HPC Compiler Company PathScale Seeks Life Raft

By Tiffany Trader

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its assets. A letter from the company with a listing of assets is included at the end of the article.

PathScale represents one of handful of compiler technologies that are designed for high performance computing, and it is one the last independent HPC compiler companies. In an interview with HPCwire, PathScale Chief Technology Officer and owner Christopher Bergström attributes the company’s financial insolvency to its heavy involvement in Intel alternative architectures.

“Unfortunately in recent years, we bet big on ARMv8 and the partner ecosystem and the hardware has been extremely disappointing,” said Bergström. “Once partners saw how low their hardware performed on HPC workloads they decided to pull back on their investment in HPC software.”

Due to confidentiality agreements, he’s limited to speaking in generalities but argues that the currently available ARMv8 processors deliver very weak performance for HPC workloads.

“ARM is possibly aware of this issue and as a result has introduced SVE (Scalable Vector Extensions),” Bergström told us. “Unfortunately, they focused more on the portability side of vectorization and the jury is still out if they can deliver competitive performance. SVE’s flexible design and freedom to change vector width on the fly will possibly impact the ability to write code tuned specifically for a target processor. In addition, design of the hardware architecture blocks software optimizations that are very common and potentially critical for HPC. And based on the publicly available roadmaps, the floating point to power ratio is not where it needs to be for HPC workloads in order to effectively compete against Intel or GPUs.”

Before coming to these conclusions, PathScale had a statement of work contract with Cavium to help support optimizing compilers for their ThunderX processors. When that funding was pulled, PathScale also lost their ability to gain and support customers for ARMv8. They looked for funders, and had conversations with stakeholders in the private and public sphere, but the money just wasn’t available.

“Show me a company in the HPC space wanting to invest,” said Bergström, “They’re not investing in compiler technology.”

ARM, which was scooped up by Japanese company SoftBank in September 2016 for $31 billion, may be the exception, but according to Bergström the PathScale technology, while it significantly leverages LLVM, doesn’t perfectly align with what they need.

Bergström brokered the deal with Cray that resurrected PathScale from the ashes of SiCortex in 2009 (more on this below) and he’s proud of what he and his team have accomplished over the last seven years. “We love compilers, we love the technology. We want to continue developing this stuff. The team is rock solid, we’re like family. We live eat and breathe compilers, but we’re not on a sustainable business path and we need a bailout or help refocusing. We need people who understand that these kind of technologies add value and LLVM by itself isn’t a panacea.”

Addison Snell, CEO of HPC analyst firm Intersect360 Research, shared some additional perspective on the market dynamics at play for independent tools vendors. “In the Beowulf era, clusters were all mostly the same, so what little differentiation there was came from things like development environments and job management software,” he said. “Independent middleware companies of all types flourished. Now we’re trending back toward an era of architectural specialization. Users are shopping for architectures more than they’re shopping for which compiler to use for a given architecture, and acquisitions have locked up some of the previously dominant players. Vendors’ solutions will have their own integrated stacks. Free open-source versions might still exist, but there will be less room for independent middleware players.”

PathScale has a winding history that dates back to 2001 with the founding of Key Research by Lawrence Livermore alum Tom McWilliams. The company was riding the commodity cluster wave, developing clustered Linux server solutions based on a low-cost 64-bit design. In 2003, contemporaneous with the rising popularity of AMD Opteron processors, Key Research rebranded as PathScale and expanded its product line to include high-performance computing adapters and 64-bit compilers.

PathScale would then pass through a number of corporate hands. In 2006, QLogic acquired PathScale, primarily to gain access to its InfiniBand interconnect technology. The following year, the compiler assets were sold to SiCortex, which sought a solution for its MIPS-based HPC systems.

When SiCortex closed its doors in 2009, Cray bought the PathScale assets and revived the company. Under an arrangement struck with Cray, PathScale would go forward as an independent technology group with an option to buy. In March 2012, PathScale CTO Christopher Bergström acquired all assets and became the sole owner of PathScale Inc.

The PathScale toolchain currently generates code for the latest Intel processors, AMD64, AMD GPUs, Power8, ARMv8, and NVIDIA GPUs in combination with both Power8 and x86.

In a message to the community, Pathscale writes:

We are evaluating all options to overcome this difficult time, including refocusing to provide training and code porting services instead of purely offering compiler licenses and optimization services. Our team deeply understands parallel programming and whether you have crazy C++ or ancient Fortran, we can likely help get it running on GPUs (NVIDIA or AMD) or vectorization targets (like Xeon Phi).

All PathScale engineers would love to continue to work on the compiler as an independent company, but we need the community to help us. We need people who believe in our technical roadmap. We need people who understand the future exascale computing software stack will likely be complex, but that complexity and advanced optimizations will make it easier for end users. At the same time we must be realistic and without immediate assistance start accepting any reasonable offer on the assets as a whole or piece by piece.

