diff --git a/hw/ip/spatz/src/spatz_vrf.sv b/hw/ip/spatz/src/spatz_vrf.sv
index 4c132a0..a3773f4 100644
--- a/hw/ip/spatz/src/spatz_vrf.sv
+++ b/hw/ip/spatz/src/spatz_vrf.sv
@@ -53,7 +53,7 @@ module spatz_vrf
     automatic logic [1:0] vreg8 = addr[$clog2(8*NrWordsPerVector) +: 2];
 
     // Barber's pole. Advance the starting bank of each vector by one every eight vector registers.
-    f_bank = addr[$clog2(NrVRFBanks)-1:0] + vreg8;
+    f_bank = addr[$clog2(NrVRFBanks)-1:0];
   endfunction: f_bank
 
   /////////////
diff --git a/sw/spatzBenchmarks/dp-fdotp/main.c b/sw/spatzBenchmarks/dp-fdotp/main.c
index 1d29171..639000c 100644
--- a/sw/spatzBenchmarks/dp-fdotp/main.c
+++ b/sw/spatzBenchmarks/dp-fdotp/main.c
@@ -94,6 +94,10 @@ int main() {
     result[0] = acc;
   }
 
+  // End timer and check if new best runtime
+  if (cid == 0)
+    timer = benchmark_get_cycle() - timer;
+  
   // Wait for all cores to finish
   snrt_cluster_hw_barrier();
 
@@ -101,10 +105,6 @@ int main() {
   if (cid == 0)
     stop_kernel();
 
-  // End timer and check if new best runtime
-  if (cid == 0)
-    timer = benchmark_get_cycle() - timer;
-
   // Check and display results
   if (cid == 0) {
     long unsigned int performance = 1000 * 2 * dotp_l.M / timer;