as to hold operands for some operations performed between the MMX and XMM registers.
In some embodiments, tiles 2520 are supported using an overlay over physical registers. For example, a tile may utilize 16 1,024-bit registers, 32 512-bit registers, etc. depending on the implementation.
Alternative embodiments of the invention may use wider or narrower registers. Additionally, alternative embodiments of the invention may use more, less, or different register files and registers.
Exemplary Core Architectures, Processors, and Computer Architectures
Processor cores may be implemented in different ways, for different purposes, and in different processors. For instance, implementations of such cores may include: 1) a general purpose in-order core intended for general-purpose computing; 2) a high performance general purpose out-of-order core intended for general-purpose computing; 3) a special purpose core intended primarily for graphics and/or scientific (throughput) computing. Implementations of different processors may include: 1) a CPU including one or more general purpose in-order cores intended for general-purpose computing and/or one or more general purpose out-of-order cores intended for general-purpose computing; and 2) a coprocessor including one or more special purpose cores intended primarily for graphics and/or scientific (throughput). Such different processors lead to different computer system architectures, which may include: 1) the coprocessor on a separate chip from the CPU; 2) the coprocessor on a separate die in the same package as a CPU; 3) the coprocessor on the same die as a CPU (in which case, such a coprocessor is sometimes referred to as special purpose logic, such as integrated graphics and/or scientific (throughput) logic, or as special purpose cores); and 4) a system on a chip that may include on the same die the described CPU (sometimes referred to as the application core(s) or application processor(s)), the above described coprocessor, and additional functionality. Exemplary core architectures are described next, followed by descriptions of exemplary processors and computer architectures. Detailed herein are circuits (units) that comprise exemplary cores, processors, etc.
C. Exemplary Core Architectures
In-Order and Out-of-Order Core Block Diagram
In
The front end unit 2630 includes a branch prediction unit 2632 coupled to an instruction cache unit 2634, which is coupled to an instruction translation lookaside buffer (TLB) 2636, which is coupled to an instruction fetch unit 2638, which is coupled to a decode unit 2640. The decode unit 2640 (or decoder) may decode instructions, and generate as an output one or more micro-operations, micro-code entry points, microinstructions, other instructions, or other control signals, which are decoded from, or which otherwise reflect, or are derived from, the original instructions. The decode unit 2640 may be implemented using various different mechanisms. Examples of suitable mechanisms include, but are not limited to, look-up tables, hardware implementations, programmable logic arrays (PLAs), microcode read only memories (ROMs), etc. In one embodiment, the core 2690 includes a microcode ROM or other medium that stores microcode for certain macroinstructions (e.g., in decode unit 2640 or otherwise within the front end unit 2630). The decode unit 2640 is coupled to a rename/allocator unit 2652 in the execution engine unit 2650.
The execution engine unit 2650 includes the rename/allocator unit 2652 coupled to a retirement unit 2654 and a set of one or more scheduler unit(s) 2656. The scheduler unit(s) 2656 represents any number of different schedulers, including reservations stations, central instruction window, etc. The scheduler unit(s) 2656 is coupled to the physical register file(s) unit(s) 2658. Each of the physical register file(s) units 2658 represents one or more physical register files, different ones of which store one or more different data types, such as scalar integer, scalar floating point, packed integer, packed floating point, vector integer, vector floating point, status (e.g., an instruction pointer that is the address of the next instruction to be executed), etc. In one embodiment, the physical register file(s) unit 2658 comprises a vector registers unit and a scalar registers unit. These register units may provide architectural vector registers, vector mask registers, and general purpose registers. The physical register file(s) unit(s) 2658 is overlapped by the retirement unit 2654 to illustrate various ways in which register renaming and out-of-order execution may be implemented (e.g., using a reorder buffer(s) and a retirement register file(s); using a future file(s), a history buffer(s), and a retirement register file(s); using a register maps and a pool of registers; etc.). The retirement unit 2654 and the physical register file(s) unit(s) 2658 are coupled to the execution cluster(s) 2660. The execution cluster(s) 2660 includes a set of one or more execution units 2662 and a set of one or more memory access units 2664. The execution units 2662 may perform various operations (e.g., shifts, addition, subtraction, multiplication) and on various types of data (e.g., scalar floating point, packed integer, packed floating point, vector integer, vector floating point). While some embodiments may include a number of execution units dedicated to specific functions or sets of functions, other embodiments may include only one execution unit or multiple execution units that all perform all functions. The scheduler unit(s) 2656, physical register file(s) unit(s) 2658, and execution cluster(s) 2660 are shown as being possibly plural because certain embodiments create separate pipelines for certain types of data/operations (e.g., a scalar integer pipeline, a scalar floating point/packed integer/packed floating point/vector integer/vector floating point pipeline, and/or a memory access pipeline that each have their own scheduler unit, physical register file(s) unit, and/or execution cluster—and in the case of a separate memory access pipeline, certain embodiments are implemented in which only the execution cluster of this pipeline has the memory access unit(s) 2664). It should also be understood that where separate pipelines are used, one or more of these pipelines may be out-of-order issue/execution and the rest in-order.
