mirror of
https://github.com/duggasco/bc250-40cu-unlock.git
synced 2026-07-18 02:51:30 +00:00
cdfeb5171b
New tools for boards with scattered harvest patterns where unlocked CUs may be defective: - bc250-compute-verify.sh: Heavy Vulkan correctness test (FP32 FMA, integer, bitwise, LDS) with per-element golden comparison - bc250-cu-health-test.sh: Reboot-resuming 20-WGP isolation test using amdgpu.disable_cu. Results to /var/lib/bc250-cu-health-test/results.tsv - bc250-cu-mask.sh: Generates selective disable_cu= config from failed WGPs — enables e.g. 38 of 40 CUs with bad ones masked - cu_map.sh: Updated with --health overlay showing stock + healthy/failed Usage: sudo ./scripts/bc250-cu-health-test.sh start # full 20-WGP test ./scripts/bc250-cu-mask.sh --results results.tsv # generate mask ./scripts/cu_map.sh --health results.tsv # visual overlay Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
136 lines
3.2 KiB
Bash
Executable File
136 lines
3.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# bc250-cu-mask.sh - generate/install selective WGP masks for BC-250 40-CU unlock.
|
|
|
|
set -euo pipefail
|
|
|
|
RESULTS="${BC250_CU_HEALTH_RESULTS:-/var/lib/bc250-cu-health-test/results.tsv}"
|
|
CONF="${BC250_CU_MASK_CONF:-/etc/modprobe.d/bc250-40cu-selective-mask.conf}"
|
|
INSTALL=0
|
|
BAD_ITEMS=()
|
|
TMP_CONF="$(mktemp)"
|
|
trap 'rm -f "$TMP_CONF"' EXIT
|
|
|
|
usage() {
|
|
cat <<EOF
|
|
Usage: $0 [--results FILE] [--bad SE.SH.WGP[,SE.SH.WGP...]] [--bad-cu SE.SH.CU[,SE.SH.CU...]] [--install]
|
|
|
|
Examples:
|
|
$0 --bad 1.0.3
|
|
$0 --results /var/lib/bc250-cu-health-test/results.tsv --install
|
|
$0 --bad-cu 1.0.6,1.0.7 --install
|
|
|
|
Output modprobe config:
|
|
options amdgpu bc250_cc_write_mode=3 disable_cu=SE.SH.CU,...
|
|
|
|
WGP is the hardware disable granularity. Each bad WGP expands to both CUs.
|
|
EOF
|
|
}
|
|
|
|
die() {
|
|
echo "ERROR: $*" >&2
|
|
exit 1
|
|
}
|
|
|
|
split_csv() {
|
|
local item
|
|
IFS=',' read -ra _items <<<"$1"
|
|
for item in "${_items[@]}"; do
|
|
[ -n "$item" ] && BAD_ITEMS+=("$item")
|
|
done
|
|
}
|
|
|
|
while [ "$#" -gt 0 ]; do
|
|
case "$1" in
|
|
--results)
|
|
RESULTS="${2:?missing value for --results}"
|
|
shift 2
|
|
;;
|
|
--bad)
|
|
split_csv "${2:?missing value for --bad}"
|
|
shift 2
|
|
;;
|
|
--bad-cu)
|
|
IFS=',' read -ra _cus <<<"${2:?missing value for --bad-cu}"
|
|
for cu_item in "${_cus[@]}"; do
|
|
IFS='.' read -r se sh cu <<<"$cu_item"
|
|
[[ "$se" =~ ^[0-1]$ && "$sh" =~ ^[0-1]$ && "$cu" =~ ^[0-9]$ ]] ||
|
|
die "invalid CU entry: $cu_item"
|
|
BAD_ITEMS+=("$se.$sh.$((cu / 2))")
|
|
done
|
|
shift 2
|
|
;;
|
|
--install)
|
|
INSTALL=1
|
|
shift
|
|
;;
|
|
-h|--help)
|
|
usage
|
|
exit 0
|
|
;;
|
|
*)
|
|
die "unknown argument: $1"
|
|
;;
|
|
esac
|
|
done
|
|
|
|
if [ "${#BAD_ITEMS[@]}" -eq 0 ] && [ -f "$RESULTS" ]; then
|
|
while IFS=$'\t' read -r idx se sh wgp status rest; do
|
|
case "$idx" in ""|\#*) continue ;; esac
|
|
[ "$status" = "FAIL" ] || continue
|
|
BAD_ITEMS+=("$se.$sh.$wgp")
|
|
done <"$RESULTS"
|
|
fi
|
|
|
|
declare -A seen_wgp=()
|
|
declare -A seen_cu=()
|
|
bad_wgps=()
|
|
disable_cus=()
|
|
|
|
for item in "${BAD_ITEMS[@]}"; do
|
|
IFS='.' read -r se sh wgp <<<"$item"
|
|
[[ "$se" =~ ^[0-1]$ && "$sh" =~ ^[0-1]$ && "$wgp" =~ ^[0-4]$ ]] ||
|
|
die "invalid WGP entry: $item"
|
|
key="$se.$sh.$wgp"
|
|
if [ -z "${seen_wgp[$key]+x}" ]; then
|
|
seen_wgp[$key]=1
|
|
bad_wgps+=("$key")
|
|
fi
|
|
for cu in $((wgp * 2)) $((wgp * 2 + 1)); do
|
|
cu_key="$se.$sh.$cu"
|
|
if [ -z "${seen_cu[$cu_key]+x}" ]; then
|
|
seen_cu[$cu_key]=1
|
|
disable_cus+=("$cu_key")
|
|
fi
|
|
done
|
|
done
|
|
|
|
disable_csv="$(IFS=,; echo "${disable_cus[*]}")"
|
|
|
|
{
|
|
echo "# BC-250 selective 40-CU mask."
|
|
echo "# Generated by $0 on $(date -Iseconds)."
|
|
echo "# Bad WGPs: ${bad_wgps[*]:-none}"
|
|
echo "# Requires patched amdgpu with bc250_cc_write_mode support."
|
|
if [ -n "$disable_csv" ]; then
|
|
echo "options amdgpu bc250_cc_write_mode=3 disable_cu=$disable_csv"
|
|
else
|
|
echo "options amdgpu bc250_cc_write_mode=3"
|
|
fi
|
|
} >"$TMP_CONF"
|
|
|
|
if [ "$INSTALL" -eq 1 ]; then
|
|
[ "$(id -u)" = "0" ] || die "--install requires root"
|
|
install -m 0644 "$TMP_CONF" "$CONF"
|
|
echo "Installed $CONF"
|
|
if command -v update-initramfs >/dev/null 2>&1; then
|
|
update-initramfs -u -k "$(uname -r)" || true
|
|
elif command -v dracut >/dev/null 2>&1; then
|
|
dracut -f || true
|
|
fi
|
|
else
|
|
cat "$TMP_CONF"
|
|
fi
|
|
|
|
usable=$((40 - ${#bad_wgps[@]} * 2))
|
|
echo "# Usable after mask: $usable/40 CUs (${#bad_wgps[@]} bad WGPs masked)"
|