FHElium

Appearance

‹ All benchmarks

AMD Ryzen Threadripper PRO 7975WX 32-Cores

2026-09-08 · Linux · PyTorch 2.13.0+cu130

N = 65,536 · Scale 250

ScalingThroughput
Log Y

Workloads and operations

PT × CT matrix multiplication

64 × 64 · Entry depth 0
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)00.511.52124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 1.67AMD Ryzen Threadripper PRO 7975WX 32-Cores · 1.12AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.738AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.825AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.835
HoistingOn

CT × CT matrix multiplication

64 × 64 · Entry depth 0
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)00.3750.751.131.5124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.918AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.514AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.494AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.479AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.494
HoistingOn

Nonlinear polynomial evaluation

Entry depth 0
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)00.511.52124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 1.09AMD Ryzen Threadripper PRO 7975WX 32-Cores · 1.32AMD Ryzen Threadripper PRO 7975WX 32-Cores · 1.43AMD Ryzen Threadripper PRO 7975WX 32-Cores · 1.22AMD Ryzen Threadripper PRO 7975WX 32-Cores · 0.771

NTT

Entry depth 0
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)0138275413550124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 362AMD Ryzen Threadripper PRO 7975WX 32-Cores · 437AMD Ryzen Threadripper PRO 7975WX 32-Cores · 460AMD Ryzen Threadripper PRO 7975WX 32-Cores · 470AMD Ryzen Threadripper PRO 7975WX 32-Cores · 426

Key switching

Entry depth 0
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)08.7517.526.335124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 24.4AMD Ryzen Threadripper PRO 7975WX 32-Cores · 19.7AMD Ryzen Threadripper PRO 7975WX 32-Cores · 21.1AMD Ryzen Threadripper PRO 7975WX 32-Cores · 19.9AMD Ryzen Threadripper PRO 7975WX 32-Cores · 17.5

RNS arithmetic

Entry depth 0
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)02,2504,5006,7509,000124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 7,590AMD Ryzen Threadripper PRO 7975WX 32-Cores · 8,000AMD Ryzen Threadripper PRO 7975WX 32-Cores · 2,430AMD Ryzen Threadripper PRO 7975WX 32-Cores · 2,110AMD Ryzen Threadripper PRO 7975WX 32-Cores · 2,210

Matrix operations

8 operations

Rotate (1 offset)

Entry depth 0 · Shift +1
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)07.51522.530124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 24.1AMD Ryzen Threadripper PRO 7975WX 32-Cores · 22.1AMD Ryzen Threadripper PRO 7975WX 32-Cores · 17.2AMD Ryzen Threadripper PRO 7975WX 32-Cores · 17AMD Ryzen Threadripper PRO 7975WX 32-Cores · 16.6

Rotate-many (7 offsets)

HoistingOn
Entry depth 0 · Shifts +1…+7 · one input
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)02468124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 6.47AMD Ryzen Threadripper PRO 7975WX 32-Cores · 4.97AMD Ryzen Threadripper PRO 7975WX 32-Cores · 4.59AMD Ryzen Threadripper PRO 7975WX 32-Cores · 4.36AMD Ryzen Threadripper PRO 7975WX 32-Cores · 4.03

Multiply (PT × CT)

Entry depth 0 · No rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)01,1302,2503,3804,500124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 3,860AMD Ryzen Threadripper PRO 7975WX 32-Cores · 2,140AMD Ryzen Threadripper PRO 7975WX 32-Cores · 267AMD Ryzen Threadripper PRO 7975WX 32-Cores · 248AMD Ryzen Threadripper PRO 7975WX 32-Cores · 251

Sum products (8 PT × CT terms)

Entry depth 0 · Sum of eight products · no rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)087.5175263350124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 277AMD Ryzen Threadripper PRO 7975WX 32-Cores · 20.1AMD Ryzen Threadripper PRO 7975WX 32-Cores · 13.5AMD Ryzen Threadripper PRO 7975WX 32-Cores · 14.9AMD Ryzen Threadripper PRO 7975WX 32-Cores · 18.3

Rescale (2 components)

Entry depth 0 · One Q depth group
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)050100150200124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 143AMD Ryzen Threadripper PRO 7975WX 32-Cores · 170AMD Ryzen Threadripper PRO 7975WX 32-Cores · 88.5AMD Ryzen Threadripper PRO 7975WX 32-Cores · 76.9AMD Ryzen Threadripper PRO 7975WX 32-Cores · 93.8

Multiply (CT × CT)

Entry depth 0 · Distinct inputs · no relinearization or rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)03757501,1301,500124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 942AMD Ryzen Threadripper PRO 7975WX 32-Cores · 457AMD Ryzen Threadripper PRO 7975WX 32-Cores · 516AMD Ryzen Threadripper PRO 7975WX 32-Cores · 491AMD Ryzen Threadripper PRO 7975WX 32-Cores · 408

Add (CT + CT)

Entry depth 0 · Same depth and scale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)01,6303,2504,8806,500124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 5,690AMD Ryzen Threadripper PRO 7975WX 32-Cores · 3,630AMD Ryzen Threadripper PRO 7975WX 32-Cores · 797AMD Ryzen Threadripper PRO 7975WX 32-Cores · 863AMD Ryzen Threadripper PRO 7975WX 32-Cores · 927

Relinearize

Entry depth 0 · 3 → 2 components · no rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)07.51522.530124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 24.6AMD Ryzen Threadripper PRO 7975WX 32-Cores · 20.7AMD Ryzen Threadripper PRO 7975WX 32-Cores · 18.1AMD Ryzen Threadripper PRO 7975WX 32-Cores · 17.7AMD Ryzen Threadripper PRO 7975WX 32-Cores · 15.8

Polynomial operations

Additional operations

Square (CT)

Entry depth 0 · Same input · no relinearization or rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)03757501,1301,500124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 949AMD Ryzen Threadripper PRO 7975WX 32-Cores · 427AMD Ryzen Threadripper PRO 7975WX 32-Cores · 455AMD Ryzen Threadripper PRO 7975WX 32-Cores · 475AMD Ryzen Threadripper PRO 7975WX 32-Cores · 413

Multiply scalar & rescale

Entry depth 0 · Scalar −0.3 · one rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)037.575113150124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 123AMD Ryzen Threadripper PRO 7975WX 32-Cores · 98AMD Ryzen Threadripper PRO 7975WX 32-Cores · 73.7AMD Ryzen Threadripper PRO 7975WX 32-Cores · 71.4AMD Ryzen Threadripper PRO 7975WX 32-Cores · 73.6

Advance depth

Entry depth 0 · Multiply by one & rescale
AMD Ryzen Threadripper PRO 7975WX 32-Cores
Throughput (tasks/s)037.575113150124816Batch sizeAMD Ryzen Threadripper PRO 7975WX 32-Cores · 124AMD Ryzen Threadripper PRO 7975WX 32-Cores · 97.5AMD Ryzen Threadripper PRO 7975WX 32-Cores · 73.9AMD Ryzen Threadripper PRO 7975WX 32-Cores · 72.9AMD Ryzen Threadripper PRO 7975WX 32-Cores · 76.4
Measurement conditions
HardwareAMD Ryzen Threadripper PRO 7975WX 32-Cores
Host CPUAMD Ryzen Threadripper PRO 7975WX 32-Cores
Intra-op / inter-op threads32 / 32
PyTorch / CUDA2.13.0+cu130 /
ExecutionEager CKKS and Backend RNS/NTT · prepared inputs and resources
Additional measurements · 2026-09-09245 cases · 20260909T144511Z-e5691286