• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.12
• /
• pp.1575-1579
• /
• 1999

Embedded processors often accommodate two instruction sets, a standard instruction set and a compressed instruction set. With the compressed instruction set, code size can be reduced while instruction count (and consequently execution time) can be increased. To achieve code size reduction without significant increase of execution time, this paper proposes a new compressed instruction set architecture, called TOE (Two Operations Execution). The proposed instruction set format includes the parallel bit that indicates an instruction can be executed simultaneously with the next instruction. To add the parallel bit, TOE instruction format reduces the destination register field. The reduction of the register field limits the number of registers that are accessible by an instruction. To overcome the limited accessibility of registers, TOE adapts non-homogeneous register partition in which registers are divided into multiple subsets, each of which are accessed by different groups of instructions. With non-homogeneous registers, each instruction can access only a limited number of registers, but an entire program can access all available registers. With efficient non-homogeneous register allocator, all registers can be used in a balanced manner. As a result, the increase of code size due to register spills is negligible. Experimental results show that more than 30% of TOE instructions can be executed in parallel without significant increase of code size when compared to existing Thumb instruction set.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.819-833
• /
• 2005

Code size reduction is ever becoming more important for compilers targeting embedded processors because these processors are often severely limited by storage constraints and thus the reduced code size can have a positively significant Impact on their performance. Various code size reduction techniques have different motivations and a variety of application contexts utilizing special hardware features of their target processors. In this work, we propose a novel technique that fully utilizes a set of hardware instructions, called the multiple load/store (MLS), that are specially featured for reducing code size by minimizing the number of memory operations in the code. To take advantage of this feature, many microprocessors support the MLS instructions, whereas no existing compilers fully exploit the potential benefit of these instructions but only use them for some limited cases. This is mainly because optimizing memory accesses with MLS instructions for general cases is an NP-hard problem that necessitates complex assignments of registers and memory off-sets for variables in a stack frame. Our technique uses a couple of heuristics to efficiently handle this problem in a polynomial time bound.

• Journal of KIISE
• /
• v.43 no.1
• /
• pp.34-39
• /
• 2016

JavaScript is widely used in web pages with HTML. Many JavaScript engines adopt Just-in-time compilers to accelerate the execution of JavaScript programs. Recently, many newly introduced devices are adopting 64-bit CPUs instead of 32-bit and Just-in-time compilers for 64-bit CPU are slowly being introduced in JavaScript engines. However, there are many inefficiencies in the currently available Just-in-time compilers for 64-bit devices. Especially, the size of code is significantly increased compared to 32-bit devices, mainly due to 64-bit wide addresses in 64-bit devices. In this paper, we are going to address the inefficiencies introduced by 64-bit wide addresses and values in the Just-in-time compiler for the V8 JavaScript engine and propose more efficient ways of generating constant values and addresses to reduce the size of code. We implemented the proposed optimization in the V8 JavaScript engine and measured the size of code as well as performance improvements with Octane and SunSpider benchmarks. We observed a 3.6% performance gain and 0.7% code size reduction in Octane and a 0.32% performance gain and 2.8% code size reduction in SunSpider.

• Journal of ILASS-Korea
• /
• v.15 no.4
• /
• pp.170-176
• /
• 2010

This paper describes the grid-size dependency of the conventional Eulerian-Lagrangian method to spray characteristics such as spray penetration and SMD in modeling DME sprays. In addition, the reduction of the grid-size dependency of the present Gas-jet model was investigated. The calculations were performed using the KIVA code and the calculated results were compared to those of experimental result. The results showed that the conventional Eulerian-Laglangian model predicts shorter spray penetration for large cell because of inaccurate calculation of momentum exchange between liquid and gas phase. However, it was shown that the gas-jet model reduced grid-size dependency to spray penetration by calculating relative velocity between liquid and ambient gas based on gas jet velocity.