The set of memory access units 2664 is coupled to the memory unit 2670, which includes a data TLB unit 2672 coupled to a data cache unit 2674 coupled to a level 2 (L2) cache unit 2676. In one exemplary embodiment, the memory access units 2664 may include a load unit, a store address unit, and a store data unit, each of which is coupled to the data TLB unit 2672 in the memory unit 2670. The instruction cache unit 2634 is further coupled to a level 2 (L2) cache unit 2676 in the memory unit 2670. The L2 cache unit 2676 is coupled to one or more other levels of cache and eventually to a main memory.
By way of example, the exemplary register renaming, out-of-order issue/execution core architecture may implement the pipeline 2600 as follows: 1) the instruction fetch 2638 performs the fetch and length decoding stages 2602 and 2604; 2) the decode unit 2640 performs the decode stage 2606; 3) the rename/allocator unit 2652 performs the allocation stage 2608 and renaming stage 2610; 4) the scheduler unit(s) 2656 performs the schedule stage 2612; 5) the physical register file(s) unit(s) 2658 and the memory unit 2670 perform the register read/memory read stage 2614; the execution cluster 2660 perform the execute stage 2616; 6) the memory unit 2670 and the physical register file(s) unit(s) 2658 perform the write back/memory write stage 2618; 7) various units may be involved in the exception handling stage 2622; and 8) the retirement unit 2654 and the physical register file(s) unit(s) 2658 perform the commit stage 2624.
The core 2690 may support one or more instructions sets (e.g., the x86 instruction set (with some extensions that have been added with newer versions); the MIPS instruction set of MIPS Technologies of Sunnyvale, Calif.; the ARM instruction set (with optional additional extensions such as NEON) of ARM Holdings of Sunnyvale, Calif.), including the instruction(s) described herein. In one embodiment, the core 2690 includes logic to support a packed data instruction set extension (e.g., AVX1, AVX2), thereby allowing the operations used by many multimedia applications to be performed using packed data.
It should be understood that the core may support multithreading (executing two or more parallel sets of operations or threads), and may do so in a variety of ways including time sliced multithreading, simultaneous multithreading (where a single physical core provides a logical core for each of the threads that physical core is simultaneously multithreading), or a combination thereof (e.g., time sliced fetching and decoding and simultaneous multithreading thereafter such as in the Intel® Hyperthreading technology).
While register renaming is described in the context of out-of-order execution, it should be understood that register renaming may be used in an in-order architecture. While the illustrated embodiment of the processor also includes separate instruction and data cache units 2634/2674 and a shared L2 cache unit 2676, alternative embodiments may have a single internal cache for both instructions and data, such as, for example, a Level 1 (L1) internal cache, or multiple levels of internal cache. In some embodiments, the system may include a combination of an internal cache and an external cache that is external to the core and/or the processor. Alternatively, all of the cache may be external to the core and/or the processor.
