← CUDA, Triton & Kernel Engineering / 31

hardNew

Map a fused bias-GELU kernel to threads and verify the final partial block

Derive row-major offsets, broadcast the bias correctly, and compare a lane-by-lane CPU reference with a vector expression. Explain when shared memory adds no reuse.

Updated Sep 2026 · Learn how AI infrastructure works through explanations, worked examples and diagrams, then practise applying it to interview questions.

Derive row-major offsets, broadcast the bias correctly, and compare a lane-by-lane CPU reference with a vector expression. Explain when shared memory adds no reuse.

The full answer is part of Premium. A free account includes more answers in each topic, but does not unlock this one.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 303 remaining answers · ₹2,000 / $25

The concepts behind this question

Use these concept explanations to review the ideas behind this question.

⚡ Kernels & Compilers

Kernel FusionKernel fusion combines operations so intermediate results can stay on-chip. It can reduce memory traffic and launch overhead, but may increase resource pressure.

🧮 Open Weights & Serving Engines

Weight Formats: FP8 Blocks, MXFP4 and AWQDerive the storage cost of low-precision tensors, including scales, zero points and higher-precision exceptions. Distinguish formats from quantization methods, understand fused dequantization, and test whether a smaller checkpoint actually improves serving capacity without unacceptable quality loss.

🧩 GPU & Accelerator ArchitectureSign in

Numerics: FP32, BF16, FP8 and FP4Floating-point formats trade range and precision for storage and compute cost. Understand exponent bits, significand bits, scaling and accumulation before choosing a format.

⚡ Kernels & Compilers

CUDA Programming ModelCUDA programs launch GPU kernels from host code. Thread indexing, memory access and stream ordering determine whether the result is correct.

Explore the full curriculum →

UP NEXT ON YOUR JOURNEY

Closest to this topicWhy fuse kernels, how much does it save, and what can fusion not fix?Closest to this topicImplement a log-structured event store for fleet metrics with range queries and compaction.Closest to this topicYour fused attention kernel matches the reference at 512 tokens and drifts at 8,000. Find the bug.

DISCUSSION · 0

No comments yet — be the first to share your approach.