Skip to content

Commit 29e7f06

Browse files
committed
Added venues to publications
1 parent a0b8a11 commit 29e7f06

File tree

4 files changed

+48
-26
lines changed

4 files changed

+48
-26
lines changed

_data/publications.yml

Lines changed: 45 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@
22
pubs:
33
- title: Autoscheduling for Sparse Tensor Algebra with an Asymptotic Cost Model
44
authors: Peter Ahrens, Fredrik Kjolstad, and Saman Amarasinghe
5+
venue: PLDI 2022
56
is_thesis: false
67
paper_link: https://arxiv.org/pdf/2111.14947.pdf
78
abstract: >
@@ -18,6 +19,7 @@
1819
}
1920
- title: "DISTAL: The Distributed Tensor Algebra Compiler"
2021
authors: Rohan Yadav, Alex Aiken, and Fredrik Kjolstad
22+
venue: PLDI 2022
2123
is_thesis: false
2224
paper_link: https://arxiv.org/pdf/2203.08069.pdf
2325
abstract: >
@@ -32,6 +34,7 @@
3234
}
3335
- title: Unified Compilation for Lossless Compression and Sparse Computing
3436
authors: Daniel Donenfeld, Stephen Chou, and Saman Amarasinghe
37+
venue: CGO 2022
3538
is_thesis: false
3639
paper_link: /files/donenfeld-cgo22-taco-compression.pdf
3740
youtube: uU3brPcwUos
@@ -52,6 +55,7 @@
5255
pubs:
5356
- title: Dynamic Sparse Tensor Algebra Compilation
5457
authors: Stephen Chou and Saman Amarasinghe
58+
venue: arXiv Preprint
5559
is_thesis: false
5660
paper_link: /files/chou-arxiv-taco-dynamic.pdf
5761
abstract: >
@@ -71,6 +75,7 @@
7175
}
7276
- title: Compilation of Sparse Array Programming Models
7377
authors: Rawn Henry*, Olivia Hsu*, Rohan Yadav, Stephen Chou, Kunle Olukotun, Saman Amarasinghe, and Fredrik Kjolstad
78+
venue: OOPSLA 2021
7479
is_thesis: false
7580
paper_link: /files/henry_hsu-oopsla21-taco-array.pdf
7681
youtube: sY_jEfaP8f4
@@ -102,6 +107,7 @@
102107
pubs:
103108
- title: A Sparse Iteration Space Transformation Framework for Sparse Tensor Algebra
104109
authors: Ryan Senanayake, Changwan Hong, Ziheng Wang, Amalee Wilson, Stephen Chou, Shoaib Kamil, Saman Amarasinghe, and Fredrik Kjolstad
110+
venue: OOPSLA 2020
105111
is_thesis: false
106112
paper_link: /files/senanayake-oopsla20-taco-scheduling.pdf
107113
youtube: 0wJsGWA5pTU
@@ -127,8 +133,34 @@
127133
numpages = {30},
128134
keywords = {Sparse Tensor Algebra, Sparse Iteration Spaces, Optimizing Transformations}
129135
}
136+
- title: Sparse Tensor Transpositions
137+
authors: Suzanne Mueller, Peter Ahrens, Stephen Chou, Fredrik Kjolstad, and Saman Amarasinghe
138+
venue: SPAA 2020
139+
is_thesis: false
140+
paper_link: /files/mueller-spaa20-taco-transpositions.pdf
141+
youtube: rUtw6vLZR-g
142+
abstract: >
143+
We present a new algorithm for transposing sparse tensors called Quesadilla. The algorithm converts the sparse tensor data structure to a list of coordinates and sorts it with a fast multi-pass radix algorithm that exploits knowledge of the requested transposition and the tensors input partial coordinate ordering to provably minimize the number of parallel partial sorting passes. We evaluate both a serial and a parallel implementation of Quesadilla on a set of 19 tensors from the FROSTT collection, a set of tensors taken from scientific and data analytic applications. We compare Quesadilla and a generalization, Top-2-sadilla to several state of the art approaches, including the tensor transposition routine used in the SPLATT tensor factorization library. In serial tests, Quesadilla was the best strategy for 60% of all tensor and transposition combinations and improved over SPLATT by at least 19% in half of the combinations. In parallel tests, at least one of Quesadilla or Top-2-sadilla was the best strategy for 52% of all tensor and transposition combinations.
144+
bibtex: >
145+
@inproceedings{mueller:2020:transposition,
146+
author = {Mueller, Suzanne and Ahrens, Peter and Chou, Stephen and Kjolstad, Fredrik and Amarasinghe, Saman},
147+
title = {Sparse Tensor Transpositions},
148+
year = {2020},
149+
isbn = {9781450369350},
150+
publisher = {Association for Computing Machinery},
151+
address = {New York, NY, USA},
152+
url = {https://doi.org/10.1145/3350755.3400245},
153+
doi = {10.1145/3350755.3400245},
154+
booktitle = {Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures},
155+
pages = {559–561},
156+
numpages = {3},
157+
keywords = {COO, sorting, radix sort, transposition, sparse tensors},
158+
location = {Virtual Event, USA},
159+
series = {SPAA '20}
160+
}
130161
- title: Automatic Generation of Efficient Sparse Tensor Format Conversion Routines
131162
authors: Stephen Chou, Fredrik Kjolstad, and Saman Amarasinghe
163+
venue: PLDI 2020
132164
is_thesis: false
133165
paper_link: /files/chou-pldi20-taco-conversion.pdf
134166
slide_link: /files/chou-pldi20-slides.pdf
@@ -154,32 +186,9 @@
154186
location = {London, UK},
155187
series = {PLDI 2020}
156188
}
157-
- title: Sparse Tensor Transpositions
158-
authors: Suzanne Mueller, Peter Ahrens, Stephen Chou, Fredrik Kjolstad, and Saman Amarasinghe
159-
is_thesis: false
160-
paper_link: /files/mueller-spaa20-taco-transpositions.pdf
161-
youtube: rUtw6vLZR-g
162-
abstract: >
163-