Specific Exemplary in-Order Core Architecture
The local subset of the L2 cache 2704 is part of a global L2 cache that is divided into separate local subsets, one per processor core. Each processor core has a direct access path to its own local subset of the L2 cache 2704. Data read by a processor core is stored in its L2 cache subset 2704 and can be accessed quickly, in parallel with other processor cores accessing their own local L2 cache subsets. Data written by a processor core is stored in its own L2 cache subset 2704 and is flushed from other subsets, if necessary. The ring network ensures coherency for shared data. The ring network is bi-directional to allow agents such as processor cores, L2 caches and other logic blocks to communicate with each other within the chip. Each ring data-path is 1024-bits wide per direction in some embodiments.
Processor with Integrated Memory Controller and Graphics
Thus, different implementations of the processor 2800 may include: 1) a CPU with the special purpose logic 2808 being integrated graphics and/or scientific (throughput) logic (which may include one or more cores), and the cores 2802A-N being one or more general purpose cores (e.g., general purpose in-order cores, general purpose out-of-order cores, a combination of the two); 2) a coprocessor with the cores 2802A-N being a large number of special purpose cores intended primarily for graphics and/or scientific (throughput); and 3) a coprocessor with the cores 2802A-N being a large number of general purpose in-order cores. Thus, the processor 2800 may be a general-purpose processor, coprocessor or special-purpose processor, such as, for example, a network or communication processor, compression engine, graphics processor, GPGPU (general purpose graphics processing unit), a high-throughput many integrated core (MIC) coprocessor (including 30 or more cores), embedded processor, or the like. The processor may be implemented on one or more chips. The processor 2800 may be a part of and/or may be implemented on one or more substrates using any of a number of process technologies, such as, for example, BiCMOS, CMOS, or NMOS.
The memory hierarchy includes one or more levels of cache within the cores 2804A-N, a set or one or more shared cache units 2806, and external memory (not shown) coupled to the set of integrated memory controller units 2814. The set of shared cache units 2806 may include one or more mid-level caches, such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, a last level cache (LLC), and/or combinations thereof. While in one embodiment a ring based interconnect unit 2812 interconnects the integrated graphics logic 2808, the set of shared cache units 2806, and the system agent unit 2810/integrated memory controller unit(s) 2814, alternative embodiments may use any number of well-known techniques for interconnecting such units. In one embodiment, coherency is maintained between one or more cache units 2806 and cores 2802-A-N.
In some embodiments, one or more of the cores 2802A-N are capable of multithreading. The system agent 2810 includes those components coordinating and operating cores 2802A-N. The system agent unit 2810 may include for example a power control unit (PCU) and a display unit. The PCU may be or include logic and components needed for regulating the power state of the cores 2802A-N and the integrated graphics logic 2808. The display unit is for driving one or more externally connected displays.
The cores 2802A-N may be homogenous or heterogeneous in terms of architecture instruction set; that is, two or more of the cores 2802A-N may be capable of execution the same instruction set, while others may be capable of executing only a subset of that instruction set or a different instruction set.
D. Exemplary Computer Architectures
Referring now to
The optional nature of additional processors 2915 is denoted in
The memory 2940 may be, for example, dynamic random access memory (DRAM), phase change memory (PCM), or a combination of the two. For at least one embodiment, the controller hub 2920 communicates with the processor(s) 2910, 2915 via a multi-drop bus, such as a frontside bus (FSB), point-to-point interface, or similar connection 2995.
In one embodiment, the coprocessor 2945 is a special-purpose processor, such as, for example, a high-throughput MIC processor, a network or communication processor, compression engine, graphics processor, GPGPU, embedded processor, or the like. In one embodiment, controller hub 2920 may include an integrated graphics accelerator.
There can be a variety of differences between the physical resources 2910, 29155 in terms of a spectrum of metrics of merit including architectural, microarchitectural, thermal, power consumption characteristics, and the like.
