Matthias Hartmann

A multi-threaded coarse-grained array processor for wireless baseband

Throughput of wireless communication standards ever increases. Computation requirements for systems implementing those standards increase even more. On battery operated devices, next to high performance a low power implementation is also crucial. Reaching this is only possible by utilizing parallelizations at all levels. The ADRES processor is an embedded coarse-grained reconfigurable baseband processor that already could exploit Data Level Parallelism (DLP), Instruction Level Parallelism (ILP) efficiently. In this paper we present extensions to ADRES to also exploit Task Level Parallelism (TLP) efficiently. We show how we reduce the overhead in communication and synchronization between tasks and demonstrate this on a mapping of an 802.11n 300Mbps standard.

Still Image Processing on Coarse-Grained Reconfigurable Array Architectures

Due to the increasing demands on efficiency, performance and flexibility reconfigurable computational architectures are very promising candidates in embedded systems design. Recently coarse-grained reconfigurable array architectures (CGRAs), such as the ADRES CGRA and its corresponding DRESC compiler are gaining more popularity due to several technological breakthroughs in this area. We investigate the mapping of two image processing algorithms, Wavelet encoding and decoding, and TIFF compression on this novel type of array architectures in a systematic way. The results of our experiments show that CGRAs based on ADRES and its DRESC compiler technology deliver improved performance levels for these two benchmark applications when compared to results obtained on a state-of-the-art commercial DSP platform, the c64x DSP from Texas Instruments. ADRES/DRESC can beat its performance by at least 50% in cycle count and the power consumption even drops to 10% of the published numbers of the c64x DSP.

Memristor-Based (ReRAM) Data Memory Architecture in ASIP Design

Recently, multiple non-volatile emerging memories (NVMs) have been proposed and show promising properties to replace SRAM-based memories in future SoCs. However, these new emerging memories, such as STT-MRAM and ReRAM, provide new challenges for the processor design e.g. larger write latencies, higher power and lower endurance. In this paper, we propose a design method for memristor-based (ReRAM) memory architectures for embedded processors to address the effects caused by longer write latencies. We evaluate this method and present the design space for using ReRAM in the data memory of an wireless base band processor. We propose architectural solutions for concealing the slow write speed of ReRAM and show their trade-offs in terms of performance with respect to different write latencies. We show that for single benchmarks the performance penalty caused by the ReRAM write latency can be reduced to 7% for the complete wireless communication benchmark suite. Morevoer, for single benchmarks the performance penalty can be eliminated completely.

Feasibility exploration of NVM based I-cache through MSHR enhancements

SRAM based memory systems are plagued by a number of problems like sub-threshold leakage and susceptibility to read/write failure with dynamic voltage scaling schemes or low supply voltage. Non-Volatile Memory (NVM) technologies are being explored extensively nowadays to replace the conventional SRAM memories even for level 1 (L1) caches. These NVMs like Spin Torque Transfer RAM (STT-MRAM), Resistive-RAM (ReRAM) and Phase Change RAM (PRAM) are less hindered by leakage problems with technology scaling and consume lesser area. However, simple replacement of SRAM by NVMs is not a viable option due to their write related issues. The main focus of this paper is the exploration of write delay and write energy issues in a NVM based L1 Instruction cache (I-cache) for an ARM like single core system. We propose a NVM I-cache and extend its MSHR (Miss Status Handling Register) functionality to address the NVMs write related issues. According to our simulations, appropriate tuning of selective architecture parameters can reduce the performance penalty introduced by the NVM (~45%) to extremely tolerable levels (~1%) and show energy gains up to 35%. Furthermore, on configuring our modified NVM based system to occupy area comparable to the original SRAM-based configuration, it outperforms the SRAM baseline and leads to even more energy savings.

Micro-architectural optimization of a coarse-grained array based baseband processor

Software Defined Radios (SDR) has been introduced as the ultimate way to achieve the flexibility that is needed to cope with the many emerging wireless standards. A key challenge in the implementation of such radios for mobile terminals is meeting the performance and energy requirements. A suitable architecture template is the first requirement, but finding the optimal instance is as important. This paper shows that it is possible to half the power consumption of an already very energy efficient baseband processor by doing micro-architectural improvements. Overall a 2.6× improvement in energy efficiency and a 2.0× improvement in power consumption has been achieved, resulting in an average power consumption for the baseband processing of 108mW.

Algorithm-Architecture Co-Optimization of Area-Efficient SDR Baseband for Highly Diversified Digital TV Standards

The rapidly evolving and diversifying wireless landscape demands highly flexible wireless chipsets. Due to the ultimate programmability, SDR solutions are becoming more and more attractive. However, the programmability overhead is still a concern for the silicon area cost of SDR solutions. In this work, we prove that, with algorithm and architecture co- design, SDR solutions can be very competitive even when compared to highly optimized ASICs. Specifically, we show a baseband processor design that can support ISDB-T, DVB-T and ATSC, but the area cost is still comparable to the combination of ASICs which handle the three terrestrial digital TV standards respectively.

Modelling and mitigation of time-zero variability in sub-16nm finfet-based STT-MRAM memories

Spin-transfer torque magnetic RAM (STT-MRAM) is one of the most promising non-volatile memory technologies and shows potential as an SRAM replacement. However, targeted for advanced CMOS technologies such as the 14nm FinFET node, time-zero variability is a major concern for these memory technologies. In this paper, we investigate the STT-MRAM variability with respect to different technology scenarios. We show the impact of these variations on the bit error rate of the emerging STT-MRAM memories.