We present a new algorithm for transposing sparse tensors called Quesadilla. The algorithm converts the sparse tensor data structure to a list of coordinates and sorts it with a fast multi-pass radix algorithm that exploits knowledge of the requested transposition and the tensors input partial coordinate ordering to provably minimize the number of parallel partial sorting passes. We evaluate both a serial and a parallel implementation of Quesadilla on a set of 19 tensors from the FROSTT collection, a set of tensors taken from scientific and data analytic applications. We compare Quesadilla and a generalization, Top-2-sadilla to several state of the art approaches, including the tensor transposition routine used in the SPLATT tensor factorization library. In serial tests, Quesadilla was the best strategy for 60% of all tensor and transposition combinations and improved over SPLATT by at least 19% in half of the combinations. In parallel tests, at least one of Quesadilla or Top-2-sadilla was the best strategy for 52% of all tensor and transposition combinations.
164-
bibtex: >
165-
@inproceedings{mueller:2020:transposition,
166-
author = {Mueller, Suzanne and Ahrens, Peter and Chou, Stephen and Kjolstad, Fredrik and Amarasinghe, Saman},
167-
title = {Sparse Tensor Transpositions},
168-
year = {2020},
169-
isbn = {9781450369350},
170-
publisher = {Association for Computing Machinery},
171-
address = {New York, NY, USA},
172-
url = {https://doi.org/10.1145/3350755.3400245},
173-
doi = {10.1145/3350755.3400245},
174-
booktitle = {Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures},
175-
pages = {559–561},
176-
numpages = {3},
177-
keywords = {COO, sorting, radix sort, transposition, sparse tensors},
178-
location = {Virtual Event, USA},
179-
series = {SPAA '20}
180-
}
181189
- title: A Framework for Computing on Sparse Tensors based on Operator Properties
182190
authors: Rawn Henry
191+
venue: MEng Thesis
183192
is_thesis: true
184193
paper_link: /files/henry-meng-thesis-taco-array.pdf
185194
abstract: >
@@ -201,6 +210,7 @@
201210
}
202211
- title: Automatic Optimization of Sparse Tensor Algebra Programs
203212
authors: Ziheng Wang
213+
venue: MEng Thesis
204214
is_thesis: true
205215
paper_link: /files/wang-meng-thesis-taco-autoscheduling.pdf
206216
abstract: >
@@ -220,6 +230,7 @@
220230
}
221231
- title: A Unified Iteration Space Transformation Framework for Sparse and Dense Tensor Algebra
222232
authors: Ryan Senanayake
233+
venue: MEng Thesis
223234
is_thesis: true
224235
paper_link: /files/senanayake-meng-thesis-taco-scheduling.pdf
225236
abstract: >
@@ -239,6 +250,7 @@
239250
}
240251
- title: Sparse Tensor Transpositions in the Tensor Algebra Compiler
241252
authors: Suzanne Mueller
253+
venue: MEng Thesis
242254
is_thesis: true
243255
paper_link: /files/mueller-meng-thesis-taco-transposition.pdf
244256
abstract: >
@@ -256,6 +268,7 @@
256268
}
257269
- title: Sparse Tensor Algebra Compilation
258270
authors: Fredrik Kjolstad
271+
venue: PhD Thesis
259272
is_thesis: true
260273
paper_link: /files/kjolstad-phd-thesis-taco-compiler.pdf
261274
abstract: >
@@ -277,6 +290,7 @@
277290
pubs:
278291
- title: A Tensor Algebra Compiler Library Interface and Runtime
279292
authors: Patricio Noyola
293+
venue: MEng Thesis
280294
is_thesis: true
281295
paper_link: /files/noyola-meng-thesis-taco-interface.pdf
282296
abstract: >
@@ -298,6 +312,7 @@
298312
}
299313
- title: "SuperTaco: Taco Tensor Algebra Kernels on Distributed Systems Using Legion"
300314
authors: Sachin Dilip Shinde
315+
venue: MEng Thesis
301316
is_thesis: true
302317
paper_link: /files/shinde-meng-thesis-taco-distributed.pdf
303318
abstract: >
@@ -317,6 +332,7 @@
317332
}
318333
- title: Tensor Algebra Compilation with Workspaces
319334
authors: Fredrik Kjolstad, Peter Ahrens, Shoaib Kamil, and Saman Amarasinghe
335+
venue: CGO 2019
320336
is_thesis: false
321337
paper_link: /files/kjolstad-cgo19-taco-workspaces.pdf
322338
abstract: >
@@ -344,6 +360,7 @@
344360
pubs:
345361
- title: Format Abstraction for Sparse Tensor Algebra Compilers
346362
authors: Stephen Chou, Fredrik Kjolstad, and Saman Amarasinghe
363+
venue: OOPSLA 2018
347364
is_thesis: false
348365
paper_link: /files/chou-oopsla18-taco-formats.pdf
349366
slide_link: /files/chou-oopsla18-slides.pdf
@@ -375,6 +392,7 @@
375392
}
376393
- title: Unified Sparse Formats for Tensor Algebra Compilers
377394
authors: Stephen Chou
395+
venue: SM Thesis
378396
is_thesis: true
379397
paper_link: /files/chou-sm-thesis-taco-formats.pdf
380398
abstract: >
@@ -398,6 +416,7 @@
398416
pubs:
399417
- title: The Tensor Algebra Compiler
400418
authors: Fredrik Kjolstad, Shoaib Kamil, Stephen Chou, David Lugato, and Saman Amarasinghe
419+
venue: OOPSLA 2017
401420
is_thesis: false
402421
paper_link: /files/kjolstad-oopsla17-tensor-compiler.pdf
403422
slide_link: /files/kjolstad-oopsla17-slides.pdf
@@ -427,6 +446,7 @@
427446
}
428447
- title: "taco: A Tool to Generate Tensor Algebra Kernels"
429448
authors: Fredrik Kjolstad, Stephen Chou, David Lugato, Shoaib Kamil, and Saman Amarasinghe
449+
venue: ASE 2017
430450
is_thesis: false
431451
paper_link: /files/kjolstad-ase17-taco-tools.pdf
432452
youtube: eE38PC2ctFs
@@ -447,6 +467,7 @@
447467
pubs:
448468
- title: An Investigation of Sparse Tensor Formats for Tensor Libraries
449469
authors: Parker Allen Tew
470+
venue: MEng Thesis
450471
is_thesis: true
451472
paper_link: /files/tew-meng-thesis-sparse.pdf
452473
abstract: >

