data/gpu_specs.yaml

# GPU Perf Prophet GPU spec database (schema_version 1.0). spec_confidence: verified = vendor spec sheet/whitepaper, estimated = derived from architecture docs/cross-refs. peak_tflops are DENSE (no structured sparsity); AMD uses MFMA instruction peak, NVIDIA uses Tensor Core peak for BF16/FP16/FP8 and scalar CUDA-core for FP32; hbm_bandwidth_tbps is peak theoretical; ~ (null) means unsupported on that GPU. in_model_scope true = exposed as a v1 recommendation target, false = in the training corpus only (Blackwell family, edge GPUs, multi-SKU combos). aliases = every unique accelerator_model_name seen in MLPerf v4.1–v6.0 system JSONs for this GPU, incl. case/suffix variants without the "(xN)" count specifier.

schema_version: "1.0"

gpus:

  # ── AMD Instinct CDNA3 ─────────────────────────────────────────────────

  - id: mi300x
    name: "AMD Instinct MI300X"
    vendor: amd
    architecture: cdna3
    memory_type: hbm3
    vram_gb: 192
    hbm_bandwidth_tbps: 5.3
    peak_tflops:
      fp32: 163.4
      bf16: 1307.4
      fp16: 1307.4
      fp8:  2614.9
      fp6:  ~             # not supported natively in CDNA3
      fp4:  ~             # not supported natively in CDNA3
      int8: 2614.9
    compute_units: 304
    l2_cache_mb: 32
    tdp_w: 750
    spec_confidence: verified   # AMD MI300X Data Sheet, Dec 2023
    in_model_scope: true
    aliases:
      - "AMD Instinct MI300X"
      - "AMD Instinct MI300X 192GB HBM3"
      - "AMD Instinct MI300X-NPS1-SPX-192GB-750W"
      - "AMD MI300X-NPS1-SPX-192GB-750W"

  - id: mi325x
    name: "AMD Instinct MI325X"
    vendor: amd
    architecture: cdna3             # same compute die as MI300X; HBM3E memory upgrade
    memory_type: hbm3e
    vram_gb: 256
    hbm_bandwidth_tbps: 6.0
    peak_tflops:
      fp32: 163.4                   # same CDNA3 compute die
      bf16: 1307.4
      fp16: 1307.4
      fp8:  2614.9
      fp6:  ~
      fp4:  ~
      int8: 2614.9
    compute_units: 304
    l2_cache_mb: 32
    tdp_w: 1000
    spec_confidence: verified   # AMD MI325X Announcement, Oct 2024
    in_model_scope: true
    aliases:
      - "AMD Instinct MI325X"
      - "AMD Instinct MI325X 256GB HBM3E"
      - "AMD Instinct MI325X 256GB HBM3e"     # lowercase variant in system JSONs

  # ── AMD Instinct CDNA4 ─────────────────────────────────────────────────

  - id: mi355x
    name: "AMD Instinct MI355X"
    vendor: amd
    architecture: cdna4
    memory_type: hbm3e
    vram_gb: 288
    hbm_bandwidth_tbps: 8.0         # AMD official spec sheet (amd-instinct-mi355x-gpu-brochure.pdf)
    peak_tflops:
      fp32: 157.3                   # AMD official spec sheet — vector FP32; CDNA4 ratio = 16× (vs CDNA3 8×)
      bf16: 2516.6                  # AMD official spec sheet — matrix
      fp16: 2516.6                  # AMD official spec sheet — matrix
      fp8:  5033.2                  # AMD official spec sheet — matrix
      fp6:  10066.3                 # AMD official spec sheet — CDNA4 native FP6
      fp4:  20132.6                 # AMD official spec sheet — MXFP4
      int8: 5033.2                  # AMD official spec sheet
    compute_units: 304              # (est) — not listed on spec sheet; no change
    l2_cache_mb: 32                 # (est)
    tdp_w: 1400                     # AMD official spec sheet (1.4 kW); 1000 W variant observed in MLPerf
    spec_confidence: verified        # confirmed 2026-06-17 against AMD official spec sheet
    in_model_scope: true
    aliases:
      - "AMD Instinct MI355X"
      - "AMD Instinct MI355X 288GB HBM3e"
      - "AMD Instinct MI355X 288GB HBM3e (Power Cap 1000 W)"
      - "AMD Instinct MI355X 288GB HBM3e (x87)"  # (x87) stripped by normalizer

