Abstract: A pipeline control system is distributed over the functional units (15, 17, 20, 25) in a processor (10). Decoder logic (12) issues operations, each with an associated tag, to the functional units, with up to n operations allowed to be outstanding. The units execute the operations and report termination information back to the decoder logic, but do not irrevocably change the state of the machine. Based on the termination information, the decoder logic retires normally terminated operations in order. If an operation terminates abnormally, the decoder logic instructs the units to back out of those operations that include and are later than the operation that terminated abnormally.

Abstract: In a first aspect of the invention, branch prediction hardware, comprising logic and interconnect, is configurable via a control line to alter the manner in which the branch prediction is generated. The configuration can be done programmatically in software. Or, the configuration can be done by hardware in response to processor events. Such processor events include the loading of the CS register and changes in the instruction workload. In a second aspect of the invention, related to speculative execution, the directions of a plurality of branches are predicted based partly on resolved branch history information. Tentative branch history information is then stored for each of the predicted branches. When a predicted branch is resolved, the resolved branch history information is updated based on the stored tentative branch history information for the branch most recently resolved. Additionally, the predictions may be partly based on preceding unresolved branch predictions if any are outstanding.

Abstract: The existing execution units of a high-performance processor are augmented by the addition of a supplemental integer execution unit, termed the Add/Move Unit (AMU), which performs select adds and moves in parallel and out-of-order with respect to the other execution units. At small incremental cost, AMU enables better use of the expensive limited resources of an existing Address Preparation unit (AP), which handles linear and physical address generation for memory operand references, control transfers, and page crosses. AMU removes data dependencies and thereby increases the available instruction level parallelism. The increased instruction level parallelism is readily exploited by the processor's ability to perform out-of-order and speculative execution, and performance is enhanced as a result.

Abstract: A pipeline control system for implementing a virtual architecture having a complex instruction set is distributed over RISC-like semi-autonomous functional units in a processor. Decoder logic fetches instructions of the target architecture and translates them into simpler RISC-like operations. These operations, each having an associated tag, are issued to the functional units. Address processing unit computes addresses of the instructions and operands, performs segment relocation, and manages the processor's memory. Operations are executed by the units in a manner that is generally independent of operation processing by the other units. The units report termination information back to the decoder logic, but do not irrevocably change the state of the machine. Based on the termination information, the decoder logic retires normally terminated operations in order.

Abstract: A pipeline control system for implementing a virtual architecture having complex instruction set is distributed over RISC-like semi-autonomous functional units in a processor. Decoder logic fetches instructions of the target architecture and translates them into simpler RISC-like operations. These operations, each having an associated tag, are issued to the functional units. Address processing unit computes addresses of the instructions and operands, performs segment relocation, and manages the processor's memory. Operations are executed by the units in a manner that is generally independent of operation processing by the other units. The units report termination information back to the decoder logic, but do not irrevocably change the state of the machine. Based on the termination information, the decoder logic retires normally terminated operations in order.

Abstract: A processor with a branch target cache (BTC) and multiple instruction prefetch storage circuits. A control mechanism allows the fetching of instructions to be transferred from a first prefetch storage circuit to a second prefetch storage circuit which contains branch target instruction bytes. The control is transferred based on a prediction of whether the branch will be taken using history bits associated with the branch instruction. If the processor later determines that the branch is mispredicted, the execution of instructions resumes from the first prefetch storage circuit.

Abstract: A pipeline control system is distributed over the functional units (15, 17, 20, 25) in a processor (10). Decoder logic (12) issues operations, each with an associated tag, to the functional units, with up to n operations allowed to be outstanding. The units execute the operations and report termination information back to the decoder logic, but do not irrevocably change the state of the machine. Based on the termination information, the decoder logic retires normally terminated operations in order. If an operation terminates abnormally, the decoder logic instructs the units to back out of those operations that include and are later than the operation that terminated abnormally.

Abstract: The existing execution units of a high-performance processor are augmented by the addition of a supplemental integer execution unit, termed the Add/Move Unit (AMU), which performs select adds and moves in parallel and out-of-order with respect to the other execution units. At small incremental cost, AMU enables better use of the expensive limited resources of an existing Address Preparation unit (AP), which handles linear and physical address generation for memory operand references, control transfers, and page crosses. AMU removes data dependencies and thereby increases the available instruction level parallelism. The increased instruction level parallelism is readily exploited by the processor's ability to perform out-of-order and speculative execution, and performance is enhanced as a result.

Abstract: A Branch Prediction Cache (BPC) selects from among multiple branch address entries for a single return-type instruction that returns to multiple callers. The BPC has a branch address associative memory, a return address associative memory, and word line logic used to validate and qualify entries. The branch address associative memory monitors program addresses for previously stored branch addresses. The return address stack (RtnStack) stores the return addresses for the most recent call-type instructions. The top of the stack is input to the return address associative memory. When a program address has multiple matches in the branch address associative memory, the return address associative memory enables only the entry that has an associated return address matching the top of the RtnStack. In an alternate embodiment, the return address associative memory is combined with a branch address cache and target address associative memory.

Abstract: An execution unit performs multiple sequential instruction pointer updates and segment limit checks within a cycle. The updates and checks are carried out in a high-performance pipelined processor that speculatively executes variable length instructions. A disclosed embodiment of the execution unit includes Next EIP (Extended Instruction Pointer) selection logic, Current EIP selection logic, an EIP History RAM, a Dual EIP Adder, a CS Limit check adder, limit checking combinational logic, and a limit fault History RAM.

