mixle.engines.bitpacked module¶

Packed binary / ternary COMPUTE: exact {-1,+1} and {-1,0,+1} dot products via popcount.

The one sub-byte path that is real arithmetic (not dequant-then-fp32): pack a vector to bits and a . b = D - 2*popcount(a XOR b) (binary) / a two-plane popcount (ternary). The hardware popcount does 64 lanes per instruction with no rounding, and the packed data is 32x smaller than float64.

Performance depends on the fp32 baseline. On Apple silicon, cache-resident GEMM goes through the AMX matrix coprocessor (Accelerate BLAS), which can make this popcount kernel slower; the advantage there is storage and bandwidth rather than compute. On CPUs without a matrix unit, memory-bound problems, or native binary/ternary models where fp32 wastes 32x the bytes, it can be a compute win. The kernel is always exact; select it for the measured regime. The compiled extension is optional (build_kernels.compile_bitpacked_kernels); a correct but slower numpy bitwise_count fallback runs when it is absent.

pack_pm1(x)[source]

Pack a {-1,+1} (or {0,1}) array’s rows to uint64 words; last axis padded to a 64-multiple.

Parameters:: x (Any)
Return type:: ndarray

binary_gemm(a_packed, b_packed, dim)[source]

Exact A @ B.T for {-1,+1} matrices packed by pack_pm1().

a_packed is (N, words) packed rows of A, b_packed is (M, words) packed rows of B (the operand whose columns are dotted), dim is the true bit length. Returns int32 (N, M).