Automatically Identifying and Creating Accelerators Directly from C Code
نویسنده
چکیده
Let’s say that you have been tasked to ensure that your company has an H.264 solution that supports high-definition video decoding at 30 frames per second. You are not a video expert. What do you do? You could get on the Internet and perform a Web search for H.264; before you know it, you’ll have the source code and be on your way. You managed to compile the code and get it running on the target, but it decodes at a whopping two frames per second. Now what? After sifting through pages and pages of profiling data, you find some hotspots, but you are not sure which parts to focus on to maximize the acceleration and you do not have enough time to try to optimize them all. Many of us have found ourselves in this situation at one time or another. Maybe you have even delivered a solution, but not without a lot of sweat and tears.
منابع مشابه
PerfExpert and MACPO: Which code segments should (not) be ported to MIC?
Accelerators like Graphics Processing Units (GPUs) or coprocessors like Intel’s MIC (Many Integrated Core) provide means to exploit large-scale SIMT/SIMD parallelism in applications. Tools for converting CPU code to code for accelerators/coprocessors are available. Application developers could quickly exploit these accelerators/coprocessors with modest effort if they could identify the code seg...
متن کاملDevelopment of a Phase Space Generator software for Medical Linear Accelerator Applications
Introduction: During the last decades, simulation of radiation therapy treatment conditions in treatment room for studying with more details in comparison with treatment planning system (TPS) is taken into consideration. The most problem with starting these kind of researches is the geometry of Medical linacs and verification of the accelerators. Therefore, researchers tried to...
متن کاملEnabling Legacy Applications on Heterogeneous Platforms
In this paper we make the case for a runtime technique to seamlessly execute legacy applications on heterogeneous platforms consisting of CPUs and accelerators. We consider discrete as well as integrated heterogeneous platforms. In the former, CPU and accelerators have different memory systems; in the latter, accelerators share physical memory with the CPU. Our proposed runtime does not require...
متن کاملTowards Automated Code Generation for Autonomous Mobile Robots
With the expected growth in mobile robotics the demand for expertise to develop robot control code will also increase. As end-users cannot be expected to develop this control code themselves, a more elegant solution would be to allow the end-users to teach the robot by demonstrating the task. In this paper we show how route learning tasks may be “translated” directly into robot control code sim...
متن کاملQ: Exploit Hardening Made Easy
Prior work has shown that return oriented programming (ROP) can be used to bypass W⊕X, a software defense that stops shellcode, by reusing instructions from large libraries such as libc. Modern operating systems have since enabled address randomization (ASLR), which randomizes the location of libc, making these techniques unusable in practice. However, modern ASLR implementations leave smaller ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006