Abstract: A high bandwidth memory system. In some embodiments, the system includes: a memory stack having a plurality of memory dies and eight 128-bit channels; and a logic die, the memory dies being stacked on, and connected to, the logic die; wherein the logic die may be configured to operate a first channel of the 128-bit channels in: a first mode, in which a first 64 bits operate in pseudo-channel mode, and a second 64 bits operate as two 32-bit fine-grain channels, or a second mode, in which the first 64 bits operate as two 32-bit fine-grain channels, and the second 64 bits operate as two 32-bit fine-grain channels.

Abstract: A high-bandwidth memory (HBM) system includes an HBM device and a logic circuit. The logic circuit receives a first command from the host device and converts the received first command to a processing-in-memory (PIM) command that is sent to the HBM device through the second interface. A time between when the first command is received from the host device and when the HBM system is ready to receive another command from the host device is deterministic. The logic circuit further receives a fourth command and a fifth command from the host device. The fifth command requests time-estimate information relating to a time between when the fifth command is received and when the HBM system is ready to receive another command from the host device. The time-estimate information includes a deterministic period of time and an estimated period of time for a non-deterministic period of time.

Abstract: A method of processing in-memory commands in a high-bandwidth memory (HBM) system includes sending a function-in-HBM instruction to the HBM by a HBM memory controller of a GPU. A logic component of the HBM receives the FIM instruction and coordinates the instructions execution using the controller, an ALU, and a SRAM located on the logic component.

Abstract: A processor includes a plurality of memory units, each of the memory units including a plurality of memory cells, wherein each of the memory units is configurable to operate as memory, as a computation unit, or as a hybrid memory-computation unit.

Abstract: A high bandwidth memory system. In some embodiments, the system includes: a memory stack having a plurality of memory dies and eight 128-bit channels; and a logic die, the memory dies being stacked on, and connected to, the logic die; wherein the logic die may be configured to operate a first channel of the 128-bit channels in: a first mode, in which a first 64 bits operate in pseudo-channel mode, and a second 64 bits operate as two 32-bit fine-grain channels, or a second mode, in which the first 64 bits operate as two 32-bit fine-grain channels, and the second 64 bits operate as two 32-bit fine-grain channels.

Abstract: A high-bandwidth memory (HBM) includes a memory and a controller. The controller receives a data write request from a processor external to the HBM and the controller stores an entry in the memory indicating at least one address of data of the data write request and generates an indication that a data bus is available for an operation during a cycle time of the data write request based on the data write request comprising sparse data or data-value similarity. Sparse data includes a predetermined percentage of data values equal to zero, and data-value similarity includes a predetermined amount of spatial value locality of the data values. The predetermined percentage of data values equal to zero of sparse data and the predetermined amount of spatial value locality of the special-value pattern are both based on a predetermined data granularity.

Abstract: A computing accelerator using a lookup table. The accelerator may accelerate floating point multiplications by retrieving the fraction portion of the product of two floating-point operands from a lookup table, or by retrieving the product of two floating-point operands of two floating-point operands from a lookup table, or it may retrieve dot products of floating point vectors from a lookup table. The accelerator may be implemented in a three-dimensional memory assembly. It may use approximation, the symmetry of a multiplication lookup table, and zero-skipping to improve performance.

Abstract: A processor includes a plurality of memory units, each of the memory units including a plurality of memory cells, wherein each of the memory units is configurable to operate as memory, as a computation unit, or as a hybrid memory-computation unit.

Abstract: A computing accelerator using a lookup table. The accelerator may accelerate floating point multiplications by retrieving the fraction portion of the product of two floating-point operands from a lookup table, or by retrieving the product of two floating-point operands of two floating-point operands from a lookup table, or it may retrieve dot products of floating point vectors from a lookup table. The accelerator may be implemented in a three-dimensional memory assembly. It may use approximation, the symmetry of a multiplication lookup table, and zero-skipping to improve performance.

Abstract: According to some example embodiments of the present disclosure, in a method for a memory lookup mechanism in a high-bandwidth memory system, the method includes: using a memory die to conduct a multiplication operation using a lookup table (LUT) methodology by accessing a LUT, which includes floating point operation results, stored on the memory die; sending, by the memory die, a result of the multiplication operation to a logic die including a processor and a buffer; and conducting, by the logic die, a matrix multiplication operation using computation units.

Abstract: A high-bandwidth memory (HBM) system includes an HBM device and a logic circuit. The logic circuit includes a first interface coupled to a host device and a second interface coupled to the HBM device. The logic circuit receives a first command from the host device through the first interface and converts the received first command to a first processing-in-memory (PIM) command that is sent to the HBM device through the second interface. The first PIM command has a deterministic latency for completion. The logic circuit further receives a second command from the host device through the first interface and converting the received second command to a second PIM command that is sent to the HBM device through the second interface. The second PIM command has a non-deterministic latency for completion.