In one embodiment, the processor 2910 executes instructions that control data processing operations of a general type. Embedded within the instructions may be coprocessor instructions. The processor 2910 recognizes these coprocessor instructions as being of a type that should be executed by the attached coprocessor 2945. Accordingly, the processor 2910 issues these coprocessor instructions (or control signals representing coprocessor instructions) on a coprocessor bus or other interconnect, to coprocessor 2945. Coprocessor(s) 2945 accept and execute the received coprocessor instructions.
Referring now to
Processors 3070 and 3080 are shown including integrated memory controller (IMC) units 3072 and 3082, respectively. Processor 3070 also includes as part of its bus controller units point-to-point (P-P) interfaces 3076 and 3078; similarly, second processor 3080 includes P-P interfaces 3086 and 3088. Processors 3070, 3080 may exchange information via a point-to-point (P-P) interface 3050 using P-P interface circuits 3078, 3088. As shown in
Processors 3070, 3080 may each exchange information with a chipset 3090 via individual P-P interfaces 3052, 3054 using point to point interface circuits 3076, 3094, 3086, 3098. Chipset 3090 may optionally exchange information with the coprocessor 3038 via a high-performance interface 3092. In one embodiment, the coprocessor 3038 is a special-purpose processor, such as, for example, a high-throughput MIC processor, a network or communication processor, compression engine, graphics processor, GPGPU, embedded processor, or the like.
A shared cache (not shown) may be included in either processor or outside of both processors, yet connected with the processors via P-P interconnect, such that either or both processors' local cache information may be stored in the shared cache if a processor is placed into a low power mode.
Chipset 3090 may be coupled to a first bus 3016 via an interface 3096. In one embodiment, first bus 3016 may be a Peripheral Component Interconnect (PCI) bus, or a bus such as a PCI Express bus or another I/O interconnect bus, although the scope of the present invention is not so limited.
As shown in
Referring now to
Referring now to
Embodiments of the mechanisms disclosed herein may be implemented in hardware, software, firmware, or a combination of such implementation approaches. Embodiments of the invention may be implemented as computer programs or program code executing on programmable systems comprising at least one processor, a storage system (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device.
Program code, such as code 3030 illustrated in
The program code may be implemented in a high level procedural or object oriented programming language to communicate with a processing system. The program code may also be implemented in assembly or machine language, if desired. In fact, the mechanisms described herein are not limited in scope to any particular programming language. In any case, the language may be a compiled or interpreted language.
One or more aspects of at least one embodiment may be implemented by representative instructions stored on a machine-readable medium which represents various logic within the processor, which when read by a machine causes the machine to fabricate logic to perform the techniques described herein. Such representations, known as “IP cores” may be stored on a tangible, machine readable medium and supplied to various customers or manufacturing facilities to load into the fabrication machines that actually make the logic or processor.
Such machine-readable storage media may include, without limitation, non-transitory, tangible arrangements of articles manufactured or formed by a machine or device, including storage media such as hard disks, any other type of disk including floppy disks, optical disks, compact disk read-only memories (CD-ROMs), compact disk rewritable's (CD-RWs), and magneto-optical disks, semiconductor devices such as read-only memories (ROMs), random access memories (RAMs) such as dynamic random access memories (DRAMs), static random access memories (SRAMs), erasable programmable read-only memories (EPROMs), flash memories, electrically erasable programmable read-only memories (EEPROMs), phase change memory (PCM), magnetic or optical cards, or any other type of media suitable for storing electronic instructions.
Accordingly, embodiments of the invention also include non-transitory, tangible machine-readable media containing instructions or containing design data, such as Hardware Description Language (HDL), which defines structures, circuits, apparatuses, processors and/or system features described herein. Such embodiments may also be referred to as program products.
E. Emulation (Including Binary Translation, Code Morphing, Etc.)
In some cases, an instruction converter may be used to convert an instruction from a source instruction set to a target instruction set. For example, the instruction converter may translate (e.g., using static binary translation, dynamic binary translation including dynamic compilation), morph, emulate, or otherwise convert an instruction to one or more other instructions to be processed by the core. The instruction converter may be implemented in software, hardware, firmware, or a combination thereof. The instruction converter may be on processor, off processor, or part on and part off processor.
