Thread-level speculation (TLS) allows potentially dependent threads to speculatively execute in parallel, thus making it easier for the compiler to extract parallel threads. Howeve...
Abstract--Multimedia and DSP applications have several computationally intensive kernels which are often offloaded and accelerated by application-specific hardware. This paper pres...
Sejong Oh, Tag Gon Kim, Jeonghun Cho, Elaheh Bozor...
With billion-transistor chips on the horizon, single-chip multiprocessors (CMPs) are likely to become commodity components. Speculative CMPs use hardware to enforce dependence, al...
Troy A. Johnson, Rudolf Eigenmann, T. N. Vijaykuma...
For some sequential loops, existing techniques that form speculative threads only at their loop boundaries do not adequately expose the speculative parallelism inherent in them. T...
Lin Gao 0002, Lian Li 0002, Jingling Xue, Tin-Fook...
While architects understandhow to build cost-effective parallel machines across a wide spectrum of machine sizes (ranging from within a single chip to large-scale servers), the re...
J. Gregory Steffan, Christopher B. Colohan, Antoni...