Chao Li

Chao Li

Auto-generated profile, based on publicly available information

Chao Li

Institute of Applied Mathematics, Shangluo University, Shangluo, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2014
Verified
Conference Paper
Closed access
CLChao Li
Chao Li
YYYi Yang
Yi Yang
HDHongwen Dai
Hongwen Dai
SYShengen Yan
Shengen Yan
FMFrank Mueller
Frank Mueller
HZHuiyang Zhou
Huiyang Zhou
On-chip caches are commonly used in computer systems to hide long off-chip memory access latencies. To manage on-chip caches, either software-managed or hardware-managed schemes can be employed. State-of-art accelerators, such as the NVIDIA Fermi or Kepler GPUs and Intel's forthcoming MIC “Knights Landing” (KNL), support both software-managed caches, aka. shared memory (GPUs) or near memory (KNL), and hardware-managed L1 data caches (D-caches). Furthermore, shared memory and the L1 D-cache on a GPU utilize the same physical storage and their capacity can be configured at runtime (same for KNL). In this paper, we present an in-depth study to reveal interesting and sometimes unexpected tradeoffs between shared memory and the hardware-managed L1 D- caches in GPU architecture. In our study, the kernels utilizing the L1 D-caches are generated from those leveraging shared memory to ensure that the same optimizations such as tiling are applied equally in both versions. Our detailed analyses reveal that rather than cache hit rates, the following tradeoffs often have more profound performance impacts. On one hand, the kernels utilizing the L1 caches may support higher degrees of thread-level parallelism, offer more opportunities for data to be allocated in registers, and sometimes result in lower dynamic instruction counts. On the other hand, the applications utilizing shared memory enable more coalesced accesses and tend to achieve higher degrees of memory-level parallelism. Overall, our results show that most benchmarks perform significantly better with shared memory than the L1 D-caches due to the high impact of memory-level parallelism and memory coalescing.

23 September 2025 in Iranian Journal of Science
Verified
Journal Article
Closed access
PDF file
LKLiang Kong
Liang Kong
CLChao Li
Chao Li

26 September 2021 in Symmetry
Verified
Journal Article
Open access
PDF file
DZDonghan Zhang
Donghan Zhang
CLChao Li
Chao Li
FCFugang Chao
Fugang Chao
A proper total k-coloring ϕ of G with ∑z∈EG(u)∪{u}ϕ(z)≠∑z∈EG(v)∪{v}ϕ(z) for each uv∈E(G) is called a total neighbor sum distinguishing k-coloring, where EG(u)={uv|uv∈E(G)}. Pilśniak and Woźniak conjectured that every graph with maximum degree Δ exists a total neighbor sum distinguishing (Δ+3)-coloring. In this paper, we proved that any IC-planar graph with Δ≥12 satisfies this conjecture, which improves the result of Song and Xu.

1 January 2025 in Filomat
Verified
Journal Article
Open access
LKLiang Kong
Liang Kong
CLChao Li
Chao Li
Let A be a unital prime *-algebra containing a nontrivial projection and ? be a nonzero scalar. We prove that a map ? : A ? A satisfies ?([A, B]? ?) = [?(A), B]? ? + [A,?(B)]? ? for all A, B ? A if and only if ? is an additive ?-derivation and ?(?A) = ??(A) for all A ? A, where [A, B]? ? = AB? ? ?BA?.

1 January 2025 in Journal of Mathematics
Verified
Journal Article
Open access
LKLiang Kong
Liang Kong
CLChao Li
Chao Li
Let be a unital ∗‐algebra with the unit I and be the symmetric center of . Assume that contains a nontrivial projection P such that implies A = 0 and implies A = 0. In this paper, we proved that if a map satisfies [ φ ( A ), B ] ∗ = −[ φ ( B ), A ] ∗ for all , then there exists a map such that φ ( A ) = Z A + f ( A ) for all , where . As applications, we obtain the concrete form of nonadditive skew commuting maps on prime ∗‐algebra, factor von Neumann algebras and standard operator algebras.