Scratchpad memory

Abstract: In this paper we address the problem of on-chip memory selection for computationally intensive applications, by proposing scratch pad memory as an alternative to cache. Area and energy for different scratch pad and cache sizes are computed using the CACTI tool while performance was evaluated using the trace results of the simulator. The target processor chosen for evaluation was AT91M40400. The results clearly establish scratehpad memory as a low power alternative in most situations with an average energy reducation of 40%. Further the average area-time reduction for the seratchpad memory was 46% of the cache memory.

Abstract: The number of embedded systems is increasing and a remarkable percentage is designed as mobile applications. For the latter, energy consumption is a limiting factor because of today's battery capacities. Besides the processor, memory accesses consume a high amount of energy. The use of additional less power hungry memories like caches or scratchpads is thus common. Caches incorporate the hardware control logic for moving data in and out automatically. On the other hand, this logic requires chip area and energy. A scratchpad memory is much more energy efficient, but there is a need for software control of its content. In this paper, an algorithm integrated into a compiler is presented which analyses the application and selects program and data parts which are placed into the scratchpad. Comparisons against a cache solution show remarkable advantages between 12% and 43% in energy consumption for designs of the same memory size.

Abstract: Optimizations aimed at improving the efficiency of on-chip memories are extremely important. We propose a compiler-controlled dynamic on-chip scratch-pad memory (SPM) management framework that uses both loop and data transformations. Experimental results obtained using a generic cost model indicate significant reductions in data transfer activity between SPM and off-chip memory.

Abstract: This paper presents a highly predictable, low overhead and yet dynamic, memory allocation strategy for embedded systems with scratch-pad memory. A scratch-pad is a fast compiler-managed SRAM memory that replaces the hardware-managed cache. It is motivated by its better real-time guarantees vs cache and by its significantly lower overheads in energy consumption, area and overall runtime, even with a simple allocation scheme [4].Existing scratch-pad allocation methods are of two types. First, software-caching schemes emulate the workings of a hardware cache in software. Instructions are inserted before each load/store to check the software-maintained cache tags. Such methods incur large overheads in runtime, code size, energy consumption and SRAM space for tags and deliver poor real-time guarantees just like hardware caches. A second category of algorithms partitionsm variables at compile-time into the two banks. For example, our previous work in [3] derives a provably optimal static allocation for global and stack variables and achieves a speedup over all earlier methods. However, a drawback of such static allocation schemes is that they do not account for dynamic program behavior. It is easy to see why a data allocation that never changes at runtime cannot achieve the full locality benefits of a cache.In this paper we present a dynamic allocation method for global and stack data that for the first time, (i) accounts for changing program requirements at runtime (ii) has no software-caching tags (iii) requires no run-time checks (iv) has extremely low overheads, and (v) yields 100% predictable memory access times. In this method data that is about to be accessed frequently is copied into the SRAM using compiler-inserted code at fixed and infrequent points in the program. Earlier data is evicted if necessary. When compared to a provably optimal static allocation our results show runtime reductions ranging from 11% to 38%, averaging 31.2%, using no additional hardware support. With hardware support for pseudo-DMA and full DMA, which is already provided in some commercial systems, the runtime reductions increase to 33.4% and 34.2% respectively.

Abstract: In this research, we propose a highly predictable, low overhead, and, yet, dynamic, memory-allocation strategy for embedded systems with scratch pad memory. A scratch pad is a fast compiler-managed SRAM memory that replaces the hardware-managed cache. It is motivated by its better real-time guarantees versus cache and by its significantly lower overheads in energy consumption, area, and overall runtime, even with a simple allocation scheme. Primarily scratch pad allocation methods are of two types. First, software-caching schemes emulate the workings of a hardware cache in software. Instructions are inserted before each load/store to check the software-maintained cache tags. Such methods incur large overheads in runtime, code size, energy consumption, and SRAM space for tags and deliver poor real-time guarantees just like hardware caches. A second category of algorithms partitions variables at compile-time into the two banks. However, a drawback of such static allocation schemes is that they do not account for dynamic program behavior. It is easy to see why a data allocation that never changes at runtime cannot achieve the full locality benefits of a cache. We propose a dynamic allocation methodology for global and stack data and program code that; (i) accounts for changing program requirements at runtime, (ii) has no software-caching tags, (iii) requires no runtime checks, (iv) has extremely low overheads, and (v) yields 100p predictable memory access times. In this method, data that is about to be accessed frequently is copied into the scratch pad using compiler-inserted code at fixed and infrequent points in the program. Earlier data is evicted if necessary. When compared to a provably optimal static allocation, results show that our scheme reduces runtime by up to 39.8p and energy by up to 31.3p, on average, for our benchmarks, depending on the SRAM size used. The actual gain depends on the SRAM size, but our results show that close to the maximum benefit in runtime and energy is achieved for a substantial range of small SRAM sizes commonly found in embedded systems. Our comparison with a direct mapped cache shows that our method performs roughly as well as a cached architecture.