Matching Items (2)
Filtering by
- All Subjects: Storage
- Creators: Armendariz Guajardo, Jose
- Creators: Chakrabariti, Chaitali
Description
The Resistive Random Access Memory (ReRAM) is an emerging non-volatile memory
technology because of its attractive attributes, including excellent scalability (< 10 nm), low
programming voltage (< 3 V), fast switching speed (< 10 ns), high OFF/ON ratio (> 10),
good endurance (up to 1012 cycles) and great compatibility with silicon CMOS technology [1].
However, ReRAM suffers from larger write latency, energy and reliability issue compared to
Dynamic Random Access Memory (DRAM). To improve the energy-efficiency, latency efficiency and reliability of ReRAM storage systems, a low cost cross-layer approach that spans device, circuit, architecture and system levels is proposed.
For 1T1R 2D ReRAM system, the effect of both retention and endurance errors on
ReRAM reliability is considered. Proposed approach is to design circuit-level and architecture-level techniques to reduce raw Bit Error Rate significantly and then employ low cost Error Control Coding to achieve the desired lifetime.
For 1S1R 2D ReRAM system, a cross-point array with “multi-bit per access” per subarray
is designed for high energy-efficiency and good reliability. The errors due to cell-level as well
as array-level variations are analyzed and a low cost scheme to maintain reliability and latency
with low energy consumption is proposed.
For 1S1R 3D ReRAM system, access schemes which activate multiple subarrays with
multiple layers in a subarray are used to achieve high energy efficiency through activating fewer
subarray, and good reliability is achieved through innovative data organization.
Finally, a novel ReRAM-based accelerator design is proposed to support multiple
Convolutional Neural Networks (CNN) topologies including VGGNet, AlexNet and ResNet.
The multi-tiled architecture consists of 9 processing elements per tile, where each tile
implements the dot product operation using ReRAM as computation unit. The processing
elements operate in a systolic fashion, thereby maximizing input feature map reuse and
minimizing interconnection cost. The system-level evaluation on several network benchmarks
show that the proposed architecture can improve computation efficiency and energy efficiency
compared to a state-of-the-art ReRAM-based accelerator.
technology because of its attractive attributes, including excellent scalability (< 10 nm), low
programming voltage (< 3 V), fast switching speed (< 10 ns), high OFF/ON ratio (> 10),
good endurance (up to 1012 cycles) and great compatibility with silicon CMOS technology [1].
However, ReRAM suffers from larger write latency, energy and reliability issue compared to
Dynamic Random Access Memory (DRAM). To improve the energy-efficiency, latency efficiency and reliability of ReRAM storage systems, a low cost cross-layer approach that spans device, circuit, architecture and system levels is proposed.
For 1T1R 2D ReRAM system, the effect of both retention and endurance errors on
ReRAM reliability is considered. Proposed approach is to design circuit-level and architecture-level techniques to reduce raw Bit Error Rate significantly and then employ low cost Error Control Coding to achieve the desired lifetime.
For 1S1R 2D ReRAM system, a cross-point array with “multi-bit per access” per subarray
is designed for high energy-efficiency and good reliability. The errors due to cell-level as well
as array-level variations are analyzed and a low cost scheme to maintain reliability and latency
with low energy consumption is proposed.
For 1S1R 3D ReRAM system, access schemes which activate multiple subarrays with
multiple layers in a subarray are used to achieve high energy efficiency through activating fewer
subarray, and good reliability is achieved through innovative data organization.
Finally, a novel ReRAM-based accelerator design is proposed to support multiple
Convolutional Neural Networks (CNN) topologies including VGGNet, AlexNet and ResNet.
The multi-tiled architecture consists of 9 processing elements per tile, where each tile
implements the dot product operation using ReRAM as computation unit. The processing
elements operate in a systolic fashion, thereby maximizing input feature map reuse and
minimizing interconnection cost. The system-level evaluation on several network benchmarks
show that the proposed architecture can improve computation efficiency and energy efficiency
compared to a state-of-the-art ReRAM-based accelerator.
ContributorsMao, Manqing (Author) / Chakrabariti, Chaitali (Thesis advisor) / Yu, Shimeng (Committee member) / Cao, Yu (Committee member) / Orgas, Umit (Committee member) / Arizona State University (Publisher)
Created2019
Description
Capsaicin and dihydrocapsaicin account for 90% of capsaicinoids when it comes to the pungency of peppers. Capsaicin stability was investigated through a cooking and storage parameter where three different tests were done; cooking duration, cooking temperature, and storage stability. The concentration of capsaicinoids was quantified through gas chromatography-mass spectrometry where those values were then used to determine the total Scoville heat units (SHU). Furthermore, half-life was determined by finding the decay rate during cooking and storage. Results showed that there was an increase in degradation of capsaicinoids concentration when peppers were cooked for a long period of time. Degradation rate increases with increasing temperatures as would be expected by the Arrhenius equation. Hence, if a maximum pungency is wanted, it is best to cook the least time as possible or add the peppers towards the end of the culinary technique. This would help by cooking the peppers for a short period of time while not being exposed to the high temperature long enough before significant degradation occurs. Lastly, the storage stability results interpreted that a maximum potency of the peppers can be retained in a freezer or refrigerator opposed to an open room temperature environment or exposure from the sun. Furthermore, the stability of peppers has a long shelf life with even that the worse storage condition's half-life value was 113.5 months (9.5 years). Thus, peppers do not need to be bought frequently because its potency will last for several years.
ContributorsBustamante, Krista Gisselle (Author) / Cahill, Thomas (Thesis director) / Sweat, Ken (Committee member) / Armendariz Guajardo, Jose (Committee member) / School of Mathematical and Natural Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2017-12