Customized Parallel Computing research group Profile
Customized Parallel Computing research group

@CustomParComp

Followers
51
Following
2
Media
4
Statuses
63

Tampere, Finland
Joined July 2018
Don't wanna be here? Send us removal request.
@CustomParComp
Customized Parallel Computing research group
11 months
As part of @sochubfi, CPC successfully taped out a customized TTA-based Digital Signal Processor (DSP). "Beaivi DSP" was fully designed and C-programmed by using the OpenASIP tools developed by the group since the 2000s: @ITC_TampereUni.
0
0
2
@CustomParComp
Customized Parallel Computing research group
1 year
Link to the full playlist:
Tweet card summary image
youtube.com
0
0
2
@grok
Grok
19 days
Blazing-fast image creation – using just your voice. Try Grok Imagine.
283
568
3K
@CustomParComp
Customized Parallel Computing research group
1 year
The results of past 3 years of hard work on the edge AI offloading SW stack based on PoCL-R were shown in the AISA Y3 demo day last Friday. Feature showcase videos available (spoiler: Crazyflie can edge offload AI!): @vga_tuni @OpenCLorg @Bitcraze_se.
1
0
1
@CustomParComp
Customized Parallel Computing research group
2 years
OpenASIP v2.1 released: It adds support for LLVM 17, speeds up DSE thanks to a more intelligent LLVM BE generation, and more! @sochubfi.
Tweet card summary image
github.com
Main changes and features: Added support for LLVM 17 and 16. Dropped support for LLVM versions older than 16. The LLVM legacy pass manager for opt is no longer supported. All opt passes now use th...
0
0
1
@CustomParComp
Customized Parallel Computing research group
2 years
RT @HepolaKari: Our article introduces a dual-mode processor that utilizes ILP statically when available, without suffering from low code d….
0
1
0
@CustomParComp
Customized Parallel Computing research group
2 years
Maarten Molendijk from @TUeindhoven presented "BrainTTA: A 28.6 TOPS/W Compiler Programmable Transport-Triggered NN SoC" in @ieee_iccd. BrainTTA was designed and programmed using the tools. @sochubfi.
0
0
0
@CustomParComp
Customized Parallel Computing research group
2 years
RT @portablecl: PoCL-R is a new backend for offloading OpenCL tasks to other nodes on the network. Now with OpenCL API offloading can be pe….
portablecl.org
PoCL: a performance portable open source OpenCL implementation
0
5
0
@CustomParComp
Customized Parallel Computing research group
3 years
HW accelerators require vendor-specific steps to use. A generic memory-mapped interface helps integrating them to a diverse OpenCL platform. Our interfacing work is now published in and the code available in the @portablecl repo! @openclapi @CPSoSAWARE.
0
3
5
@CustomParComp
Customized Parallel Computing research group
3 years
Check a demo made with some of our final technical outcomes from the @CPSoSAWARE EU project: Nano-PoCL, PoCL-R and AlmaIF v2. Offloading OpenVX from a nanodrone to an FPGA using OpenCL as the offload API. Exciting stuff! @openclapi @portablecl.
0
3
4
@CustomParComp
Customized Parallel Computing research group
3 years
OpenASIP 2.0 is out! It has the first #RISCV customization features, improved FU generation, LLVM 15, IP wrapping, among other new features! @sochubfi @CPSoSAWARE @openhwgroup
0
2
1
@CustomParComp
Customized Parallel Computing research group
3 years
RT @HepolaKari: VLIW processors exploit ILP efficiently but suffer from bad code density in serial parts where instruction packets cannot b….
researchgate.net
PDF | Exploiting instruction level parallelism (ILP) is a widely used method for increasing performance of processors. While traditional very long... | Find, read and cite all the research you need...
0
1
0
@CustomParComp
Customized Parallel Computing research group
3 years
RT @HepolaKari: The open-standard RISC-V ISA has made the open source hardware community more active but there has been a lack of tools for….
Tweet card summary image
researchgate.net
PDF | Application-specific instruction-set processors (ASIPs) are interesting for improving performance or energy-efficiency for a set of applications... | Find, read and cite all the research you...
0
1
0
@CustomParComp
Customized Parallel Computing research group
3 years
OpenASIP 1.25 is now out. It supports LLVM 14 and adds partial retargetable inline asm support and loop buffer compilation features. Thanks to @CPSoSAWARE for supporting the @CustomParComp. group's contributions! @sochubfi @llvmorg.
0
1
3
@CustomParComp
Customized Parallel Computing research group
4 years
RT @JoonasMultanen: Emerging memory technologies could enable extremely energy-efficient compute devices in the future. Read how domain wal….
0
3
0
@CustomParComp
Customized Parallel Computing research group
4 years
OpenASIP 1.24 released! Adds LLVM 13 and first steps for Blocks CGRA support. Thanks @FitOptiVis. @CPSoSAWARE @sochubfi for supporting the @CustomParComp group's contributions!.
0
2
2
@CustomParComp
Customized Parallel Computing research group
4 years
A presentation about our ongoing work on PoCL-R: Distributed OpenCL Runtime for Low Latency Offloading available: @portablecl @openclapi @FitOptiVis @CPSoSAWARE.
0
5
7
@CustomParComp
Customized Parallel Computing research group
4 years
CPC is looking forward to contributing to this interesting joint project in its distributed high performance low latency computing aspects!.
@dimecc_fi
DIMECC
4 years
Great news! @dimecc_fi facilitates the new AISA (AI based Situational Awareness) project!.The partners of the #AISAPROJECT are @nokia Technologies, @valmetglobal Automation, #Mirka, #Insta, @TopDataScience, @ficololtd and @TampereUni @BusinessFinland.
0
0
0
@CustomParComp
Customized Parallel Computing research group
4 years
OpenASIP 1.23 released! It's mainly a maintenance release that adds LLVM 12 support and removes support for older than LLVM 11 to clean up the code base. Thanks @FitOptiVis @CPSoSAWARE @sochubfi .for supporting the @CustomParComp group's work!.
0
1
2