• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.75-81
• /
• 2016

This paper proposes a design of the tile based on graphic pipeline to improve the graphic application performance in SIMT based GP-GPU. The proposed Tile based on graphics pipeline avoids unnecessary graphic processing operation, and processes the rasterization step in parallel. The massive data processing in parallel through SIMT architecture improve the computational performance, thereby improving the 3D graphic pipeline performance. The more vertex data of 3D model, the higher performance. The proposed structure was confirmed to improve processing performance of up to 3 times from about 1.18 times as compared to 'RAMP' and previous studies.

• Structural Engineering and Mechanics
• /
• v.22 no.5
• /
• pp.563-574
• /
• 2006

This paper studies mechanical behavior of the superelastic shape memory alloy (SMA) rods in terms of local deformations and time via tensile loading-unloading cycles for both ends fixed end constraints. Besides the unique stress induced martensitic transformation (SIMT), SMA's time dependent behavior when it is in mixed-phase condition upon loading and unloading, also need careful attention with a view of investigating the local deformation of the structural elements made of the same material. With this perspective, the so-called stress-relaxation tests have been performed to demonstrate and investigate the local strains-total strains relationships with time, particularly, during the forward SIMT. Some remarkable phenomena have been observed pertaining to SIMT, which are absent in traditional materials and those unique phenomena have been explained qualitatively. For example, at the stopped loading conditions the two ends (fixed end and moving end of the tensile testing machine) were in fixed positions. So that there was no axial overall deformation of the specimen but some notable increase in the axial local deformation was shown by the extensometer placed at the middle of the SMA specimen. It should be noted that this peculiar behavior termed as 'inertia driven SIMT' occurs only when the loading was stopped at mixed phase condition. Besides this relaxation test for the SMA specimens, the same is performed for the mild steel (MS) specimens under similar test conditions. The MS specimens, however, show no unusual increase of local strains during the stress relaxation tests.

• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.89-93
• /
• 2016

In this paper, we proposed SIMT based Image Signal Processor which can apply various image preprocessing algorithms and allow parallel processing of application programs such as image recognition. Conventional ISP has the hard-wired image enhancement algorithm of which the processing speed is fast, but there was difficult to optimize performance depending on various image processing algorithms. The proposed ISP improved the processing time applying SIMT architecture and processed a variety of image processing algorithms as an instruction based processor. We used Xilinx Virtex-7 board and the processing time compared to cell multicore processor, ARM Cortex-A9, ARM Cortex-A15 was reduced by about 71 percent, 63 percent and 33 percent, respectively.

• Journal of IKEEE
• /
• v.18 no.3
• /
• pp.392-397
• /
• 2014

In this paper, we propose a memory operation system architecture for memory latency penalty reduction in SIMT architecture based stream processor. The proposed architecture applied non-blocking cache architecture to reduce cache miss penalty generated by blocking cache architecture. We verified that the proposed memory operation architecture improve the performance of the stream processor by comparing processing performances of various algorithms. We measured the performance improvement rate that was improved in accordance with the ratio of memory instruction in each algorithm. As a result, we confirmed that the performance of stream processor improves up to minimum 8.2% and maximum 46.5%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.540-543
• /
• 2013

This paper describes an implementation of a unified ALU on multi-core GPGPU based on SIMT architecture. Our unified ALU can operate conditional branch instructions, data movement instructions, integer arithmetic instructions and floating-point arithmetic instructions. Since multi-core GPGPU contains a lot of ALU for parallel processing of various types, the main point of this paper is to design the minimum size ALU by unifying similar processing of each operations on circit level. All instrunctions were tested by making a test program. And we compare this results with results of CPU operations to verify our ALU. Our unified ALU's gate size is approximately 20,000 and the maximum operation frequency is 430MHz.

