[KongchangAI]
Concept双精度 / FP64计算

FP64

The double-precision floating-point format, a high-precision numeric type required for classical scientific simulation such as climate and fusion modeling. In AI-first supercomputers it is often replaced by low-precision matrix operations or emulated.

Timeline (last 90 days)

Nov 17

FP64 (double-precision floating point) is the 64-bit floating-point operation format in the IEEE 754 standard, providing about 15-17 significant decimal digits of precision.

Unverified50%
Nov 16

GPU throughput on FP32 is usually far higher than on FP64, and the FP64 capability of consumer-grade GPUs is often substantially cut down.

Unverified50%
Nov 13

FP64 has a machine precision of about 2.2×10⁻¹⁶, whereas FP32 has a machine precision of only about 1.2×10⁻⁷.

Unverified50%
Nov 13

On GPUs, FP64 theoretical throughput is typically only 1/2 to 1/32 that of FP32 (depending on architecture) and requires more registers and bandwidth, so optimizing FP64 GEMM is more challenging than lower precision.

Unverified50%
Nov 13

NVIDIA disclosed on its developer blog that the cuBLAS library has added a batch of optimizations targeting FP64, aimed at accelerating scientific simulation.

Unverified50%
Nov 13

The new algorithm paths may differ subtly from old implementations in floating-point rounding order, and simulations sensitive to results need regression comparisons to verify numerical consistency.

Unverified50%
Nov 13

Molecular dynamics software typically uses FP64 as the default precision, because error accumulation in force-field integration directly affects energy conservation and trajectory stability.

Unverified50%
Nov 13

FP64 (double-precision floating point) means representing a floating-point number in 64 binary bits, of which 52 bits are for the mantissa, 11 bits for the exponent and 1 bit for the sign.

Unverified50%

All Facts (8)

Source Articles