Search NASA⌕ Search

SEARCH · Search NASA

Results for “DRAM”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7

Optimization and Control of Plasma Doping Processes

Plasma doping (PLAD) is a well characterized alternative to beam-line technology, which has already been adopted in high volume manufacturing in the ultra high dose, low energy regime for advanced DRAM technology nodes. As semiconductor technology evolves, the demand for ever lower energy, higher dose implants will continue to grow, and the requirements for process control will become increasingly stringent. During plasma immersion ion implantation, ionized species present in the plasma are extracted and implanted into the wafer, while other processes, such as deposition, etching and sputtering, are competing in parallel. The dopant profile into the substrate results from contributions of all these mechanisms. Using the hardware and plasma composition control features present in the PLAD system to balance the contributions of the above processes, the dopant profile can be modified and dopant retention can be optimized. In this paper, we detail the process control approach used to optimize process performance for low energy, high dose implants, and validate it with plasma and wafer state data.

36 MATERIALS SCIENCE↗

Formation of Ultra-Shallow Junctions by Advanced Plasma Doping Techniques

The fabrication of advanced CMOS devices calls for production worthy doping solutions to address requirements for increasingly shallow and abrupt junctions, while maintaining high dopant activation to meet series resistance requirements. Plasma Doping (PLAD), which has already been adopted in high volume manufacturing in the ultra high dose, low energy regime for advanced DRAM technology nodes, is now being investigated for source drain extension (SDE) implants, where precise and repeatable dopant placement is critical for maintaining control over device parameters. In this article, we investigate the process performance of SDE implants carried out in a VIISta registered PLAD system using p- type dopant precursors. Key metrics, such as junction depth, profile abruptness and sheet resistance are reported for as-implanted junctions, as well as samples processed with low thermal budget anneal techniques. Device performance data demonstrating the feasibility of the approach are presented. The advanced control features in the PLAD system are critical in enabling the process performance required for SDE implants.

36 MATERIALS SCIENCE↗

Physical and Electrical Characterization of 120 nm Technology Node Devices using PULSION registered Plasma Doping

Plasma doping is a well-known technology used in semiconductor manufacturing for two major DRAM manufacturing steps: polysilicon counter-doping and contact doping. For these specific applications, the PULSION tool shows physical benefits, as well as cost of ownership benefits, with the capability to perform low energy, high dose implantation in a high throughput mode. Nevertheless, throughput is a common challenge for all semiconductor manufacturing, not only for advanced technologies. The purpose of this study is to demonstrate that plasma doping is not limited to advanced devices, but can also satisfy the requirements of >90 nm nodes, for specific applications such as Lightly Doped Drain (LDD) implants.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Different Profile Responses to Dose Variation for B{sub 2}H{sub 6} and BF{sub 3} Plasma Doping using PULSION registered

Plasma doping has been accepted into semiconductor manufacturing for two low energy, high dose implant applications. The p-type polysilicon counter-doping and contact doping for DRAM devices can be carried out using BF{sub 3} or B{sub 2}H{sub 6} precursor gas. The choice between these two precursors depends on the benefits and constraints of each one. In order to identify these benefits and constraints, the boron dopant profile responses to dose variation for both precursors have been studied using the PULSION plasma doping tool.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

PULSION registered HP: Tunable, High Productivity Plasma Doping

Plasma doping has been explored for many implant applications for over two decades and is now being used in semiconductor manufacturing for two applications: DRAM polysilicon counter-doping and contact doping. The PULSION HP is a new plasma doping tool developed by Ion Beam Services for high-volume production that enables customer control of the dominant mechanism--deposition, implant, or etch. The key features of this tool are a proprietary, remote RF plasma source that enables a high density plasma with low chamber pressure, resulting in a wide process space, and special chamber and wafer electrode designs that optimize doping uniformity.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Plasma process optimization for N-type doping applications

Plasma doping (PLAD) has been adopted across the implant technology space and into high volume production for both conventional DRAM and NAND doping applications. PLAD has established itself as an alternative to traditional ion implantation by beamline implantation. The push for high doping concentration, shallow doping depth, and conformal doping capability expand the need for a PLAD solution to meet such requirements. The unique doping profile and doping characteristics at high dose rates allow for PLAD to deliver a high throughput, differentiated solution to meet the demand of evolving transistor technology. In the PLAD process, ions are accelerated to the wafer as with a negative wafer bias applied to the wafer. Competing mechanisms, such as deposition, sputtering, and etching inherent in plasma doping require unique control and process optimization. In this work, we look at the distinctive process tool control and characterization features which enable an optimized doping process using n-type (PH{sub 3} or AsH{sub 3}) chemistries. The data in this paper will draw the relationship between process optimization through plasma chemistry study to the wafer level result.