  - id: mi350x
    name: "AMD Instinct MI350X"
    vendor: amd
    architecture: cdna4
    memory_type: hbm3e
    vram_gb: 288
    hbm_bandwidth_tbps: 8.0         # AMD official spec sheet (amd-instinct-mi350x-gpu-brochure.pdf)
    peak_tflops:
      fp32: 144.2                   # vector FP32; 256 CUs × same clock as MI355X die; confirmed via platform FP16-vector 1153.6 TFLOPS ÷ 8
      bf16: 2307.0                  # matrix dense; derived from confirmed fp8 (4614.0) using CDNA4 2:1 ratio (verified against MI355X)
      fp16: 2307.0                  # matrix dense; same derivation
      fp8:  4614.0                  # matrix dense; AMD official spec sheet — platform 36.9 PFLOPS ÷ 8 GPUs = 4612.5 ≈ 4614 TFLOPS
      fp6:  9228.0                  # matrix dense; derived from confirmed fp8 × 2 (CDNA4 native MXFP6 support confirmed)
      fp4:  18456.0                 # matrix dense; derived from confirmed fp8 × 4 (CDNA4 native MXFP4 support confirmed)
      int8: 4614.0                  # same as fp8 per AMD CDNA4 pattern
    compute_units: 256              # AMD official spec sheet — 8 XCDs × 32 CUs each
    l2_cache_mb: 32                 # (est)
    tdp_w: 1000                     # AMD official spec sheet — air-cooled 1000W variant (vs MI355X 1400W)
    spec_confidence: verified       # confirmed 2026-06-18 against AMD official spec sheet (amd-instinct-mi350x-gpu-brochure.pdf); bf16/fp6/fp4 derived from confirmed fp8 using CDNA4 ratios
    in_model_scope: false           # spec is verified but scope gate is blocked: LOGO-CV ρ=0.019 (14 rows, 35 rounds) — wait for v7.0+ MLPerf data
    aliases:
      - "AMD Instinct MI350X"
      - "AMD Instinct MI350X 288GB HBM3e"

  # ── NVIDIA Hopper ──────────────────────────────────────────────────────

  - id: h100_sxm
    name: "NVIDIA H100 SXM5"
    vendor: nvidia
    architecture: hopper
    memory_type: hbm3
    vram_gb: 80
    hbm_bandwidth_tbps: 3.35
    peak_tflops:
      fp32: 66.9                    # scalar CUDA-core FP32
      bf16: 989.4                   # Tensor Core, dense
      fp16: 989.4
      fp8:  1978.9
      fp6:  ~
      fp4:  ~
      int8: 3957.8
    streaming_multiprocessors: 132
    l2_cache_mb: 50
    tdp_w: 700
    spec_confidence: verified   # NVIDIA H100 GPU Architecture Whitepaper
    in_model_scope: true
    aliases:
      - "NVIDIA H100-SXM-80GB"
      - "Virtualized NVIDIA H100-SXM-80GB"

  - id: h100_pcie
    name: "NVIDIA H100 PCIe"
    vendor: nvidia
    architecture: hopper
    memory_type: hbm2e
    vram_gb: 80
    hbm_bandwidth_tbps: 2.0
    peak_tflops:
      fp32: 51.2
      bf16: 756.5
      fp16: 756.5
      fp8:  1513.0
      fp6:  ~
      fp4:  ~
      int8: 3026.0
    streaming_multiprocessors: 114
    l2_cache_mb: 50
    tdp_w: 350
    spec_confidence: verified   # NVIDIA H100 PCIe Datasheet
    in_model_scope: false       # not in v1 scope; included for training signal
    aliases:
      - "NVIDIA H100-PCIe-80GB"