_data/related.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -6,6 +6,7 @@
66
pubs:
77
- title: Compiler Support for Sparse Tensor Computations in MLIR
88
authors: Aart J.C. Bik, Penporn Koanantakool, Tatiana Shpeisman, Nicolas Vasilache, Bixia Zheng, and Fredrik Kjolstad
9+
venue: arXiv Preprint
910
is_thesis: false
1011
paper_link: https://arxiv.org/abs/2202.04305
1112
slide_link: https://llvm.org/devmtg/2021-11/slides/2021-CompilerSupportforSparseTensorComputationsinMLIR.pdf

_includes/publist.html

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
 
1616
<b>{{ pub.title }}</b>
1717
&nbsp;
18-
<small>{{ pub.authors }}</small>
18+
<small>{{ pub.authors }} {% if pub.venue %}({{ pub.venue }}){% endif %}</small>
1919
</summary>
2020
<blockquote>
2121
{% if pub.paper_link %}

publications.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ hero_height: is-small
44
layout: page
55
---
66

7-
TACO is built on research that is described in the following publications, which include conference papers and preprints (denoted by <i class="fas fa-newspaper"></i>) as well as master's and doctoral theses (denoted by <i class="fas fa-book"></i>).
7+
TACO is built on research that is described in the following publications, which include conference papers and preprints (denoted by <i class="fas fa-newspaper"></i>) as well as master's and PhD theses (denoted by <i class="fas fa-book"></i>).
88
Simply click on the title of any paper or thesis below to see more information, download a copy, or watch the accompanying talk.
99

1010
(*) denotes co-first authors.

0 commit comments

Comments
 (0)