ROCm dan HIP: Tutorial Mendalam 10 Bab: Realitas Platform: Memahami Ekosistem ROCm

Ekosistem ROCm (Radeon Open Compute) adalah tumpukan perangkat lunak berlapis yang modular, dirancang untuk menghubungkan perangkat keras sumber terbuka dengan komputasi berkinerja tinggi. Ini bukan driver monolitik, melainkan Realitas Pipeline—urutan tahapan penginstalan yang menjamin lingkungan yang stabil dan dapat direproduksi.

1. Hierarki Tumpukan Modular

Komponen ROCm terpisah secara fungsional untuk memungkinkan skalabilitas yang halus. Tumpukan ini mengalir dari AMDGPU Kernel Driver melalui ROCT (Thunk), ROCR (Runtime), dan akhirnya ke HIP API dan Perpustakaan Matematika. Arsitektur ini menuntut proses onboarding yang sistematis.

2. Siklus Pengembangan Instalasi

Realitas platform menentukan rantai ketergantungan yang ketat: satu harus menyelaraskan versi kernel dengan Matriks Dukungan, inisialisasi repositori yang ditandatangani GPG, selesaikan ketergantungan melalui manajer paket bawaan, dan konfigurasikan PATH dan render kelompok untuk mengekspos permukaan perangkat keras ke HIP.

TERMINALbash — 80x24

> Ready. Click "Run" to execute.

QUESTION 1

Which component acts as the 'authoritative gatekeeper' in the ROCm deployment workflow?

The HIP Runtime API

The Support Matrix

The GPG Repository Key

The LLVM Compiler Backend

QUESTION 2

What is the primary purpose of 'Repository Bootstrapping'?

To compile the kernel driver from source.

To establish a trusted link to AMD servers via GPG keys and source mapping.

To allocate VRAM for the first time.

To convert CUDA code to HIP code automatically.

QUESTION 3

Why does the shell usually report 'command not found' for hipcc immediately after installation?

The installation failed silently.

The user lacks permissions to execute the file.

ROCm binaries reside in non-standard versioned directories (e.g., /opt/rocm/bin).

The kernel fusion driver (KFD) is not loaded.

QUESTION 4

Which system group is required for a user to access GPU device files like /dev/kfd?

admin

render (or video)

amd-drivers

compute-users

QUESTION 5

What does the rocminfo utility verify?

Hardware temperature and clock speeds.

The successful handshake between user-space libraries and the kernel driver.

Code syntax errors in HIP applications.

Internet connectivity to AMD's update servers.

✅ Correct!

Yes. rocminfo checks if the HSA (Heterogeneous System Architecture) agents are reachable.

❌ Incorrect

Temperature is checked via rocm-smi; rocminfo is for stack health and topology.