  - id: h100_nvl
    name: "NVIDIA H100 NVL"
    vendor: nvidia
    architecture: hopper
    memory_type: hbm3
    vram_gb: 94
    hbm_bandwidth_tbps: 3.93        # (est) scaled from H100 SXM die bandwidth
    peak_tflops:
      fp32: 66.9
      bf16: 989.4                   # same compute die as H100 SXM5
      fp16: 989.4
      fp8:  1978.9
      fp6:  ~
      fp4:  ~
      int8: 3957.8
    streaming_multiprocessors: 132
    l2_cache_mb: 50
    tdp_w: 700                      # (est)
    spec_confidence: estimated
    in_model_scope: false
    aliases:
      - "NVIDIA H100-NVL-94GB"

  - id: h200_sxm
    name: "NVIDIA H200 SXM"
    vendor: nvidia
    architecture: hopper            # same Hopper die as H100; HBM3E memory upgrade
    memory_type: hbm3e
    vram_gb: 141
    hbm_bandwidth_tbps: 4.8
    peak_tflops:
      fp32: 66.9                    # same compute die as H100 SXM5
      bf16: 989.4
      fp16: 989.4
      fp8:  1978.9
      fp6:  ~
      fp4:  ~
      int8: 3957.8
    streaming_multiprocessors: 132
    l2_cache_mb: 50
    tdp_w: 700
    spec_confidence: verified   # NVIDIA H200 Tensor Core GPU Datasheet
    in_model_scope: true
    aliases:
      - "NVIDIA H200-SXM-141GB"
      - "NVIDIA H200-SXM-141GB-CTS"
      - "Virtualized NVIDIA H200-SXM-141GB"

  - id: h200_nvl
    name: "NVIDIA H200 NVL"
    vendor: nvidia
    architecture: hopper
    memory_type: hbm3e
    vram_gb: 141
    hbm_bandwidth_tbps: 4.8         # same HBM3E spec as H200 SXM
    peak_tflops:
      fp32: 66.9
      bf16: 989.4
      fp16: 989.4
      fp8:  1978.9
      fp6:  ~
      fp4:  ~
      int8: 3957.8
    streaming_multiprocessors: 132
    l2_cache_mb: 50
    tdp_w: 600                      # (est) NVL form-factor typically lower TDP
    spec_confidence: estimated
    in_model_scope: false           # not in v1 scope; included for training signal
    aliases:
      - "NVIDIA H200-NVL-141GB"

  # GH200 = H100 GPU die + Grace CPU on NVLink-C2C.  GPU-side specs only.
  - id: gh200_96gb
    name: "NVIDIA GH200 96GB"
    vendor: nvidia
    architecture: hopper
    memory_type: hbm3
    vram_gb: 96
    hbm_bandwidth_tbps: 3.35        # H100 GPU die bandwidth
    peak_tflops:
      fp32: 66.9
      bf16: 989.4
      fp16: 989.4
      fp8:  1978.9
      fp6:  ~
      fp4:  ~
      int8: 3957.8
    streaming_multiprocessors: 132
    l2_cache_mb: 50
    tdp_w: 900                      # full GH200 module TDP
    spec_confidence: verified
    in_model_scope: false
    aliases:
      - "NVIDIA GH200 Grace Hopper Superchip 96GB"