This application is a national stage of International Application No. PCT/US2017/040541, filed Jul. 1, 2017, which claims priority to U.S. Provisional Application No. 62/473,732, filed Mar. 20, 2017.
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/US2017/040541 | 7/1/2017 | WO | 00 |
| Publishing Document | Publishing Date | Country | Kind |
|---|---|---|---|
| WO2018/174931 | 9/27/2018 | WO | A |
| Number | Name | Date | Kind |
|---|---|---|---|
| 4310879 | Pandeya | Jan 1982 | A |
| 5025407 | Gulley et al. | Jun 1991 | A |
| 5170370 | Lee et al. | Dec 1992 | A |
| 5247632 | Newman | Sep 1993 | A |
| 5426378 | Ong | Jun 1995 | A |
| 5475822 | Sibigtroth et al. | Dec 1995 | A |
| 5584027 | Smith | Dec 1996 | A |
| 5682544 | Pechanek et al. | Oct 1997 | A |
| 5761466 | Chau | Jun 1998 | A |
| 5765216 | Weng et al. | Jun 1998 | A |
| 5887183 | Agarwal et al. | Mar 1999 | A |
| 5892962 | Cloutier | Apr 1999 | A |
| 6041403 | Parker et al. | Mar 2000 | A |
| 6069489 | Iwanczuk | May 2000 | A |
| 6134578 | Ehlig et al. | Oct 2000 | A |
| 6161219 | Ramkumar et al. | Dec 2000 | A |
| 6212112 | Naura et al. | Apr 2001 | B1 |
| 6332186 | Elwood et al. | Dec 2001 | B1 |
| 6487171 | Honig et al. | Nov 2002 | B1 |
| 6487524 | Preuss | Nov 2002 | B1 |
| 6643765 | Hansen et al. | Nov 2003 | B1 |
| 6647484 | Jiang et al. | Nov 2003 | B1 |
| 6831654 | Pether et al. | Dec 2004 | B2 |
| 6877020 | Bratt et al. | Apr 2005 | B1 |
| 6944747 | Nair et al. | Sep 2005 | B2 |
| 7003542 | Devir | Feb 2006 | B2 |
| 7016418 | Wang | Mar 2006 | B2 |
| 7107436 | Moyer | Sep 2006 | B2 |
| 7209939 | Castrapel et al. | Apr 2007 | B2 |
| 7275148 | Moyer et al. | Sep 2007 | B2 |
| 7430578 | Debes et al. | Sep 2008 | B2 |
| 7610466 | Moyer | Oct 2009 | B2 |
| 7672389 | Gueguen | Mar 2010 | B2 |
| 7725521 | Chen et al. | May 2010 | B2 |
| 7792895 | Juffa et al. | Sep 2010 | B1 |
| 7873812 | Mimar | Jan 2011 | B1 |
| 7912889 | Juffa et al. | Mar 2011 | B1 |
| 7932910 | Hansen et al. | Apr 2011 | B2 |
| 8040349 | Danskin | Oct 2011 | B1 |
| 8051124 | Salama et al. | Nov 2011 | B2 |
| 8374284 | Watson | Feb 2013 | B2 |
| 8392487 | Mesh et al. | Mar 2013 | B1 |
| 8577950 | Eichenberger et al. | Nov 2013 | B2 |
| 8760994 | Wang et al. | Jun 2014 | B2 |
| 8817033 | Hur | Aug 2014 | B2 |
| 8825988 | Rupley et al. | Sep 2014 | B2 |
| 8943119 | Hansen et al. | Jan 2015 | B2 |
| 8984043 | Ginzburg et al. | Mar 2015 | B2 |
| 9098460 | Yanagisawa | Aug 2015 | B2 |
| 9442723 | Yang et al. | Sep 2016 | B2 |
| 9557998 | Ould-Ahmed-Vall et al. | Jan 2017 | B2 |
| 9703708 | Alameldeen et al. | Jul 2017 | B2 |
| 9906359 | Gueron | Feb 2018 | B2 |
| 9960907 | Gueron | May 2018 | B2 |
| 10275243 | Grochowski et al. | Apr 2019 | B2 |
| 10535114 | Bolz | Jan 2020 | B2 |
| 10620951 | Azizi et al. | Apr 2020 | B2 |
| 10649772 | Bradford et al. | May 2020 | B2 |
| 10719323 | Baum et al. | Jul 2020 | B2 |
| 20020032710 | Saulsbury et al. | Mar 2002 | A1 |
| 20030038547 | Reinhardt et al. | Feb 2003 | A1 |
| 20030126176 | Devir | Jul 2003 | A1 |
| 20030221089 | Spracklen | Nov 2003 | A1 |
| 20040097856 | Cipra et al. | May 2004 | A1 |
