61759c51b5
research/determinism-cost.md §4.6, in the same record and by the same procedure: the 192 payloads decoded again on every platform with every kernel set it runs (15 new runs, 0 decodes differing from the record's), and the record's time and energy runs repeated in one session per host beside the record's own build and the float decoder. On x86_64 host A the integer decode on the narrow kernels took 144.8 ms and 12.43 J of marginal package energy at quality 6 against 210.7 ms and 14.03 J for the float decode beside it (the record's build: 728.0 ms, 92.14 J). On the build host its own CPU energy fell from 11.01 J to 6.43 J at quality 6 and is still above the float decode's 1.28 J by that count. Host B's integer decode was measured before and after, without a float decode beside it. The scripts that took the readings are in runs/; decode-throughput.md notes the new sets; the changelog records the change. Co-Authored-By: Claude Opus 5.5 <[email protected]>
10 lines
660 B
Shell
10 lines
660 B
Shell
# Build the CPU and GPU (ops_gpu) integer decoders from ~/wai-build/idf/src into bin/{native,gpu}.<tag>.
|
|
set -euo pipefail
|
|
R=$HOME/wai-build/idf; W=$R/work; export CARGO_TARGET_DIR=$R/target # the toolchain: rustup 1.98.0 on PATH
|
|
TAG=${1:?tag}
|
|
cd $R/src/wai/wai-rs
|
|
nice -n 10 cargo build --locked --release --no-default-features --features neural_int --bin wai_det_cost -j 16 2>&1 | tail -1
|
|
cp $CARGO_TARGET_DIR/release/wai_det_cost $R/bin/native.$TAG
|
|
nice -n 10 cargo build --locked --release --no-default-features --features neural_int,ops_gpu --bin wai_det_cost -j 16 2>&1 | tail -1
|
|
cp $CARGO_TARGET_DIR/release/wai_det_cost $R/bin/gpu.$TAG
|
|
ls -la $R/bin
|