  - id: gh200_144gb
    name: "NVIDIA GH200 144GB"
    vendor: nvidia
    architecture: hopper
    memory_type: hbm3e
    vram_gb: 144
    hbm_bandwidth_tbps: 4.9         # (est) HBM3E variant
    peak_tflops:
      fp32: 66.9
      bf16: 989.4
      fp16: 989.4
      fp8:  1978.9
      fp6:  ~
      fp4:  ~
      int8: 3957.8
    streaming_multiprocessors: 132
    l2_cache_mb: 50
    tdp_w: 900
    spec_confidence: estimated
    in_model_scope: false
    aliases:
      - "NVIDIA GH200 Grace Hopper Superchip 144GB"

  # NVIDIA Ampere — A100 has zero LLM rows in v4.1–v6.0 corpus; specs kept for the recommender's roofline-only fallback.

  - id: a100_sxm_80gb
    name: "NVIDIA A100 SXM4 80GB"
    vendor: nvidia
    architecture: ampere
    memory_type: hbm2e
    vram_gb: 80
    hbm_bandwidth_tbps: 2.0
    peak_tflops:
      fp32: 77.6                    # scalar CUDA-core FP32
      bf16: 312.0                   # Tensor Core, dense
      fp16: 312.0
      fp8:  ~                       # FP8 not supported natively on Ampere
      fp6:  ~
      fp4:  ~
      int8: 624.0
    streaming_multiprocessors: 108
    l2_cache_mb: 40
    tdp_w: 400
    spec_confidence: verified   # NVIDIA A100 GPU Architecture Whitepaper
    in_model_scope: true        # in v1 scope; roofline-only prediction (no training rows)
    aliases:
      - "NVIDIA A100-SXM4-80GB"
      - "NVIDIA A100-SXM-80GB"
      - "NVIDIA A100 80GB"

  # NVIDIA Ada Lovelace — L4 and RTX 4090 have zero LLM rows in corpus; included for recommender.

  - id: l4
    name: "NVIDIA L4"
    vendor: nvidia
    architecture: ada_lovelace
    memory_type: gddr6
    vram_gb: 24
    hbm_bandwidth_tbps: 0.300       # 300 GB/s GDDR6
    peak_tflops:
      fp32: 30.3
      bf16: 121.6                   # Tensor Core, dense
      fp16: 121.6
      fp8:  242.6
      fp6:  ~
      fp4:  ~
      int8: 485.0
    streaming_multiprocessors: 60
    l2_cache_mb: 48
    tdp_w: 72
    spec_confidence: verified   # NVIDIA L4 Tensor Core GPU Datasheet
    in_model_scope: true        # in v1 scope; roofline-only (no training rows)
    aliases:
      - "NVIDIA L4"
      - "NVIDIA L4 24GB"

  - id: l40s
    name: "NVIDIA L40S"
    vendor: nvidia
    architecture: ada_lovelace
    memory_type: gddr6
    vram_gb: 48
    hbm_bandwidth_tbps: 0.864       # 864 GB/s GDDR6
    peak_tflops:
      fp32: 91.6
      bf16: 362.1
      fp16: 362.1
      fp8:  724.1
      fp6:  ~
      fp4:  ~
      int8: 1448.2
    streaming_multiprocessors: 142
    l2_cache_mb: 96
    tdp_w: 350
    spec_confidence: verified   # NVIDIA L40S Datasheet
    in_model_scope: false
    aliases:
      - "NVIDIA L40S"

  - id: rtx4090
    name: "NVIDIA GeForce RTX 4090"
    vendor: nvidia
    architecture: ada_lovelace
    memory_type: gddr6x
    vram_gb: 24
    hbm_bandwidth_tbps: 1.008       # GDDR6X
    peak_tflops:
      fp32: 82.6
      bf16: 165.2                   # Tensor Core, dense
      fp16: 165.2
      fp8:  330.3                   # (est) 2× FP16
      fp6:  ~
      fp4:  ~
      int8: 660.6
    streaming_multiprocessors: 128
    l2_cache_mb: 72
    tdp_w: 450
    spec_confidence: verified   # NVIDIA RTX 4090 Product Specifications
    in_model_scope: true        # in v1 scope; roofline-only (no training rows)
    aliases:
      - "NVIDIA GeForce RTX 4090"
      - "NVIDIA RTX 4090"

  # NVIDIA Blackwell — out of v1 scope; roofline bounds let the model train on corpus rows without ever surfacing them as recommendations.

