News for hackers. Stuff that matters.
Re:Samsung Debuts zHBM Prototype, Stacking Memory Directly o... by _joel on Thursday September 10, 2026 @08:44AM (#49642847)
How many contraction/expansion cylces do you normally see in a DC setting, generally? Is there a measure for that to baseline against?
Re:Samsung Debuts zHBM Prototype, Stacking Memory Directly o... by bearjaws on Thursday September 10, 2026 @10:08AM (#49643962)
IIRC it's thousands per day on these systems, mainly due to high power density and low mass, even small lapses in computation (100-500ms) rapidly change the temperatures of stacked die.

So even a GPU averaging 98% utilization may have thousands of cycles per day.

Compared to a regular server blade it may be dozens or barely any at all.

Re:Samsung Debuts zHBM Prototype, Stacking Memory Directly o... by venussnatch on Thursday September 10, 2026 @11:50AM (#49645794)
Naive question, but could this not be fixed by a scheduler? If it's only idle 2% of the time, give it busy work for that 2%
Re:Samsung Debuts zHBM Prototype, Stacking Memory Directly o... by adgjlsfhk1 on Thursday September 10, 2026 @12:00PM (#49645960)
the easier answer would be to remove the ability to idle