| 20040111587 | Nair et al. | Jun 2004 | A1 |
| 20040228295 | Zhang et al. | Nov 2004 | A1 |
| 20050053012 | Moyer | Mar 2005 | A1 |
| 20050055534 | Moyer | Mar 2005 | A1 |
| 20050055535 | Moyer et al. | Mar 2005 | A1 |
| 20050055543 | Moyer | Mar 2005 | A1 |
| 20050094893 | Samadani | May 2005 | A1 |
| 20050193050 | Sazegari | Sep 2005 | A1 |
| 20060095721 | Biles | May 2006 | A1 |
| 20060101245 | Nair et al. | May 2006 | A1 |
| 20060190517 | Guerrero | Aug 2006 | A1 |
| 20070006231 | Wang et al. | Jan 2007 | A1 |
| 20070126474 | Chang et al. | Jun 2007 | A1 |
| 20070186210 | Hussain et al. | Aug 2007 | A1 |
| 20070271325 | Juffa et al. | Nov 2007 | A1 |
| 20070280261 | Szymanski | Dec 2007 | A1 |
| 20080031545 | Nowicki et al. | Feb 2008 | A1 |
| 20080071851 | Zohar et al. | Mar 2008 | A1 |
| 20080140994 | Khailany et al. | Jun 2008 | A1 |
| 20080162824 | Jalowiecki et al. | Jul 2008 | A1 |
| 20080208942 | Won et al. | Aug 2008 | A1 |
| 20080301414 | Pitsianis et al. | Dec 2008 | A1 |
| 20090006816 | Hoyle et al. | Jan 2009 | A1 |
| 20090043836 | Dupaquis et al. | Feb 2009 | A1 |
| 20090172365 | Orenstien et al. | Jul 2009 | A1 |
| 20090196103 | Kim | Aug 2009 | A1 |
| 20090292758 | Brokenshire et al. | Nov 2009 | A1 |
| 20090300091 | Brokenshire et al. | Dec 2009 | A1 |
| 20090300249 | Moyer et al. | Dec 2009 | A1 |
| 20100106692 | Moloney | Apr 2010 | A1 |
| 20100180100 | Lu et al. | Jul 2010 | A1 |
| 20100199247 | Huynh | Aug 2010 | A1 |
| 20100325187 | Juffa et al. | Dec 2010 | A1 |
| 20110040821 | Eichenberger et al. | Feb 2011 | A1 |
| 20110040822 | Eichenberger et al. | Feb 2011 | A1 |
| 20110072065 | Mimar | Mar 2011 | A1 |
| 20110153707 | Ginzburg et al. | Jun 2011 | A1 |
| 20120011348 | Eichenberger et al. | Jan 2012 | A1 |
| 20120079252 | Sprangle | Mar 2012 | A1 |
| 20120113133 | Shpigelblat | May 2012 | A1 |
| 20120137074 | Kim et al. | May 2012 | A1 |
| 20120144130 | Fossum | Jun 2012 | A1 |
| 20120254588 | Adrian et al. | Oct 2012 | A1 |
| 20120254592 | San et al. | Oct 2012 | A1 |
| 20120314774 | Yang et al. | Dec 2012 | A1 |
| 20130016786 | Segall | Jan 2013 | A1 |
| 20130042093 | Van et al. | Feb 2013 | A1 |
| 20130076761 | Ellis | Mar 2013 | A1 |
| 20130262548 | Ge et al. | Oct 2013 | A1 |
| 20130305020 | Valentine et al. | Nov 2013 | A1 |
| 20130339668 | Ould-Ahmed-Vall et al. | Dec 2013 | A1 |
| 20140019713 | Ould-Ahmed-Vall et al. | Jan 2014 | A1 |
| 20140032876 | Burkart et al. | Jan 2014 | A1 |
| 20140149480 | Catanzaro et al. | May 2014 | A1 |
| 20140157287 | Howes et al. | Jun 2014 | A1 |
| 20140172937 | Linderman et al. | Jun 2014 | A1 |
| 20150052333 | Hughes et al. | Feb 2015 | A1 |
| 20150067302 | Gueron | Mar 2015 | A1 |
| 20150135195 | Khare et al. | May 2015 | A1 |
| 20150154024 | Anderson et al. | Jun 2015 | A1 |
| 20150199266 | Franchetti et al. | Jul 2015 | A1 |
| 20150242267 | Modarresi | Aug 2015 | A1 |
| 20160011870 | Plotnikov et al. | Jan 2016 | A1 |
| 20160165321 | Denoual | Jun 2016 | A1 |
| 20160239706 | Dijkman et al. | Aug 2016 | A1 |
| 20160246619 | Chang et al. | Aug 2016 | A1 |
| 20170053375 | Bolz | Feb 2017 | A1 |
| 20180004510 | Grochowski et al. | Jan 2018 | A1 |
