#!/bin/bash
# Run a built binary (poet.elf, test.elf, rbm.elf) with NVBLAS: large
# Armadillo matrix multiplies (v_to_h, h_to_v, CD gradients, ...) get
# transparently offloaded to the GPU via cuBLAS, falling back to the
# system's CPU BLAS (nvblas.conf) for anything NVBLAS doesn't handle.
# No source changes -- this only intercepts BLAS symbol calls at runtime.
#
# Usage: ./run_gpu.sh build/release/poet.elf f "the "
set -euo pipefail
here="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
export NVBLAS_CONFIG_FILE="$here/nvblas.conf"
exec env LD_PRELOAD=libnvblas.so "$@"