際際滷shows by User: astojanov / http://www.slideshare.net/images/logo.gif 際際滷shows by User: astojanov / Thu, 22 Jun 2017 01:37:49 GMT 際際滷Share feed for 際際滷shows by User: astojanov Vectorization with LMS: SIMD Intrinsics /slideshow/vectorization-with-lms-simd-intrinsics/77159846 intrinsics-170622013750
Vectorization with LMS: SIMD Intrinsics - Introductory slides to the tutorial given at PLDI 2017 in Barcelona, Spain]]>
Vectorization with LMS: SIMD Intrinsics - Introductory slides to the tutorial given at PLDI 2017 in Barcelona, Spain]]> Thu, 22 Jun 2017 01:37:49 GMT /slideshow/vectorization-with-lms-simd-intrinsics/77159846 astojanov@slideshare.net(astojanov) Vectorization with LMS: SIMD Intrinsics astojanov Vectorization with LMS: SIMD Intrinsics - Introductory slides to the tutorial given at PLDI 2017 in Barcelona, Spain <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/intrinsics-170622013750-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Vectorization with LMS: SIMD Intrinsics - Introductory slides to the tutorial given at PLDI 2017 in Barcelona, Spain
Vectorization with LMS: SIMD Intrinsics from ETH Zurich
]]> 766 4 https://cdn.slidesharecdn.com/ss_thumbnails/intrinsics-170622013750-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Abstracting Vector Architectures in Library Generators: Case Study Convolution Filters /slideshow/abstracting-vector-architectures-in-library-generators-case-study-convolution-filters/42984254 arraypdf-141224032326-conversion-gate02
We present FGen, a program generator for high performance convolution operations (finite-impulse-response filters). The generator uses an internal mathematical DSL to enable structural optimization at a high level of abstraction. We use FGen as a testbed to demonstrate how to provide modular and extensible support for modern SIMD vector architectures in a DSL-based generator. Specifically, we show how to combine staging and generic programming with type classes to abstract over both the data type (real or complex) and the target architecture (e.g., SSE or AVX) when mapping DSL expressions to C code with explicit vector intrinsics. Benchmarks shows that the generated code is highly competitive with commercial libraries.]]>
We present FGen, a program generator for high performance convolution operations (finite-impulse-response filters). The generator uses an internal mathematical DSL to enable structural optimization at a high level of abstraction. We use FGen as a testbed to demonstrate how to provide modular and extensible support for modern SIMD vector architectures in a DSL-based generator. Specifically, we show how to combine staging and generic programming with type classes to abstract over both the data type (real or complex) and the target architecture (e.g., SSE or AVX) when mapping DSL expressions to C code with explicit vector intrinsics. Benchmarks shows that the generated code is highly competitive with commercial libraries.]]> Wed, 24 Dec 2014 03:23:26 GMT /slideshow/abstracting-vector-architectures-in-library-generators-case-study-convolution-filters/42984254 astojanov@slideshare.net(astojanov) Abstracting Vector Architectures in Library Generators: Case Study Convolution Filters astojanov We present FGen, a program generator for high performance convolution operations (finite-impulse-response filters). The generator uses an internal mathematical DSL to enable structural optimization at a high level of abstraction. We use FGen as a testbed to demonstrate how to provide modular and extensible support for modern SIMD vector architectures in a DSL-based generator. Specifically, we show how to combine staging and generic programming with type classes to abstract over both the data type (real or complex) and the target architecture (e.g., SSE or AVX) when mapping DSL expressions to C code with explicit vector intrinsics. Benchmarks shows that the generated code is highly competitive with commercial libraries. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/arraypdf-141224032326-conversion-gate02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> We present FGen, a program generator for high performance convolution operations (finite-impulse-response filters). The generator uses an internal mathematical DSL to enable structural optimization at a high level of abstraction. We use FGen as a testbed to demonstrate how to provide modular and extensible support for modern SIMD vector architectures in a DSL-based generator. Specifically, we show how to combine staging and generic programming with type classes to abstract over both the data type (real or complex) and the target architecture (e.g., SSE or AVX) when mapping DSL expressions to C code with explicit vector intrinsics. Benchmarks shows that the generated code is highly competitive with commercial libraries.