36 MATERIALS SCIENCE↗

efam: an e xpanded, metaproteome-supported HMM profile database of viral protein fam ilies

Viruses infect, reprogram and kill microbes, leading to profound ecosystem consequences, from elemental cycling in oceans and soils to microbiome-modulated diseases in plants and animals. Although metagenomic datasets are increasingly available, identifying viruses in them is challenging due to poor representation and annotation of viral sequences in databases. Here, we establish efam, an expanded collection of Hidden Markov Model (HMM) profiles that represent viral protein families conservatively identified from the Global Ocean Virome 2.0 dataset. This resulted in 240 311 HMM profiles, each with at least 2 protein sequences, making efam >7-fold larger than the next largest, pan-ecosystem viral HMM profile database. Adjusting the criteria for viral contig confidence from ‘conservative’ to ‘eXtremely Conservative’ resulted in 37 841 HMM profiles in our efam-XC database. To assess the value of this resource, we integrated efam-XC into VirSorter viral discovery software to discover viruses from less-studied, ecologically distinct oxygen minimum zone (OMZ) marine habitats. This expanded database led to an increase in viruses recovered from every tested OMZ virome by ~24% on average (up to ~42%) and especially improved the recovery of often-missed shorter contigs (<5 kb). Additionally, to help elucidate lesser-known viral protein functions, we annotated the profiles using multiple databases from the DRAM pipeline and virion-associated metaproteomic data, which doubled the number of annotations obtainable by standard, single-database annotation approaches. Together, these marine resources (efam and efam-XC) are provided as searchable, compressed HMM databases that will be updated bi-annually to help maximize viral sequence discovery and study from any ecosystem.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Survey on the Expanding Scope and Interdisciplinary Opportunities for Processing-in-Memory Techniques

Processing-in-Memory (PIM) is emerging as a practical path to overcome the limitations of traditional von Neumann architectures. At its core, PIM systems implement computing primitives such as logic operations and multiply-accumulate acceleration through compute-in-memory, near-memory processing, or hybrid designs. The role of memory cells varies widely across technologies, acting as inputs, outputs, or analog accumulators through bit-lines and sense amplifiers. This diversity creates trade-offs in precision, bandwidth, latency, and programmability, making it difficult to build a unified understanding on the progress of the field. In this survey, we organize recent advances of PIM into three areas. First, we discuss the progress on the architectural optimizations of PIM and its integration with both DRAM and emerging non-volatile memories. Second, we examine how PIM is being used to accelerate key computing domains, including generative AI workloads and high-performance kernels, along with new approaches. Third, we highlight the growing adoption of PIM in computational sciences, where it is being applied to solve interdisciplinary problems such as genome analysis, mRNA quantification, mass spectrometry, quantum circuit simulation, wave modeling, and secure computation. Finally, we synthesize the major challenges that continue to slow PIM adoption, including manufacturing constraints, power delivery, thermal reliability, data consistency, runtime and memory-management coordination, and the difficulty of building portable software abstractions without sacrificing commercial viability. This work provides an updated, structured perspective on PIM’s potential across computing and computational sciences and the barriers that must be solved for it to reach its full impact.

Asifuzzaman, Kazi [Oak Ridge National Laboratory (↗

Processing-in-Memory Enabled Graphics Processors for 3D Rendering

The performance of 3D rendering of Graphics Processing Unit that convents 3D vector stream into 2D frame with 3D image effects significantly impact users’ gaming experience on modern computer systems. Due to the high texture throughput in 3D rendering, main memory bandwidth becomes a critical obstacle for improving the overall rendering performance. 3D stacked memory systems such as Hybrid Memory Cube (HMC) provide opportunities to significantly overcome the memory wall by directly connecting logic controllers to DRAM dies. Based on the observation that texel fetches significantly impact off-chip memory traffic, we propose two architectural designs to enable Processing-In-Memory based GPU for efficient 3D rendering.

