We began to develop Cell immediately after the launch of PlayStation 2 in May 2000. Obviously Cell was positioned as the processor for a next-generation computer entertainment system to succeed PlayStation 2, but we started the development project with a much more ambitious concept. We wanted to create a client processor capable of functioning as the nucleus for software interactions between networks and future computers connected to those networks. We also wanted that processor to be capable of functioning as a server. I was involved in most aspects of Cell's development, including not only the establishment of the basic concept, but semiconductor design as well.

When I first heard about the Cell concept, I felt a pure chill of excitement. I joined Sony Computer Entertainment after its establishment, and I've been involved in the development of processors for all three generations of platforms-PlayStation, PlayStation 2 and PLAYSTATION 3. However, the first encounter with a totally new challenge is always an exciting moment for an engineer. I was absolutely thrilled to have this opportunity to work on the development of this dream processor.

Because the concept of networked computing was at the heart of the Cell development project, we began by defining a design philosophy. Rather than starting with the development of hardware IC packaging, we decided to create a Java virtual machine that could be executed directly. We also decided to incorporate an agent-oriented approach into the hardware, in the form of software that would be able to work with peripheral elements while also operating independently. From the outset, we decided that Cell should be a multicore chip with multiple processor cores. Multiprocessor systems with multiple CPUs were already on the market. We debated until the last possible moment about whether Cell should be a homogenous multicore system with multiple cores based on the same specifications, or a heterogeneous multicore system containing multiple cores with different specifications. The use of multiple processors based on the same specification would increase the complexity of some elements, including the cache system and memory management. This approach would also result in higher costs, since it would be necessary to incorporate these elements for each processor. In contrast, an architecture with multiple processors operating separately under a single processor dedicated to memory management would simplify memory management and provide robust security. This approach would also result in a simpler structure for the multiple processors and allow a smaller package area, thereby helping to reduce costs. After considering these advantages, we ultimately decided on a heterogeneous multicore specification consisting of one PowerPC Processor Element (PPE) and eight Synergistic Processor Elements (SPE).

From its commencement in May 2000, Cell development project was a continuous tightrope walk. Right up to the end I doubted that we'd be able to complete the chip (chuckles). As with any product, the process from the start of development to completion required us to perfect each of the individual elements that made up the finished product. The most difficult challenge was battling with heat.

In developing Cell, we were aiming for 90nm generation manufacturing. A major problem encountered at that time was a major increase in heat resulting from leak current (the phenomenon of current leakage from semiconductors). To increase the operating frequency, it is necessary to raise the operating voltage. However, expanding leak current causes power consumption to increase, triggering an exponential rise in the amount of heat generated. The amount of heat was substantially greater than we'd originally predicted. In fact, the technology had reached a major turning point, and the entire industry was focused on the problem of heat caused by leak current. The second half of the Cell design process was devoted almost entirely to battling with heat.

One way to achieve a fundamental solution to this problem was to reduce the operating voltage. However, because there is variation in the chips, we needed to find a way to control the voltage while also ensuring yield and reliability. Reducing the voltage also reduces power consumption, but if the voltage is too low, the transistor switching mechanism may not work properly, leading to errors after the product is on the market. However, the voltage is controlled on each chip in units of a several tens of millivolts, and the performance of each chip (the maximum voltage at which the chip can operate) is recorded individually during testing. We were able to set the optimal voltage by having the system read these records.

We also approached optimization from an application perspective. With a multicore system, there is always wait time. We added a function that used this wait time to suspend all circuits and cores that were not operating by controlling the clock supply. This is like turning out the lights in rooms or on entire floors where no people are present. Statistically, we can reduce heat by switching off these elements.

Unfortunately there was another dilemma. Games designed to use the full potential of the hardware are naturally going to be highly advanced. Therefore, playing such games leads to a decrease in unused circuits and an increase in power consumption. Several of us wrote a program that would block up the most pipelines, and we used that to establish Thermal Design Power (TDP).

Of course, there were many other challenges apart from heat, including semiconductor packaging, enhancing manufacturing yield, and software development. However, the development team was extremely motivated, and everyone worked from morning to night without noticing the time. Although our schedule was very tight, as engineers we were driven by the challenge of creating the world's most advanced technology. Each problem solved gave the team greater confidence to move on to the next step.

Sony, Sony Computer Entertainment, Toshiba and IBM all focused their total capabilities on the development of Cell. Differences in corporate cultures and philosophies made the project more interesting, although initially there were some problems over leadership. Yet when you work with people everyday in the same place, you gradually begin to understand their thinking. I personally learned a lot from this exposure to corporate cultures and development methods that were different from Sony's. I think that by combining each company's areas of excellence, we were able to create a better prototype chip.

In January 2004, we completed the prototype design and reached the tape-out stage (the completion of semiconductor design). Development team members held a party to celebrate this milestone. We were so happy, and it was a really joyous occasion. The time for relaxation was brief, however, because we immediately had to start work on the installation of the new chip in PLAYSTATION 3. In addition, another project had already been launched to establish manufacturing processes for the 65nm generation. In retrospect, I remember my involvement in the development of Cell as a time of total concentration and relentless effort. It was a major task, but a very fulfilling one. Perhaps that's why we were able to maintain the effort. If I ever have a similar opportunity again, I'll be ready to accept the challenge.

The name "Sony Computer Entertainment" includes the words "computer" and "entertainment." As the name suggests, we're dedicated to the ongoing provision of computer-based entertainment. Engineers need dreams. Just as important is our need to offer the world new dreams. I believe that I must always be in pursuit of a dream. My ambition is to create game consoles that will give enjoyment to the people who play with them, and to create systems that game developers will be delighted to work with. For example, all internet users supply information as well as receive it. In the same way, I believe that the world will be even more exciting if users not only play games but also participate in their development. I look forward to taking up new challenges that will lead to the realization of this dream.