Our assets include:

  • PathScale website, trademarks and branding

  • C, C++ and Fortran compilers

  • Complete GPGPU and many-core runtime which supports OMP4 and OpenACC and is portable across multiple architectures (NVIDIA GPU, ARMv8, Power8+NVIDIA and AMD GPU)

  • Significant modifications to CLANG and LLVM to enable support for OpenACC and OpenMP and parallel programming models.

  • Complete engineering team with expertise working on CLANG and LLVM and MIPSPro.

  • Advertising credits with popular websites ($30,000)

A purchase or funding from crowdsourcing or other community event will keep a highly optimizing OpenMP and OpenACC C/C++ and Fortran compiler toolchain plus experienced development team in operation. Succinctly, PathScale preserves architectural diversity and opens the door for competition with a performant compiler for interesting architectures with OpenMP and OpenACC parallelization.

If interested please contact funding@pathscale.com.


Editor’s note: HPCwire has reached out to Cavium and ARM and we will update the article with any responses we receive.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Graphcore Introduces Larger-Than-Ever IPU-Based Pods

October 22, 2021

Graphcore and its “Intelligent Processing Units” (IPUs) emerged from stealth in 2016 and launched its second-generation IPU in 2020. While the company has also launched its IPUs in a variety of form factors over the Read more…

Quantum Chemistry Project to Be Among the First on EuroHPC’s LUMI System

October 22, 2021

Finland’s CSC has just installed the first module of LUMI, a 550-peak petaflops system supported by the European Union’s EuroHPC Joint Undertaking. While LUMI -- pictured in the header -- isn’t slated to complete i Read more…

Killer Instinct: AMD’s Multi-Chip MI200 GPU Readies for a Major Global Debut

October 21, 2021

AMD’s next-generation supercomputer GPU is on its way – and by all appearances, it’s about to make a name for itself. The AMD Radeon Instinct MI200 GPU (a successor to the MI100) will, over the next year, begin to power three massive systems on three continents: the United States’ exascale Frontier system; the European Union’s pre-exascale LUMI system; and Australia’s petascale Setonix system. Read more…

D-Wave Embraces Gate-Based Quantum Computing; Charts Path Forward

October 21, 2021

Earlier this month D-Wave Systems, the quantum computing pioneer that has long championed quantum annealing-based quantum computing (and sometimes taken heat for that approach), announced it was expanding into gate-based Read more…

LLNL Prepares the Water and Power Infrastructure for El Capitan

October 21, 2021

When it’s (ostensibly) ready in early 2023, El Capitan is expected to deliver in excess of two exaflops of peak computing power – around four times the power of Fugaku, the current top-ranked supercomputer in the wor Read more…

AWS Solution Channel

Royalty-free stock illustration ID: 537899029

Running GROMACS on GPU instances

Comparing the performance of real applications across different Amazon Elastic Compute Cloud (Amazon EC2) instance types is the best way we’ve found for finding optimal configurations for HPC applications here at AWS. Read more…

Faster Optical Switch that Operates at ‘Room Temp’ Developed by IBM, Skolkovo Researchers

October 19, 2021

Optical switching technology holds great promise for many applications but hot operating temperatures have been a key obstacle slowing progress. Now, a new optical switching device that can operate at room temperatures a Read more…

Killer Instinct: AMD’s Multi-Chip MI200 GPU Readies for a Major Global Debut

October 21, 2021

AMD’s next-generation supercomputer GPU is on its way – and by all appearances, it’s about to make a name for itself. The AMD Radeon Instinct MI200 GPU (a successor to the MI100) will, over the next year, begin to power three massive systems on three continents: the United States’ exascale Frontier system; the European Union’s pre-exascale LUMI system; and Australia’s petascale Setonix system. Read more…

D-Wave Embraces Gate-Based Quantum Computing; Charts Path Forward

October 21, 2021

Earlier this month D-Wave Systems, the quantum computing pioneer that has long championed quantum annealing-based quantum computing (and sometimes taken heat fo Read more…

LLNL Prepares the Water and Power Infrastructure for El Capitan

October 21, 2021

When it’s (ostensibly) ready in early 2023, El Capitan is expected to deliver in excess of two exaflops of peak computing power – around four times the powe Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Quantum Workforce – NSTC Report Highlights Need for International Talent

October 13, 2021

Attracting and training the needed quantum workforce to fuel the ongoing quantum information sciences (QIS) revolution is a hot topic these days. Last week, the U.S. National Science and Technology Council issued a report – The Role of International Talent in Quantum Information Science... Read more…

Eni Returns to HPE for ‘HPC4’ Refresh via GreenLake

October 13, 2021

Italian energy company Eni is upgrading its HPC4 system with new gear from HPE that will be installed in Eni’s Green Data Center in Ferrera Erbognone (a provi Read more…