Innovative hardware/software co-design↗

SharP: Towards Programming Extreme-Scale Systems with Hierarchical Heterogeneous Memory

The pre-exascale systems are expected to have a significant amount of hierarchical and heterogeneous on-node memory, and this trend of system architecture in extreme-scale systems is expected to continue into the exascale era. Along with hierarchical-heterogeneous memory, the system typically has a high-performing network and a compute accelerator. This system architecture is not only effective for running traditional High Performance Computing (HPC) applications (Big-Compute), but also running data-intensive HPC applications and Big-Data applications. As a consequence, there is a growing desire to have a single system serve the needs of both Big-Compute and Big-Data applications. Though the system architecture supports the convergence of the Big-Compute and Big-Data, the programming models have yet to evolve to support either hierarchical-heterogeneous memory systems or the convergence. In this work, we propose and develop the programming abstraction called SHARed data-structure centric Programming abstraction (SharP) to address both of these goals, i.e., provide (1) a simple, usable, and portable abstraction for hierarchical-heterogeneous memory and (2) a unified programming abstraction for Big-Compute and Big-Data applications. To evaluate SharP, we implement a Stencil benchmark using SharP, port QMCPack, a petascale-capable application, and adapt Memcached ecosystem, a popular Big-Data framework, to use SharP, and quantify the performance and productivity advantages. Additionally, we demonstrate the simplicity of using SharP on different memories including DRAM, High-bandwidth Memory (HBM), and non-volatile random access memory (NVRAM).

97 MATHEMATICS AND COMPUTING↗

FitCache: A Transparent Drop-In Framework for Multi-Tier Caching to Accelerate Distributed Deep Learning Workloads

Training in Deep learning (DL) remains highly compute- and data-intensive, with I/O becoming a critical bottleneck as models and datasets scale. Recent studies report that data loading can dominate training time, especially on large-scale HPC systems with shared parallel file systems (PFS). Existing caching approaches either rely on single-tier designs or require intrusive modifications to training pipelines, limiting their portability and effectiveness. In this work, we present FitCache, a transparent drop-in framework for multi-tier caching to accelerate distributed DL training by coordinating fast local memory (e.g., DRAM, Persistent Memory (PMem)) and NVMe as hierarchical caches atop PFS. Our design adapts to hardware diversity, i.e., if NVMe is missing, memory transparently acts as a caching tier, ensuring stable performance. FitCache transparently intercepts I/O requests and issues concurrent fetches across all tiers, returning data from the fastest responder without centralized metadata or static redirection paths. FitCache adapts to dynamic workloads and heterogeneous clusters while maintaining POSIX compatibility. Experiments on Frontier (2048 GPUs) and smaller research clusters show that FitCache reduces training time by up to 40% and per-batch I/O latency by up to 71.6% compared to Lustre Orion PFS, offering a drop-in solution for scalable DL training.

Hu, Guangxing [ORNL] (ORCID:0009000283203614)↗

Population Count on Intel® CPU, GPU, and FPGA

Population count is a primitive used in many applications. Commodity processors have dedicated instructions for achieving high-performance population count. Motivated by the productivity of high-level synthesis and the importance of population count, in this paper we investigated the OpenCL implementations of population count algorithms, and evaluated their performance and resource utilizations on an FPGA. Based on the results, we select the most efficient implementation. Then we derived a reduction pattern from a representative application of population count. We parallelized the reduction with atomic functions, and optimized it with vectorized memory accesses, tree reduction, and compute-unit duplication. We evaluated the performance of the reduction kernel on an Intel (R) Xeon (R) CPU and an Intel (R) IrisT Pro integrated GPU, and an FPGA card that features an Intel (R) Arria (R) 10 FPGA. When DRAM memory bandwidth is comparable on the three computing platforms, the FPGA can achieve the highest kernel performance for large workload. On the other hand, we described performance bottlenecks on the FPGA. To make FPGAs more competitive in raw performance compared to high-performant CPU and GPU platforms, it is important to increase external memory bandwidth, minimize data movement between a host and a device, and reduce OpenCL runtime overhead on an FPGA.

heterogeneous computing↗

Exascale Workload Characterization and Architecture Implications

We use a hybrid methodology based on binary instrumentation and performance counters to characterize a set of proxy applications (mini-apps and PETSc applications) representative of a broad range of scientific applications (and particularly DOE's future high performance computing workloads). From this empirical basis, we create statistical models that extrapolate application properties (instruction mix, memory size, and memory bandwidth) as a function of problem size. We validate them and project the first quantitative characterization of an exascale computing workload. Finally, the exascale workload is used to evaluate a radical new exascale architecture, stacked DRAM with processor under memory (PUM). Of the two projections, one shows major potential benefits in using PUM. However, the second, more conservative projection suggests that only a small number of exascale applications are likely to be memory-bandwidth limited, but even these are fundamentally memory-capacity limited.

