ARES: Abstract Representations for Extreme Scale Stack - Revision history

imported>JeffreyVetter: /* Goals and Objectives */

2015-12-08T01:56:48Z

Goals and Objectives

← Older revision		Revision as of 01:56, December 8, 2015
Line 8:		Line 8:
	* Website including publications, software, and other information: http://ft.ornl.gov/research/ares		* Website including publications, software, and other information: http://ft.ornl.gov/research/ares

	== ~~Goals and Objectives~~ ==		== Overview ==

	Achieving success in programming future high-performance systems should not		Achieving success in programming future high-performance systems should not

imported>JeffreyVetter at 01:56, December 8, 2015

2015-12-08T01:56:29Z

@@ Line 1: / Line 1: @@
 == Goals and Objectives ==
@@ Line 34: / Line 43: @@
 the rate of innovation and scientific discovery in the era of
 extreme-scale computing.

imported>JeffreyVetter: /* Team Members */

2014-05-27T21:35:03Z

Team Members

← Older revision		Revision as of 21:35, May 27, 2014
Line 35:		Line 35:
	extreme-scale computing.		extreme-scale computing.

	== ~~Team Members~~ ==		== Organization ==

	* LANL, Pat McCormick, pat@lanl.gov		* LANL (Pat McCormick, pat@lanl.gov)
	* ORNL, Jeffrey Vetter, vetter@computer.org		* ORNL (Jeffrey Vetter, vetter@computer.org)

imported>JeffreyVetter at 21:33, May 27, 2014

2014-05-27T21:33:49Z

@@ Line 1: / Line 1: @@
 Achieving success in programming future high-performance systems should not
 depend on finding the single best approach, nor committing to an evolutionary
@@ Line 32: / Line 34: @@
 the rate of innovation and scientific discovery in the era of
 extreme-scale computing.

imported>JeffreyVetter at 21:32, May 27, 2014

2014-05-27T21:32:00Z

← Older revision		Revision as of 21:32, May 27, 2014
Line 20:		Line 20:
	Accordingly, ARES will investigate this approach through five specific tasks:		Accordingly, ARES will investigate this approach through five specific tasks:

	# Design, implement, and refine the ARES high-level intermediate		# Design, implement, and refine the ARES high-level intermediate representation (HLIR)} that captures the pertinent features of extreme-scale applications, architectures, and programming constructs. These activities will include developing tools for storing, manipulating, and verifying this HLIR.
	representation (HLIR)} that captures the pertinent features of		# Develop prototype ARES front-ends for two languages that map advanced language concepts (e.g., those in OpenACC) onto our HLIR.
	extreme-scale applications, architectures, and programming constructs. These		# Develop a prototype ARES optimization engine for HLIR} that optimizes the HLIR for select target architectures.
	activities will include developing tools for storing, manipulating, and		# Develop prototype ARES back-end compilation system, based on LLVM, that converts this optimized HLIR into executable instructions.
	verifying this HLIR.		# Proactively engage the broader community by publishing our software and findings, and sponsoring tutorials and meetings when appropriate. This will both ensure that our design captures the most relevant approaches, and allow our peers to leverage this infrastructure.

	# Develop prototype ARES front-ends for two languages that map advanced language
	concepts (e.g., those in OpenACC) onto our HLIR.

	# Develop a prototype ARES optimization engine for HLIR} that optimizes the HLIR
	for select target architectures.

	# Develop prototype ARES back-end compilation system, based on LLVM, that converts
	this optimized HLIR into executable instructions.

	# Proactively engage the broader community by publishing our software and findings,
	and sponsoring tutorials and meetings when appropriate. This will both ensure that our
	design captures the most relevant approaches, and allow our peers to leverage this
	infrastructure.

	We believe that the choices made in the design of this toolchain can		We believe that the choices made in the design of this toolchain can

imported>JeffreyVetter at 21:30, May 27, 2014

2014-05-27T21:30:58Z

imported>JeffreyVetter: Created page with "Achieving success in programming future high-performance systems should not depend on finding the single best approach, nor committing to an evolutionary or revolutionary path..."