The Blueprint for the National Strategic Computing Reserve

October 12, 2021

Over the last year, the HPC community has been buzzing with the possibility of a National Strategic Computing Reserve (NSCR). An in-utero brainchild of the COVID-19 High-Performance Computing Consortium, an NSCR would serve as a Merchant Marine for urgent computing... Read more…

UCLA Researchers Report Largest Chiplet Design and Early Prototyping

October 12, 2021

What’s the best path forward for large-scale chip/system integration? Good question. Cerebras has set a high bar with its wafer scale engine 2 (WSE-2); it has 2.6 trillion transistors, including 850,000 cores, and was fabricated using TSMC’s 7nm process on a roughly 8” x 8” silicon footprint. Read more…

Enter Dojo: Tesla Reveals Design for Modular Supercomputer & D1 Chip

August 20, 2021

Two months ago, Tesla revealed a massive GPU cluster that it said was “roughly the number five supercomputer in the world,” and which was just a precursor to Tesla’s real supercomputing moonshot: the long-rumored, little-detailed Dojo system. Read more…

Esperanto, Silicon in Hand, Champions the Efficiency of Its 1,092-Core RISC-V Chip

August 27, 2021

Esperanto Technologies made waves last December when it announced ET-SoC-1, a new RISC-V-based chip aimed at machine learning that packed nearly 1,100 cores onto a package small enough to fit six times over on a single PCIe card. Now, Esperanto is back, silicon in-hand and taking aim... Read more…

US Closes in on Exascale: Frontier Installation Is Underway

September 29, 2021

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, held by Zoom this week (Sept. 29-30), it was revealed that the Frontier supercomputer is currently being installed at Oak Ridge National Laboratory in Oak Ridge, Tenn. The staff at the Oak Ridge Leadership... Read more…

Ahead of ‘Dojo,’ Tesla Reveals Its Massive Precursor Supercomputer

June 22, 2021

In spring 2019, Tesla made cryptic reference to a project called Dojo, a “super-powerful training computer” for video data processing. Then, in summer 2020, Tesla CEO Elon Musk tweeted: “Tesla is developing a [neural network] training computer... Read more…

Intel Reorgs HPC Group, Creates Two ‘Super Compute’ Groups

October 15, 2021

Following on changes made in June that moved Intel’s HPC unit out of the Data Platform Group and into the newly created Accelerated Computing Systems and Graphics (AXG) business unit, led by Raja Koduri, Intel is making further updates to the HPC group and announcing... Read more…

Intel Completes LLVM Adoption; Will End Updates to Classic C/C++ Compilers in Future

August 10, 2021

Intel reported in a blog this week that its adoption of the open source LLVM architecture for Intel’s C/C++ compiler is complete. The transition is part of In Read more…

Hot Chips: Here Come the DPUs and IPUs from Arm, Nvidia and Intel

August 25, 2021

The emergence of data processing units (DPU) and infrastructure processing units (IPU) as potentially important pieces in cloud and datacenter architectures was Read more…

AMD-Xilinx Deal Gains UK, EU Approvals — China’s Decision Still Pending

July 1, 2021

AMD’s planned acquisition of FPGA maker Xilinx is now in the hands of Chinese regulators after needed antitrust approvals for the $35 billion deal were receiv Read more…

Leading Solution Providers

Contributors

HPE Wins $2B GreenLake HPC-as-a-Service Deal with NSA

September 1, 2021

In the heated, oft-contentious, government IT space, HPE has won a massive $2 billion contract to provide HPC and AI services to the United States’ National Security Agency (NSA). Following on the heels of the now-canceled $10 billion JEDI contract (reissued as JWCC) and a $10 billion... Read more…

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

Quantum Roundup: IBM, Rigetti, Phasecraft, Oxford QC, China, and More

July 13, 2021

IBM yesterday announced a proof for a quantum ML algorithm. A week ago, it unveiled a new topology for its quantum processors. Last Friday, the Technical Univer Read more…

The Latest MLPerf Inference Results: Nvidia GPUs Hold Sway but Here Come CPUs and Intel

September 22, 2021

The latest round of MLPerf inference benchmark (v 1.1) results was released today and Nvidia again dominated, sweeping the top spots in the closed (apples-to-ap Read more…

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

Intel Unveils New Node Names; Sapphire Rapids Is Now an ‘Intel 7’ CPU

July 27, 2021

What's a preeminent chip company to do when its process node technology lags the competition by (roughly) one generation, but outmoded naming conventions make i Read more…

Frontier to Meet 20MW Exascale Power Target Set by DARPA in 2008

July 14, 2021

After more than a decade of planning, the United States’ first exascale computer, Frontier, is set to arrive at Oak Ridge National Laboratory (ORNL) later this year. Crossing this “1,000x” horizon required overcoming four major challenges: power demand, reliability, extreme parallelism and data movement. Read more…

Quantum Computer Market Headed to $830M in 2024

September 13, 2021

What is one to make of the quantum computing market? Energized (lots of funding) but still chaotic and advancing in unpredictable ways (e.g. competing qubit tec Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire