OpenAI discloses progress on model-assisted chip design
What happened
On November 18, OpenAI published results from research on model-assisted chip design, covering the Jalapeño chip and work with AMD. Standard cell area fell about 13% and 10% in two Jalapeño compute blocks, and the optimizations were verified in silicon debug. In the AMD work, on a heavily optimized flagship GPU IP baseline, the models delivered up to 14% improvement in power, performance and area (PPA), and some changes went into designs sent to manufacturing. On November 19, The Decoder reported further that OpenAI says the AMD results came in under 5 months, equivalent to about a year of extra optimization progress.
Written by AI from the coverage · updated 2 days ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderOpenAI says its models delivered a year's worth of chip optimization on top of AMD's own engineering
OpenAI 称,与 AMD 合作在不到 5 个月内,将其旗舰 GPU IP 的 PPA(功耗、性能与芯片面积)改善最高达 14 percent,相当于约一年的额外优化进展。
- OpenAI NewsPickOpenAI models cut chip area on Jalapeño and improve AMD GPU design
OpenAI published research on models helping with chip design. Standard cell area on two Jalapeño compute blocks fell about 13% and 10%, and silicon debugging confirmed the optimizations. Work with AMD on a heavily optimized flagship GPU IP baseline reached up to 14% better power, performance and area (PPA), with some changes already in designs sent to manufacturing.
Heat over time
Heat now 5·Comparable peak 19(Nov 19 03:00)·Comparable change over 24 hours -50%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.