2014-05-27T21:29:26Z

Created page with "Achieving success in programming future high-performance systems should not depend on finding the single best approach, nor committing to an evolutionary or revolutionary path..."

New page

Achieving success in programming future high-performance systems should not
depend on finding the single best approach, nor committing to an evolutionary
or revolutionary path. Instead, we should transform the software development
toolchain to support the design and implementation of multiple, ideally
inter-operating, approaches that allow the community to explore and
progressively move towards effective programming methodologies. To achieve
this goal our research effort breaks the tight coupling found in vertical,
language- and API-centric software stacks and supplants it with a toolchain
that incorporates a new common set of abstract representations of programs in
the form of a high-level intermediate representation (HLIR). This
representation serves as an intermediary between the language-centric abstract
syntax tree and the conventional lower-level intermediate representation (IR).
In addition to encoding the usual serial execution semantics of a traditional IR,
our higher-level IR aims to additionally encode more abstract concepts such as
concurrency, parallelism, communication, synchronization, and non-uniform memory
structures. Like a traditional IR, but unlike an abstract syntax tree, this
higher-level representation will be language independent, thus capable of supporting
a wide range of both mainstream and experimental languages.

Accordingly, ARES will investigate this approach through five specific tasks:

1. Design, implement, and refine the ARES high-level intermediate
representation (HLIR)} that captures the pertinent features of
extreme-scale applications, architectures, and programming constructs. These
activities will include developing tools for storing, manipulating, and
verifying this HLIR.

2. Develop prototype ARES front-ends for two languages that map advanced language
concepts (e.g., those in OpenACC) onto our HLIR.

3. Develop a prototype ARES optimization engine for HLIR} that optimizes the HLIR
for select target architectures.

4. Develop prototype ARES back-end compilation system, based on LLVM, that converts
this optimized HLIR into executable instructions.

5. Proactively engage the broader community by publishing our software and findings,
and sponsoring tutorials and meetings when appropriate. This will both ensure that our
design captures the most relevant approaches, and allow our peers to leverage this
infrastructure.

We believe that the choices made in the design of this toolchain can
have a profound impact on productivity and in the overall success of
deploying powerful new approaches for programming, which, in turn,
directly affect scientists' ability to maintain, let alone increase,
the rate of innovation and scientific discovery in the era of
extreme-scale computing.

← Older revision		Revision as of 21:30, May 27, 2014
Line 20:		Line 20:
	Accordingly, ARES will investigate this approach through five specific tasks:		Accordingly, ARES will investigate this approach through five specific tasks:

	1. Design, implement, and refine the ARES high-level intermediate		# Design, implement, and refine the ARES high-level intermediate
	representation (HLIR)} that captures the pertinent features of		representation (HLIR)} that captures the pertinent features of
	extreme-scale applications, architectures, and programming constructs. These		extreme-scale applications, architectures, and programming constructs. These
Line 26:		Line 26:
	verifying this HLIR.		verifying this HLIR.

	2. Develop prototype ARES front-ends for two languages that map advanced language		# Develop prototype ARES front-ends for two languages that map advanced language
	concepts (e.g., those in OpenACC) onto our HLIR.		concepts (e.g., those in OpenACC) onto our HLIR.

	3. Develop a prototype ARES optimization engine for HLIR} that optimizes the HLIR		# Develop a prototype ARES optimization engine for HLIR} that optimizes the HLIR
	for select target architectures.		for select target architectures.

	4. Develop prototype ARES back-end compilation system, based on LLVM, that converts		# Develop prototype ARES back-end compilation system, based on LLVM, that converts
	this optimized HLIR into executable instructions.		this optimized HLIR into executable instructions.

	5. Proactively engage the broader community by publishing our software and findings,		# Proactively engage the broader community by publishing our software and findings,
	and sponsoring tutorials and meetings when appropriate. This will both ensure that our		and sponsoring tutorials and meetings when appropriate. This will both ensure that our
	design captures the most relevant approaches, and allow our peers to leverage this		design captures the most relevant approaches, and allow our peers to leverage this