diff --git a/scripts/scaffold-tuolumne.job b/scripts/scaffold-tuolumne.job
index bbbba33..a22d8c6 100644
--- a/scripts/scaffold-tuolumne.job
+++ b/scripts/scaffold-tuolumne.job
@@ -13,7 +13,8 @@ ml cce/21.0.0 cray-mpich/9.1.0 rocm/7.1.1 rccl/fast-env-slows-mpi
 
 # (1) Avoid libmagma error
 # (2) Removing libmpi may cause segfault on mpi4py import
-export LD_PRELOAD="/opt/rocm-7.1.1/llvm/lib/libomp.so /opt/cray/pe/mpich/9.1.0/ofi/gnu/11.2/lib/libmpi_gnu.so.12"
+# (3-5) undefined symbol: cblas_gemm_f16f16f32
+export LD_PRELOAD="/opt/rocm-7.1.1/llvm/lib/libomp.so /opt/cray/pe/mpich/9.1.0/ofi/gnu/11.2/lib/libmpi_gnu.so.12 /opt/intel/oneapi/mkl/2024.2/lib/libmkl_core.so.2 /opt/intel/oneapi/mkl/2024.2/lib/libmkl_gnu_thread.so.2 /opt/intel/oneapi/mkl/2024.2/lib/libmkl_intel_lp64.so.2"
 
 # Disable direct convolution benchmarking (should speedup warmup by a significant amount, does the below three options together)
 # export MIOPEN_DEBUG_CONV_DIRECT=0