Abstracting Vector Architectures in Library Generators: Case Study Convolution Filters from ETH Zurich
]]> 2441 4 https://cdn.slidesharecdn.com/ss_thumbnails/arraypdf-141224032326-conversion-gate02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Gesture-based Human-computer Interaction /slideshow/presentation-42983806/42983806 presentation-141224025632-conversion-gate02
In the last decade, new classes of devices for accessing information have emerged along with increased connectivity. In parallel to the proliferation of these devices, new interaction styles have been explored. One major problem is the restrictive human machine interface like gloves, magnetic trackers, and head mounted displays. Such interfaces with excessive connections are hampering the interactivity. This presentation introduces a method to develop a robust computer vision module to capture and recognise the human gestures using a regular video camera and use the full potential of these gestures in a user friendly graphical environment.]]>
In the last decade, new classes of devices for accessing information have emerged along with increased connectivity. In parallel to the proliferation of these devices, new interaction styles have been explored. One major problem is the restrictive human machine interface like gloves, magnetic trackers, and head mounted displays. Such interfaces with excessive connections are hampering the interactivity. This presentation introduces a method to develop a robust computer vision module to capture and recognise the human gestures using a regular video camera and use the full potential of these gestures in a user friendly graphical environment.]]> Wed, 24 Dec 2014 02:56:32 GMT /slideshow/presentation-42983806/42983806 astojanov@slideshare.net(astojanov) Gesture-based Human-computer Interaction astojanov In the last decade, new classes of devices for accessing information have emerged along with increased connectivity. In parallel to the proliferation of these devices, new interaction styles have been explored. One major problem is the restrictive human machine interface like gloves, magnetic trackers, and head mounted displays. Such interfaces with excessive connections are hampering the interactivity. This presentation introduces a method to develop a robust computer vision module to capture and recognise the human gestures using a regular video camera and use the full potential of these gestures in a user friendly graphical environment. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/presentation-141224025632-conversion-gate02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> In the last decade, new classes of devices for accessing information have emerged along with increased connectivity. In parallel to the proliferation of these devices, new interaction styles have been explored. One major problem is the restrictive human machine interface like gloves, magnetic trackers, and head mounted displays. Such interfaces with excessive connections are hampering the interactivity. This presentation introduces a method to develop a robust computer vision module to capture and recognise the human gestures using a regular video camera and use the full potential of these gestures in a user friendly graphical environment.
Gesture-based Human-computer Interaction from ETH Zurich
]]> 760 4 https://cdn.slidesharecdn.com/ss_thumbnails/presentation-141224025632-conversion-gate02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Automating Return Oriented Programming Attacks /slideshow/automating-return-oriented-programming-attacks/15661445 arop-121216142750-phpapp01
Master thesis of Alen ]]>
Master thesis of Alen ]]> Sun, 16 Dec 2012 14:27:50 GMT /slideshow/automating-return-oriented-programming-attacks/15661445 astojanov@slideshare.net(astojanov) Automating Return Oriented Programming Attacks astojanov Master thesis of Alen <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/arop-121216142750-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Master thesis of Alen
Automating Return Oriented Programming Attacks from ETH Zurich
]]> 4278 8 https://cdn.slidesharecdn.com/ss_thumbnails/arop-121216142750-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-astojanov-48x48.jpg?cb=1523371322 https://astojanov.wordpress.com/ https://cdn.slidesharecdn.com/ss_thumbnails/intrinsics-170622013750-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/vectorization-with-lms-simd-intrinsics/77159846 Vectorization with LMS... https://cdn.slidesharecdn.com/ss_thumbnails/arraypdf-141224032326-conversion-gate02-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/abstracting-vector-architectures-in-library-generators-case-study-convolution-filters/42984254 Abstracting Vector Arc... https://cdn.slidesharecdn.com/ss_thumbnails/presentation-141224025632-conversion-gate02-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/presentation-42983806/42983806 Gesture-based Human-co...