Abstract: Embodiments of the invention include method, systems and computer program products for servicing indirect storage requests. Method includes decoding a storage request instruction and sending to a first one of a plurality of memory controllers an address represented by a first pointer associated with at least a portion of the storage request instruction. A first memory is used to read information associated with a second pointer contained at the address. The first memory forwards the storage request instruction to a second one of the plurality of memory controllers, wherein the second one of the plurality of memory controllers is associated with and/or manages a memory location represented by the second pointer. The second one of the plurality of memory controllers reads and forwards data associated with the storage request instruction to a processor using the second pointer. The processor writes the forwarded data in a destination register of the processor.

Abstract: Predicting indirect branch instructions may comprise predicting a target address for a fetched branch instruction. Accuracy of the target address may be tracked. The fetched branch instruction may be flagged as a problematic branch instruction based on the tracking. A pattern cache may be trained for predicting a more accurate target address for the fetched branch instruction, and the next time the fetched branch instruction is again fetched, a target address may be predicted from the pattern cache.

Abstract: Embodiments include method, systems and computer program products for fusing one or more transaction request messages. The computer-implemented method includes comparing, using a memory controller, at least two electronic transaction request messages and determining if the at least two electronic transaction request messages are of a same electronic transaction request message type. The memory controller is used to determine that the at least two electronic transaction request messages are directed to associated portions of memory based at least in part on determining that the at least two electronic transaction request messages are the same electronic transaction request message type. The memory controller fuses the at least two electronic transaction request messages based at least in part on determining that the at least two electronic transaction request messages are directed to associated portions of memory.

Abstract: A computer-implemented method includes receiving, at a memory controller, a new transaction request referencing a new transaction to be executed on a memory. The memory includes two or more memory groups embodying two or more memory technologies, and the memory controller includes two or more group request queues with a respective group request queue corresponding to each memory group of the two or more memory groups. A memory group is selected, by the memory controller, from among the two or more memory groups. The transaction request is placed, by the memory controller, on the respective group request queue corresponding to the selected memory group. The new transaction is executed on the selected memory group. A new response to the new transaction is received, by the memory controller, from the selected memory group. The new response is returned.

Abstract: An aspect includes receiving a request to access data in a memory, the request from a requesting processor and including a virtual address of the data. It is determined, based on contents of a page table that a plurality of physical addresses in the memory corresponds to the virtual address. The physical addresses include a first physical address of a primary memory location in a first partition accessed via a bus that is communicatively coupled to a port of a first processor, and a second physical address of a secondary memory location in a second partition accessed via a bus that is communicatively coupled to a port of a second processor. Contents of the primary memory location in the first partition were previously copied into the secondary memory location. Based on the requesting processor, one of the physical addresses is selected and data at the selected physical address is accessed.

Abstract: An aspect includes receiving a request to access data in a memory, the request from a requesting processor and including a virtual address of the data. It is determined, based on contents of a page table that a plurality of physical addresses in the memory corresponds to the virtual address. The physical addresses include a first physical address of a primary memory location in a first partition accessed via a bus that is communicatively coupled to a port of a first processor, and a second physical address of a secondary memory location in a second partition accessed via a bus that is communicatively coupled to a port of a second processor. Contents of the primary memory location in the first partition were previously copied into the secondary memory location. Based on the requesting processor, one of the physical addresses is selected and data at the selected physical address is accessed.

Abstract: A computer-implemented method includes receiving, at a memory controller, a new transaction request referencing a new transaction to be executed on a memory. The memory includes two or more memory groups embodying two or more memory technologies, and the memory controller includes two or more group request queues with a respective group request queue corresponding to each memory group of the two or more memory groups. A memory group is selected, by the memory controller, from among the two or more memory groups. The transaction request is placed, by the memory controller, on the respective group request queue corresponding to the selected memory group. The new transaction is executed on the selected memory group. A new response to the new transaction is received, by the memory controller, from the selected memory group. The new response is returned.

Abstract: Embodiments include method, systems and computer program products for fusing one or more transaction request messages. The computer-implemented method includes comparing, using a memory controller, at least two electronic transaction request messages and determining if the at least two electronic transaction request messages are of a same electronic transaction request message type. The memory controller is used to determine that the at least two electronic transaction request messages are directed to associated portions of memory based at least in part on determining that the at least two electronic transaction request messages are the same electronic transaction request message type. The memory controller fuses the at least two electronic transaction request messages based at least in part on determining that the at least two electronic transaction request messages are directed to associated portions of memory.

Abstract: Embodiments of the invention include method, systems and computer program products for servicing indirect storage requests. Method includes decoding a storage request instruction and sending to a first one of a plurality of memory controllers an address represented by a first pointer associated with at least a portion of the storage request instruction. A first memory is used to read information associated with a second pointer contained at the address. The first memory forwards the storage request instruction to a second one of the plurality of memory controllers, wherein the second one of the plurality of memory controllers is associated with and/or manages a memory location represented by the second pointer. The second one of the plurality of memory controllers reads and forwards data associated with the storage request instruction to a processor using the second pointer. The processor writes the forwarded data in a destination register of the processor.