  - id: b200_sxm
    name: "NVIDIA B200 SXM"
    vendor: nvidia
    architecture: blackwell
    memory_type: hbm3e
    vram_gb: 180                    # as reported in MLPerf system JSONs
    hbm_bandwidth_tbps: 8.0         # (est) Blackwell specification
    peak_tflops:
      fp32: 147.0                   # (est)
      bf16: 2250.0                  # (est)
      fp16: 2250.0                  # (est)
      fp8:  4500.0                  # (est)
      fp6:  ~
      fp4:  9000.0                  # (est) — Blackwell MXFP4
      int8: 9000.0                  # (est)
    streaming_multiprocessors: 160  # (est)
    l2_cache_mb: 96                 # (est)
    tdp_w: 1000                     # (est)
    spec_confidence: estimated
    in_model_scope: false           # Blackwell explicitly out of v1 scope
    aliases:
      - "NVIDIA B200-SXM-180GB"

  - id: b300_sxm
    name: "NVIDIA B300 SXM"
    vendor: nvidia
    architecture: blackwell
    memory_type: hbm3e
    vram_gb: 270                    # as reported in MLPerf system JSONs
    hbm_bandwidth_tbps: 10.0        # (est)
    peak_tflops:
      fp32: 147.0                   # (est)
      bf16: 2250.0                  # (est)
      fp16: 2250.0                  # (est)
      fp8:  4500.0                  # (est)
      fp6:  ~
      fp4:  9000.0                  # (est)
      int8: 9000.0                  # (est)
    streaming_multiprocessors: 160  # (est)
    l2_cache_mb: 96                 # (est)
    tdp_w: 1200                     # (est)
    spec_confidence: estimated
    in_model_scope: false
    aliases:
      - "NVIDIA B300-SXM-270GB"

  # GB200 NVL module = 2x B200 GPU dies + 2x Grace CPUs; specs are per-module, and num_gpus normalization treats the module as the unit (matching MLPerf's accelerators_per_node reporting).
  - id: gb200
    name: "NVIDIA GB200 NVL"
    vendor: nvidia
    architecture: blackwell
    memory_type: hbm3e
    vram_gb: 384                    # 2× 192 GB per NVL72 spec (est)
    hbm_bandwidth_tbps: 16.0        # (est) 2× B200
    peak_tflops:
      fp32: 294.0                   # (est) 2× B200
      bf16: 4500.0                  # (est) 2× B200
      fp16: 4500.0                  # (est)
      fp8:  9000.0                  # (est)
      fp6:  ~
      fp4:  18000.0                 # (est)
      int8: 18000.0                 # (est)
    streaming_multiprocessors: 320  # (est) 2× B200
    l2_cache_mb: 192                # (est)
    tdp_w: 2700                     # (est) full NVL module
    spec_confidence: estimated
    in_model_scope: false
    aliases:
      - "NVIDIA GB200"

  - id: gb300
    name: "NVIDIA GB300"
    vendor: nvidia
    architecture: blackwell
    memory_type: hbm3e
    vram_gb: 384                    # (est)
    hbm_bandwidth_tbps: 16.0        # (est)
    peak_tflops:
      fp32: 294.0                   # (est)
      bf16: 4500.0                  # (est)
      fp16: 4500.0                  # (est)
      fp8:  9000.0                  # (est)
      fp6:  ~
      fp4:  18000.0                 # (est)
      int8: 18000.0                 # (est)
    streaming_multiprocessors: 320  # (est)
    l2_cache_mb: 192                # (est)
    tdp_w: 2700                     # (est)
    spec_confidence: estimated
    in_model_scope: false
    aliases:
      - "NVIDIA GB300"