• Journal of KIISE:Software and Applications
• /
• v.32 no.3
• /
• pp.227-235
• /
• 2005

In the embedded system domain, both memory requirement and energy consumption are great concerns. To save memory and energy, the 32 bit ARM processor supports the 16 bit Thumb instruction set. For a given program, the Thumb code is typically smaller than the ARM code. However, the limitations of the Thumb instruction set can often lead to generation of poorer quality code. To generate codes with smaller size but a little slower execution speed, Krishnaswarmy suggests a profiling guided selection algorithm at module level for generating mixed ARM and Thumb codes for application programs. The resulting codes of the algorithm give significant code size reductions with a little loss in performance. When the instruction set is selected at module level, some functions, which should be compiled in Thumb mode to reduce code size, are compiled to ARM code. It means we have additional code size reduction chance. In this paper, we propose a profile guided selection algorithm at function level for generating mixed ARM and Thumb codes for application programs so that the resulting codes give additional code size reductions without loss in performance compared to the module level algorithm. We can reduce 2.7％ code size additionally with no performance penalty

• ETRI Journal
• /
• v.39 no.3
• /
• pp.319-325
• /
• 2017

The decoding process of a quasi-cyclic low-density parity check code requires a unique type of rotator. These rotators, called multi-size cyclic-shifters (MSCSs), rotate input data with various sizes, where the size is the amount of data to be rotated. This paper proposes a low-complexity MSCS structure for the case when the sizes have a nontrivial common divisor. By combining the strong points of two previous structures, the proposed structure achieves the smallest area. The experimental results show that the area reduction was more than 14.7% when the proposed structure was applied to IEEE 802.16e as an example.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.11-23
• /
• 2012

To achieve efficient code size reduction, this paper proposes a new compressed instruction set architecture for the OpenRISC architecture. The new instructions and their corresponding formats are designed by the profiling information of the existing instruction usage. New 16-bit instructions and 32-bit instructions are proposed to compressed the existing 32-bit instructions and instruction sequences, respectively. The proposed instructions can be classified into three types. The first is the new 16-bit instructions for the frequent normal 32-bit instructions such as add, load, store, branch, and jump instructions. The second type is the new 32-bit instructions for the consecutive two load instructions, two store instructions, and 32-bit data mov instructions. Finally, two new 32-bit instructions are proposed to compress function prolog and epilog code, respectively. OpenRISC hardware decoder is extended to support the new instructions. Experiments show that the efficiency of code size reduction improves by an average of 30.4% when compared to the OR1200 instruction set architecture without loss of execution performance.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.4
• /
• pp.83-90
• /
• 2004

In this paper, we proposed a new instruction set(X32Y ISA) with 3 different types of instruction mode. The proposed instruction set organizes 32-bit, 24-bit, 16-bit instruction in order to solves a problem of memory size limitation in an embedded microprocessor. We designed a 32-bit 5 stage pipeline RISC microprocessor based on the X32V ISA. To verify the proposed the X32V ISA and a microprocessor, we estimated a program code size of multimedia application programs using a X32V simulator. In result, we verified that the Light mode and the Ultra Light mode obtains 8%, 27% reduction of a program code size through comparison with the Default mode. The proposed microprocessor was verified all X32V instructions execution at Xilinx FPGA with 33MHz operating frequency,

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.228-231
• /
• 1999

This paper describes the design and implementation of an application specific instruction-set processor developed for embedded DSP applications. The instruction-set has an uniform size of 16 bits, and supports 3 types of instructions: Primitive, Complex, and Specific. To reduce code size and cycle count we introduce complex instructions that can be selected according to the application under consideration, which leads to 50% code size reduction maximally. The processor has two independent data memories to double the data throughput and the address space. The processor is synthesized by 0.6$\mu$m single-poly double-metal technology. Critical path simulation shows that the maximum frequency is 110MHz and total gate count is 132, 000.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2003.05a
• /
• pp.878-883
• /
• 2003

To modify some problems of ACI shear provisions, ultimate shear strength equation considering size effect and arch action to compute shear strength in high-strength concrete beams without stirrups is presented in this research. Three basic equations, namely size reduction factor, rho factor, and arch action factor, are derived from crack band model of fracture mechanics, analysis of previous some shear equations for longitudinal reinforcement ratio, and concrete strut described as linear function in deep beams. Constants of basic equations are determined using statistical analysis of previous shear testing data. To verify proposed shear equation for each variable, namely d, , ρ, f/sub c/' and aid, about 250 experimental data are used and proposed shear equation is compared with ACI 318-99 code, CEB-FIP Model code, Kim & Park's equation and Zsutty's equation. While proposed shear equation is simpler than other shear equations, it is shown to be economical predictions and reasonable safety margin. Hence proposed shear strength equation is expected to be applied to practice shear design.