| 20180113708 | Corbal et al. | Apr 2018 | A1 |
| 20180189227 | Korthikanti et al. | Jul 2018 | A1 |
| 20180321938 | Boswell et al. | Nov 2018 | A1 |
| 20190042202 | Sade et al. | Feb 2019 | A1 |
| 20190042248 | Bradford et al. | Feb 2019 | A1 |
| 20190042256 | Sade et al. | Feb 2019 | A1 |
| 20190042541 | Sade et al. | Feb 2019 | A1 |
| 20190042542 | Narayanamoorthy et al. | Feb 2019 | A1 |
| 20190121837 | Azizi et al. | Apr 2019 | A1 |
| 20190205137 | Meadows et al. | Jul 2019 | A1 |
| 20190347310 | Valentine et al. | Nov 2019 | A1 |
| 20200065352 | Valentine et al. | Feb 2020 | A1 |
| 20200097291 | Hughes et al. | Mar 2020 | A1 |
| 20200210517 | Baum et al. | Jul 2020 | A1 |
| 20200233665 | Valentine et al. | Jul 2020 | A1 |
| 20200233666 | Valentine et al. | Jul 2020 | A1 |
| 20200233667 | Valentine et al. | Jul 2020 | A1 |
| Number | Date | Country |
|---|---|---|
| 3547120 | Oct 2019 | EP |
| 3646169 | May 2020 | EP |
| 10-2011-0079495 | Jul 2011 | KR |
| 2004053841 | Jun 2004 | WO |
| 2006081094 | Aug 2006 | WO |
| 2007143278 | Dec 2007 | WO |
| 2008037975 | Apr 2008 | WO |
| 2013048369 | Apr 2013 | WO |
| 2016003740 | Jan 2016 | WO |
| 2016075158 | May 2016 | WO |
| 2016105727 | Jun 2016 | WO |
| 2018125250 | Jul 2018 | WO |
| 2018174927 | Sep 2018 | WO |
| 2019002811 | Jan 2019 | WO |
| Entry |
|---|
| Exposing Memory Access Patterns to Improve Instruction and Memory Efficiency in GPUs by Neal C. Crago et al., ACM Transactions on Architecture and Code Optimization, vol. 15, No. 4, Article 45. Publication date: Oct. 2018. (Year: 2018). |
| ‘Brief Introduction to Vectors and Matrices’ archived from unf.edu on Dec. 30, 2008. (Year: 2008). |
| ‘Incompatibilities with MATLAB in Variable-Size Support for Code Generation’ by MathWorks, archive from 2015. (Year: 2015). |
| ‘Instruction Decoders and Combinatorial Circuits’ from lateblt.tripod, archived from Nov. 2016. (Year: 2016). |
| ‘Zeroing one or more matrix rows or columns’ from Stackoverflow, Apr. 2015. (Year: 2015). |
| Corrected Notice of Allowability, U.S. Appl. No. 15/201,442, dated Jan. 22, 2019, 5 pages. |
| Corrected Notice of Allowability, U.S. Appl. No. 15/201,442, dated Mar. 11, 2019, 2 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040534, dated Oct. 3, 2019, 9 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040536, dated Oct. 3, 2019, 10 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040537, dated Oct. 3, 2019, 10 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040538, dated Oct. 3, 2019, 10 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040539, dated Oct. 3, 2019, 11 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040540, dated Oct. 3, 2019, 9 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040541, dated Oct. 3, 2019, 10 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040543, dated Oct. 3, 2019, 11 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040544, dated Oct. 3, 2019, 11 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040545, dated Oct. 3, 2019, 10 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040546, dated Oct. 3, 2019, 10 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040547, dated Jan. 16, 2020, 12 pages. |