• Journal of IKEEE
• /
• v.21 no.3
• /
• pp.276-279
• /
• 2017

In this paper, SIMT structure based GPGPU (General Purpose Computing on Graphics Processing Units) is used for accelerating the Rasterizer which constitutes the screen of the display device in pixel unit. The GPU has a large number of ALUs, and the processing is very fast because of parallel processing. Therefore, in this paper, we implemented a rasterizer that generates a 3D graphics model using a CPU that performs operations sequentially and a GPU that performs operations in parallel. We confirmed that proposed rasterizer in this paper is 1.45 times better than rasterizer using Intel CPU when generating one frame.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.479-484
• /
• 2021

This paper proposed and designed a structure to achieve high performance with a small number of cores in GPGPU with SIMT structure. GPGPU for application to mobile devices requires a structure to increase performance compared to power consumption. In order to reduce power consumption, the number of cores decreased, but to improve performance, the size of the warp scheduler for managing threads was set to 4, which was greatly reduced than 32 of general GPGPU. Reducing warp size can reduce the number of idle cycles in pipelines and efficiently apply memory latency to reduce miss penalty when accessing cache memory. The designed GPGPU measured computational performance using a test program that includes floating point operations and measured power consumption through a 28nm CMOS process to obtain 104.5GFlops/Watt as a performance per power. The results of this paper showed about four times better performance per power compared to Tegra K1 of Nvidia

• Journal of IKEEE
• /
• v.19 no.3
• /
• pp.455-459
• /
• 2015

This paper proposes a dispatch unit of GP-GPU with SIMT architecture to support the acceleration of general-purpose operation as well as graphics processing. If all the information of an operand used instructions issued from the warp scheduler is decoded, an unnecessary operand load occurs, resulting in register loads. To resolve this problem, this paper proposes a method that can reduce the operand load and the load on the resister by decoding only the information of the operand using a pre-decoding method. The operand information from the dispatch unit is passed to the operand selection unit with preventing register bank collisions. Thus the overall performance are improved. In the simulation test, the total clock cycles required by processing 10,000 arbitrary instructions issued from the wrap scheduler using ModelSim SE 10.0b are measured. It shows that the application of the dispatch unit equipped with the pre-decoding function proposed in this paper can make an improvement of about 12% in processing performance compared to the conventional method.

• International Journal of Advanced Culture Technology
• /
• v.4 no.4
• /
• pp.30-37
• /
• 2016

In this paper, the method of controlling the clock that is inputted on the hardware from the application, and the hardware design method are to be proposed. When the hardware is synthesized to the Field Programmable Gate Array(FPGA), the input clock is fixed, and when the input clock is changed, the synthesis process must be passed again to require more time. To solve this problem, the Mixed-Mode Clock Manager(MMCM) module is mounted to control the MMCM module from the application. The controlled MMCM module controls the input clock of the module. The experiment was process the Neural Network algorithm in the x86 CPU and SIMT based processor mounted the FPGA. The results of the experiment, SIMT-based processors, the time that is processed at a frequency of 50MHz was 77ms, 100MHz was 34ms. There was no additional synthesis time due to a change of the clock frequency.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.664-671
• /
• 2021

This paper proposes a GPGPU structure that can reduce the number of operations and memory access by effectively applying a data reuse method to a convolutional neural network(CNN). Convolution is a two-dimensional operation using kernel and input data, and the operation is performed by sliding the kernel. In this case, a reuse method using an internal register is proposed instead of loading kernel from a cache memory until the convolution operation is completed. The serial operation method was applied to the convolution to increase the effect of data reuse by using the principle of GPGPU in which instructions are executed by the SIMT method. In this paper, for register-based data reuse, the kernel was fixed at 4×4 and GPGPU was designed considering the warp size and register bank to effectively support it. To verify the performance of the designed GPGPU on the CNN, we implemented it as an FPGA and then ran LeNet and measured the performance on AlexNet by comparison using TensorFlow. As a result of the measurement, 1-iteration learning speed based on AlexNet is 0.468sec and the inference speed is 0.135sec.