Abstract: According to some example embodiments of the present disclosure, in a method for a memory lookup mechanism in a high-bandwidth memory system, the method includes: using a memory die to conduct a multiplication operation using a lookup table (LUT) methodology by accessing a LUT, which includes floating point operation results, stored on the memory die; sending, by the memory die, a result of the multiplication operation to a logic die including a processor and a buffer; and conducting, by the logic die, a matrix multiplication operation using computation units.

Abstract: A high bandwidth memory (HBM) system includes a first HBM+ card. The first HBM+ card includes a plurality of HBM+ cubes. Each HBM+ cube has a logic die and a memory die. The first HBM+ card also includes a HBM+ card controller coupled to each of the plurality of HBM+ cubes and configured to interface with a host, a pin connection configured to connect to the host, and a fabric connection configured to connect to at least one HBM+ card.

Abstract: A high-bandwidth memory (HBM) system includes an HBM device and a logic circuit. The logic circuit includes a first interface coupled to a host device and a second interface coupled to the HBM device. The logic circuit receives a first command from the host device through the first interface and converts the received first command to a first processing-in-memory (PIM) command that is sent to the HBM device through the second interface. The first PIM command has a deterministic latency for completion. The logic circuit further receives a second command from the host device through the first interface and converting the received second command to a second PIM command that is sent to the HBM device through the second interface. The second PIM command has a non-deterministic latency for completion.

Abstract: A pseudo main memory system. The system includes a memory adapter circuit for performing memory augmentation using compression, deduplication, and/or error correction. The memory adapter circuit is connected to a memory, and employs the memory augmentation methods to increase the effective storage capacity of the memory. The memory adapter circuit is also connected to a memory bus and implements an NVDIMM-F or modified NVDIMM-F interface for connecting to the memory bus.

Abstract: An apparatus may include a heterogeneous computing environment that may be controlled, at least in part, by a task scheduler in which the heterogeneous computing environment may include a processing unit having fixed logical circuits configured to execute instructions; a reprogrammable processing unit having reprogrammable logical circuits configured to execute instructions that include instructions to control processing-in-memory functionality; and a stack of high-bandwidth memory dies in which each may be configured to store data and to provide processing-in-memory functionality controllable by the reprogrammable processing unit such that the reprogrammable processing unit is at least partially stacked with the high-bandwidth memory dies. The task scheduler may be configured to schedule computational tasks between the processing unit, and the reprogrammable processing unit.

Abstract: Inventive aspects include An HBM+ system, comprising a host including at least one of a CPU, a GPU, an ASIC, or an FPGA; and an HBM+ stack including a plurality of HBM modules arranged one atop another, and a logic die disposed beneath the plurality of HBM modules. The logic die is configured to offload processing operations from the host. A system architecture is disclosed that provides specific compute capabilities in the logic die of high bandwidth memory along with the supporting hardware and software architectures, logic die microarchitecture, and memory interface signaling options. Various new methods are provided for using in-memory processing abilities of the logic die beneath an HBM memory stack. In addition, various new signaling protocols are disclosed to use an HBM interface. The logic die microarchitecture and supporting system framework are also described.

Abstract: A pseudo main memory system. The system includes a memory adapter circuit for performing memory augmentation using compression, deduplication, and/or error correction. The memory adapter circuit is connected to a memory, and employs the memory augmentation methods to increase the effective storage capacity of the memory. The memory adapter circuit is also connected to a memory bus and implements an NVDIMM-F or modified NVDIMM-F interface for connecting to the memory bus.

Abstract: A method of dynamically selecting deduplication granularity in a memory system to decrease deduplication granularity and to increase hash-table efficiency, the method including selecting one or more deduplication granularities at an application level of an application using the memory system, the one or more deduplication granularities being selected according to features of the memory system, and assigning a memory region corresponding to each of the one or more selected deduplication granularities, where the method may use a memory manager to share memory translation table and hash table, and may be employed by a system that enables using higher capacity pre-allocated counter fields for frequently utilized lines.

Abstract: An apparatus may include a heterogeneous computing environment that may be controlled, at least in part, by a task scheduler in which the heterogeneous computing environment may include a processing unit having fixed logical circuits configured to execute instructions; a reprogrammable processing unit having reprogrammable logical circuits configured to execute instructions that include instructions to control processing-in-memory functionality; and a stack of high-bandwidth memory dies in which each may be configured to store data and to provide processing-in-memory functionality controllable by the reprogrammable processing unit such that the reprogrammable processing unit is at least partially stacked with the high-bandwidth memory dies. The task scheduler may be configured to schedule computational tasks between the processing unit, and the reprogrammable processing unit.