| International Preliminary Report on Patentability, PCT App. No. PCT/US2017/040548, dated Oct. 3, 2019, 10 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040534, dated Jan. 3, 2018, 11 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040536, dated Dec. 20, 2017, 11 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040537, dated Dec. 20, 2017, 11 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040538, dated Jan. 9, 2018, 12 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040539, dated Dec. 20, 2017, 12 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040540, dated Jan. 3, 2018, 14 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040541, dated Dec. 20, 2017, 11 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040543, dated Dec. 14, 2017, 15 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040544, dated Dec. 14, 2017, 13 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040545, dated Jan. 3, 2018, 11 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040546, dated Jan. 24, 2018, 15 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040547, dated Mar. 30, 2018, 15 pages. |
| International Search Report and Written Opinion, PCT App. No. PCT/US2017/040548, dated Dec. 20, 2017, 17 pages. |
| Lahr Dave, “Timing Matrix Multiplication in SciDB and Setting the Number of Worker Instances in SciDB and Running Matrix Multiplication Piecemeal”, Available Online at <http://dllahr.blogspot.com/2012/11/timing-matrix-multiplication-in-scidb.html>, Nov. 13, 2012, 8 pages. |
| Non-Final Office Action, U.S. Appl. No. 15/201,442, dated May 4, 2018, 11 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/398,200, dated Jul. 28, 2020, 17 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/487,766, dated Aug. 3, 2020, 13 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/487,784, dated Aug. 3, 2020, 19 pages. |
| Notice of Allowance, U.S. Appl. No. 15/201,442, dated Dec. 14, 2018, 5 pages. |
| Corrected Notice of Allowability, U.S. Appl. No. 16/474,483, dated Dec. 1, 2020, 2 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/487,747, dated Oct. 1, 2020, 13 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/487,755, dated Nov. 24, 2020, 10 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/487,774, dated Dec. 21, 2020, 13 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/487,787, dated Oct. 1, 2020, 16 pages. |
| Non-Final Office Action, U.S. Appl. No. 16/624,178, dated Jan. 13, 2021, 12 pages. |
| Notice of Allowance, U.S. Appl. No. 16/474,483, dated Sep. 2, 2020, 9 pages. |
| Supplementary European Search Report and Search Opinion, EP App. No. 17901884.1, dated Dec. 14, 2020, 12 pages. |
| Yang et al., “Research and Design of Dedicated Instruction for Reconfigurable Matrix Multiplication of VLIW Processor”, International Conference on Intelligent Networking and Collaborative Systems, 2016, 4 pages. |
| Number | Date | Country | |
|---|---|---|---|
| 20200241877 A1 | Jul 2020 | US |
| Number | Date | Country | |
|---|---|---|---|
| 62473732 | Mar 2017 | US |