Balaprakash, Prasanna↗

Performance Assessment of Emerging Memories Through FPGA Emulation

Emerging memory technologies offer the prospect of large capacity, high bandwidth, and a range of access latencies ranging from DRAM-like to SSD-like. In this paper, we evaluate the performance of parallel applications on CPUs whose main memories sweep a wide range of latencies within a bandwidth cap. We use an FPGA emulator, the logic in memory emulator (LiME) to accelerate evaluation. The LiME framework uses a multiprocessor system on chip (MPSoC) combining multicore CPU, integrated memory controller, and FPGA fabric, and enables emulation orders of magnitude faster than software simulation. This work highlights the performance impact of higher latency on concurrent applications and identifies conditions under which future high latency memories can effectively be used as main memory.

97 MATHEMATICS AND COMPUTING↗

Understanding Strong Scaling on GPUs Using Empirical Performance Saturation Size

The roofline model provides a concise overview of the maximum performance capabilities of a given computer system through a combination of peak memory bandwidth and compute performance rates. The increasing complexity of scheduling and cache in recent GPUs, however, has introduced complicated performance variability that is not captured by arithmetic intensity alone. This work examines the effect of problem size and GPU launch configurations on roofline performance for V100, A100, MI100, and MI250X graphics processing units. We introduce an extended roofline model that takes problem size into account, and find that strong scaling on GPUs can be characterized by saturation problem sizes as additional key metrics. Saturation problem sizes break up a plot of GPU performance vs. problem size into three distinct performance regimes– size-limited, cache-bound, and DRAM-bound. With our extended roofline model, we are able to provide a robust view of these performance regimes across recent GPU architectures.

Eberius, David↗

A Survey of Software Techniques for Using Non-Volatile Memories for Storage and Main Memory Systems

Non-volatile memory (NVM) devices, such as Flash, phase change RAM, spin transfer torque RAM, and resistive RAM, offer several advantages and challenges when compared to conventional memory technologies, such as DRAM and magnetic hard disk drives (HDDs). Here, we present a survey of software techniques that have been proposed to exploit the advantages and mitigate the disadvantages of NVMs when used for designing memory systems, and, in particular, secondary storage (e.g., solid state drive) and main memory. Furthermore, we classify these software techniques along several dimensions to highlight their similarities and differences. Given that NVMs are growing in popularity, we believe that this survey will motivate further research in the field of software technology for NVMs.

97 MATHEMATICS AND COMPUTING↗

A High Performance Block Eigensolver for Nuclear Configuration Interaction Calculations

As on-node parallelism increases and the performance gap between the processor and the memory system widens, achieving high performance in large-scale scientific applications requires an architecture-aware design of algorithms and solvers. We focus on the eigenvalue problem arising in nuclear Configuration Interaction (CI) calculations, where a few extreme eigenpairs of a sparse symmetric matrix are needed. Here, we consider a block iterative eigensolver whose main computational kernels are the multiplication of a sparse matrix with multiple vectors (SpMM), and tall-skinny matrix operations. We then present techniques to significantly improve the SpMM and the transpose operation SpMM T by using the compressed sparse blocks (CSB) format. We achieve 3-4× speedup on the requisite operations over good implementations with the commonly used compressed sparse row (CSR) format. We develop a performance model that allows us to correctly estimate the performance of our SpMM kernel implementations, and we identify cache bandwidth as a potential performance bottleneck beyond DRAM. We also analyze and optimize the performance of LOBPCG kernels (inner product and linear combinations on multiple vectors) and show up to 15× speedup over using high performance BLAS libraries for these operations. The resulting high performance LOBPCG solver achieves 1.4× to 1.8× speedup over the existing Lanczos solver on a series of CI computations on high-end multicore architectures (Intel Xeons). We also analyze the performance of our techniques on an Intel Xeon Phi Knights Corner (KNC) processor.

97 MATHEMATICS AND COMPUTING↗

Atomic-Scale Imaging of Polarization Switching in an (Anti-)Ferroelectric Memory Material: Zirconia (ZrO2)

Direct, atomic-scale visualization of polarization switching in a functional, polycrystalline, binary oxide via in-situ high-resolution transmission electron microscopy (HRTEM) biasing is reported for the first time. Antiferroelectric (AFE) ZrO2 was used as the model system, which is important for commercial DRAMs and as emerging NVMs (through work-function engineering). We observed (1) clear shifting and coalescing of domains within a single grain, and (2) dramatic changes of the atomic arrangements and crystalline phases—both at voltages above the critical voltage measured for AFE switching. Similar synergistic in-situ structural-electrical characterization can pave the way to understand and engineer microscopic mechanisms for retention, fatigue, variability, sub-coercive switching and analog states in ferroelectric and AFE-based memory devices.

Lombardo, Sarah↗