New Details Surface On Blue Waters Supercomputer Split
Last month, we discussed the split between IBM and the NCSA (National Center for Supercomputing Applications) over the highly ambitious 'Blue Waters' project. Blue Waters was the name of a planned supercomputer that would've been entirely water-cooled and included as many as 524,288 CPU cores. The disintegration of the deal came as some surprise, given the amount of work that'd already been done on the project.
New details have come to light on why the University of Illinois and IBM ultimately parted ways over the project. One of the major issues appear to have been the clock speeds of the CPUs. The project selected IBM in 2007 as the supercomputer vendor for the Blue Waters project based on projections of future technology development," said IBM spokesperson Joanna Brewer. "The innovative technology that IBM ultimately developed was more complex and required significantly increased financial and technical support by IBM beyond its original expectations. We are not going into specifics."
Information from the Blue Waters Change Control Board suggests that the organization was willing to accept IBM's delays, but balked at paying the same price for the same amount of equipment when the hardware was going to arrive a year behind schedule.
We're not surprised to hear clock speeds were problematic, given how tightly components were packed into the system. Even with water cooling, that's a lot of heat.
The change request delays the delivery of Blue Waters by a year, as compared to the original request. While we understand that the original schedule is not achievable any more, we are also keenly aware that the one-year delay reduces the value of the system to the research community, NSF and the University of Illinois, and increases the expenses incurred by the University and NSF.
"While one can debate the magnitude of this damage, and the proper compensation for it, it does not seem reasonable to us to accept a change to the schedule with no compensation (e.g., in forms of additional equipment) for the reduced value of the system."
By this spring, the control board was distinctly unhappy, noting that IBM "has not agreed to a new schedule nor has it agreed to address the issue of the change in value of the system resulting from the one-year delay." In the weeks before negotiation broke down entirely, the NCSA noted that it had agreed to 36 changes to the Blue Waters project, "the vast majority proposed by or for the benefit of IBM."
With the project terminated,its leaders have hinted that IBM may be on the rope for additional penalties. Chancellor Robert Easter wrote to IBM this spring, noting that the National Science Foundation and the University of Illinois had received "scant benefit" from the equipment IBM had provided to date. Other documentation appears to back this up; there are reports of IBM workers showing up to remove three racks of POWER 7 servers. Given that both organizations had invested millions towards getting Blue Waters up and running, the loan of three racks of servers, even powerful ones, seems scant payback indeed.
New details have come to light on why the University of Illinois and IBM ultimately parted ways over the project. One of the major issues appear to have been the clock speeds of the CPUs. The project selected IBM in 2007 as the supercomputer vendor for the Blue Waters project based on projections of future technology development," said IBM spokesperson Joanna Brewer. "The innovative technology that IBM ultimately developed was more complex and required significantly increased financial and technical support by IBM beyond its original expectations. We are not going into specifics."
Information from the Blue Waters Change Control Board suggests that the organization was willing to accept IBM's delays, but balked at paying the same price for the same amount of equipment when the hardware was going to arrive a year behind schedule.
We're not surprised to hear clock speeds were problematic, given how tightly components were packed into the system. Even with water cooling, that's a lot of heat.
The change request delays the delivery of Blue Waters by a year, as compared to the original request. While we understand that the original schedule is not achievable any more, we are also keenly aware that the one-year delay reduces the value of the system to the research community, NSF and the University of Illinois, and increases the expenses incurred by the University and NSF.
"While one can debate the magnitude of this damage, and the proper compensation for it, it does not seem reasonable to us to accept a change to the schedule with no compensation (e.g., in forms of additional equipment) for the reduced value of the system."
By this spring, the control board was distinctly unhappy, noting that IBM "has not agreed to a new schedule nor has it agreed to address the issue of the change in value of the system resulting from the one-year delay." In the weeks before negotiation broke down entirely, the NCSA noted that it had agreed to 36 changes to the Blue Waters project, "the vast majority proposed by or for the benefit of IBM."
With the project terminated,its leaders have hinted that IBM may be on the rope for additional penalties. Chancellor Robert Easter wrote to IBM this spring, noting that the National Science Foundation and the University of Illinois had received "scant benefit" from the equipment IBM had provided to date. Other documentation appears to back this up; there are reports of IBM workers showing up to remove three racks of POWER 7 servers. Given that both organizations had invested millions towards getting Blue Waters up and running, the loan of three racks of servers, even powerful ones, seems scant payback indeed.