Abstract: An aspect includes receiving a request to access data in a memory, the request from a requesting processor and including a virtual address of the data. It is determined, based on contents of a page table that a plurality of physical addresses in the memory corresponds to the virtual address. The physical addresses include a first physical address of a primary memory location in a first partition accessed via a bus that is communicatively coupled to a port of a first processor, and a second physical address of a secondary memory location in a second partition accessed via a bus that is communicatively coupled to a port of a second processor. Contents of the primary memory location in the first partition were previously copied into the secondary memory location. Based on the requesting processor, one of the physical addresses is selected and data at the selected physical address is accessed.

Abstract: An aspect includes receiving a request to access data in a memory, the request from a requesting processor and including a virtual address of the data. It is determined, based on contents of a page table that a plurality of physical addresses in the memory corresponds to the virtual address. The physical addresses include a first physical address of a primary memory location in a first partition accessed via a bus that is communicatively coupled to a port of a first processor, and a second physical address of a secondary memory location in a second partition accessed via a bus that is communicatively coupled to a port of a second processor. Contents of the primary memory location in the first partition were previously copied into the secondary memory location. Based on the requesting processor, one of the physical addresses is selected and data at the selected physical address is accessed.

Abstract: Tracking global history vector in high performance out of order superscalar processors, in one aspect, may comprise providing a shift register storing global history vector that stores branch predictions and outcomes. A counter is maintained to determine a number of bits to shift the shift register to recover branch history. In another aspect, the global history vector may be implemented with a circular buffer structure. Youngest and oldest pointers to the circular buffer are maintained and used in recovery.

Abstract: Provided herein is a compressed cache design to predict indirect branches in a microprocessor based on the characteristics of the addresses of the branch instructions. In one aspect, a method for predicting a branch target T in a microprocessor includes the following steps. A compressed count cache table (CTABLE) of branch targets indexed using a function combining a branch address and a branch history vector for each of the targets is maintained, wherein entries in the CTABLE contain only low-order bits of each of the targets in combination with an index bit(s) I. A given one of the entries is obtained related to a given one of the branch targets and it is determined from the index bits I whether A) high-order bits of the target are equal to the branch address, or B) the high-order bits of the target are contained in an auxiliary cache table (HTABLE).

Abstract: A technique for branch target prediction includes storing, based on an instruction fetch address for a group of fetched instructions, first predicted targets for first indirect branch instructions in respective entries of a local count cache. Second predicted targets for second indirect branch instructions are stored in respective entries of a global count cache, based on the instruction fetch address and a global history vector for the instruction fetch address. One of the local count cache and the global count cache is selected to provide a selected predicted target for an indirect branch instruction in the group of fetched instructions.

Abstract: A system and method for reducing power consumption of memory chips outside of a host processor device inoperative communication with the memory chips via a memory controller. The memory can operate in modes, such that via the memory controller, the stored data can be localized and moved at various granularities, among ranks established in the chips, to result in fewer operating ranks. Memory chips may then be turned on and off based on host memory access usage levels at each rank in the chip. Host memory access usage levels at each rank in the chip is tracked by performance counters established for association with each rank of a memory chip. Turning on and off of the memory chips is based on a mapping maintained between ranks and address locations corresponding to sub-sections within each rank receiving the host processor access requests.

Abstract: Predicting indirect branch instructions may comprise predicting a target address for a fetched branch instruction. Accuracy of the target address may be tracked. The fetched branch instruction may be flagged as a problematic branch instruction based on the tracking. A pattern cache may be trained for predicting more accurate target address for the fetched branch instruction, and the next time the fetched branch instruction is again fetched, a target address may be predicted from the pattern cache.

Abstract: Provided herein is a compressed cache design to predict indirect branches in a microprocessor based on the characteristics of the addresses of the branch instructions. In one aspect, a method for predicting a branch target T in a microprocessor includes the following steps. A compressed count cache table (CTABLE) of branch targets indexed using a function combining a branch address and a branch history vector for each of the targets is maintained, wherein entries in the CTABLE contain only low-order bits of each of the targets in combination with an index bit(s) I. A given one of the entries is obtained related to a given one of the branch targets and it is determined from the index bits I whether A) high-order bits of the target are equal to the branch address, or B) the high-order bits of the target are contained in an auxiliary cache table (HTABLE).

Abstract: A technique for branch target prediction includes storing, based on an instruction fetch address for a group of fetched instructions, first predicted targets for first indirect branch instructions in respective entries of a local count cache. Second predicted targets for second indirect branch instructions are stored in respective entries of a global count cache, based on the instruction fetch address and a global history vector for the instruction fetch address. One of the local count cache and the global count cache is selected to provide a selected predicted target for an indirect branch instruction in the group of fetched instructions.

Abstract: Tracking global history vector in high performance out of order superscalar processors, in one aspect, may comprise providing a shift register storing global history vector that stores branch predictions and outcomes. A counter is maintained to determine a number of bits to shift the shift register to recover branch history. In another aspect, the global history vector may be implemented with a circular buffer structure. Youngest and oldest pointers to the circular buffer are maintained and used in recovery.

Abstract: A system and method for reducing power consumption of memory chips outside of a host processor device inoperative communication with the memory chips via a memory controller. The memory can operate in modes, such that via the memory controller, the stored data can be localized and moved at various granularities, among ranks established in the chips, to result in fewer operating ranks. Memory chips may then be turned on and off based on host memory access usage levels at each rank in the chip. Host memory access usage levels at each rank in the chip is tracked by performance counters established for association with each rank of a memory chip. Turning on and off of the memory chips is based on a mapping maintained between ranks and address locations corresponding to sub-sections within each rank receiving the host processor access requests.