Abstract: AN improved branch prediction cache (BPC) scheme that utilizes a hybrid cache structure. The BPC provides two levels of branch information caching. The fully associative first level BPC is a shallow but wide structure (36 32-byte entries), which caches full prediction information for a limited number of branch instructions. The second direct mapped level BPC is a deep but narrow structure (256 2-byte entries), which caches only partial prediction information, but does so for a much larger number of branch instructions. As each branch instruction is fetched and decoded, its address is used to perform parallel look-ups in the two branch prediction caches.

Abstract: In a first aspect of the invention, branch prediction hardware, comprising logic and interconnect, is configurable via a control line to alter the manner in which the branch prediction is generated. The configuration can be done programmatically in software. Or, the configuration can be done by hardware in response to processor events. Such processor events include the loading of the CS register and changes in the instruction workload. In a second aspect of the invention, related to speculative execution, the directions of a plurality of branches are predicted based partly on resolved branch history information. Tentative branch history information is then stored for each of the predicted branches. When a predicted branch is resolved, the resolved branch history information is updated based on the stored tentative branch history information for the branch most recently resolved. Additionally, the predictions may be partly based on preceding unresolved branch predictions if any are outstanding.

Abstract: A pipeline control system is distributed over the functional units (15, 17, 20, 25) in a processor (10). Decoder logic (12) issues operations, each with an associated tag, to the functional units, with up to n operations allowed to be outstanding. The units execute the operations and report termination information back to the decoder logic, but do not irrevocably change the state of the machine. Based on the termination information, the decoder logic retires normally terminated operations in order. If an operation terminates abnormally, the decoder logic instructs the units to back out of those operations that include and are later than the operation that terminated abnormally.

Abstract: An improved branch prediction cache (BPC) scheme that utilizes a hybrid cache structure. The BPC provides two levels of branch information caching. The fully associative first level BPC is a shallow but wide structure (36 32-byte entries), which caches full prediction information for a limited number of branch instructions. The second direct mapped level BPC is a deep but narrow structure (256 2-byte entries), which caches only partial prediction information, but does so for a much larger number of branch instructions. As each branch instruction is fetched and decoded, its address is used to perform parallel look-ups in the two branch prediction caches.

Abstract: A system which integrates the multiple instruction queues and the branch target cache (BTC) of a high performance CPU design into a single physical structure. Effectively, the queues are merged into the BTC in such a manner that, at any point in time, most of this structure functions as a BTC while certain entries function as instruction queues.By using parts of the BTC to serve as instruction queues, the inefficiency of separate queue structures is eliminated and the queues are implemented with the greater device density characteristic of the RAM structure which the BTC core is based on. This merging of these structures also substantially simplifies the instruction queue control and the routing of instruction words between BTC entries and queues.

Abstract: A pipeline control system is distributed over the functional units (15, 17, 20, 25) in a processor (10). Decoder logic (12) issues operations, each with an associated tag, to the functional units, with up to n operations allowed to be outstanding. The units execute the operations and report termination information back to the decoder logic, but do not irrevocably change the state of the machine. Based on the termination information, the decoder logic retires normally terminated operations in order. If an operation terminates abnormally, the decoder logic instructs the units to back out of those operations that include and are later than the operation that terminated abnormally.

Abstract: An improved branch prediction cache (BPC) scheme that utilizes a hybrid cache structure. The BPC provides two levels of branch information caching. The fully associative first level BPC is a shallow but wide structure (36 32-byte entries), which caches full prediction information for a limited number of branch instructions. The second direct mapped level BPC is a deep but narrow structure (256 2-byte entries), which caches only partial prediction information, but does so for a much larger number of branch instructions. As each branch instruction is fetched and decoded, its address is used to perform parallel look-ups in the two branch prediction caches.

Abstract: A digital processor has a controller, a data converter, a data register, and a logarithmic calculator. The processor has an address bus and a data bus for communication therewith. The address bus is connected to the controller. The data bus is connected to the controller and to the data register. Program instructions from the data bus are supplied to the controller and data on the data bus are supplied to the data register. Program instructions supplied to the controller are decoded and internal program instructions are generated by the controller. The controller communicates with the data converter, data register, and the logarithmic calculator via an internal bus through the internal program instructions. Integer data from the data bus are stored in the data register. The data converter receives the integer data, converts it into logarithmic data, and stores it in the data register.

Abstract: A digital processor has four components: a controller, a data converter, a data register, and a logarithmic calculator. The processor has an address bus and a data bus for communication therewith. The address bus is connected to the controller. The data bus is connected to the controller and to the data register. Program instructions from the data bus are supplied to the controller and data on the data bus are supplied to the data register. Program instructions supplied to the controller are decoded and internal program instructions are generated by the controller. The controller communicates with the data converter, data register, and the logarithmic calculator via an internal bus through the internal program instructions. Integer data from the data bus are stored in the data register. The data converter receives the integer data, converts it into logarithmic data, and stores it in the data register.

Abstract: A calculating apparatus receives four operands ("a, b, c and d") simultaneously. A first multiplier/divider performs the calculation of a*b or a.div.b and provides an output u. A second multiplier/divider performs the calculation of c*d or c.div.d and provides an output v. An adder/subtractor receives u and v and performed the calculation of u+v and u-v. A controller controls the operation of the first and second multiplier/divider to select the operation of multiplication or division.