They asked me to write a tiled matmul kernel in Triton. On the second interview they asked me about SSA, given a loop, draw it in SSA form.
Then they asked me to write the same loop in MLIR scf dialect. Then they asked me about GPU memory hierarchy and how I would parallelize 2 nested loops. Then they asked me about Dead Code Elimination, particularly, how I'd build a pass that does that optimization.
They asked me to write a tilled matmul kernel in Triton. On the second interview they asked me about SSA, given a loop, draw it in SSA form.
Then they asked me to write the same loop in MLIR scf dialect. Then they asked me about GPU memory hierarchy and how I would parallelize 2 nested loops. Then they asked me about Dead Code Elimination, particularly, how I'd build a pass that does that optimization.
The following metrics were computed from 1 interview experience for the Intel Compiler Engineer Intern role in Santa Clara, California.
Intel's interview process for their Compiler Engineer Intern roles in Santa Clara, California is extremely selective, failing the vast majority of engineers.
Candidates reported having very negative feelings for Intel's Compiler Engineer Intern interview process in Santa Clara, California.