Index: benchmark/readyQ/cycle.cfa
===================================================================
--- benchmark/readyQ/cycle.cfa	(revision 2c7eee0158db97464d1d3b620031d72e9b57e264)
+++ benchmark/readyQ/cycle.cfa	(revision b5d51b0425ffb223de40252899e6cd34651705f4)
@@ -84,5 +84,5 @@
 		}
 
-		printf("Duration (ms)        : %'ld\n", (end - start)`ms);
+		printf("Duration (ms)        : %'ld\n", (end - start)`dms);
 		printf("Number of processors : %'d\n", nprocs);
 		printf("Number of threads    : %'d\n", tthreads);
@@ -90,10 +90,10 @@
 		printf("Total Operations(ops): %'15llu\n", global_counter);
 		printf("Total blocks         : %'15llu\n", global_blocks);
-		printf("Ops per second       : %'18.2lf\n", ((double)global_counter) / (end - start)`s);
-		printf("ns per ops           : %'18.2lf\n", ((double)(end - start)`ns) / global_counter);
+		printf("Ops per second       : %'18.2lf\n", ((double)global_counter) / (end - start)`ds);
+		printf("ns per ops           : %'18.2lf\n", (end - start)`dns / global_counter);
 		printf("Ops per threads      : %'15llu\n", global_counter / tthreads);
 		printf("Ops per procs        : %'15llu\n", global_counter / nprocs);
-		printf("Ops/sec/procs        : %'18.2lf\n", (((double)global_counter) / nprocs) / (end - start)`s);
-		printf("ns per ops/procs     : %'18.2lf\n", ((double)(end - start)`ns) / (global_counter / nprocs));
+		printf("Ops/sec/procs        : %'18.2lf\n", (((double)global_counter) / nprocs) / (end - start)`ds);
+		printf("ns per ops/procs     : %'18.2lf\n", (end - start)`dns / (global_counter / nprocs));
 		fflush(stdout);
 	}
Index: benchmark/readyQ/cycle.go
===================================================================
--- benchmark/readyQ/cycle.go	(revision 2c7eee0158db97464d1d3b620031d72e9b57e264)
+++ benchmark/readyQ/cycle.go	(revision b5d51b0425ffb223de40252899e6cd34651705f4)
@@ -72,5 +72,5 @@
 	p.Printf("Cycle size (# thrds) : %d\n", ring_size);
 	p.Printf("Total Operations(ops): %15d\n", global_counter)
-	p.Printf("Yields per second    : %18.2f\n", float64(global_counter) / delta.Seconds())
+	p.Printf("Ops per second       : %18.2f\n", float64(global_counter) / delta.Seconds())
 	p.Printf("ns per ops           : %18.2f\n", float64(delta.Nanoseconds()) / float64(global_counter))
 	p.Printf("Ops per threads      : %15d\n", global_counter / uint64(tthreads))
Index: benchmark/readyQ/rq_bench.hfa
===================================================================
--- benchmark/readyQ/rq_bench.hfa	(revision 2c7eee0158db97464d1d3b620031d72e9b57e264)
+++ benchmark/readyQ/rq_bench.hfa	(revision b5d51b0425ffb223de40252899e6cd34651705f4)
@@ -88,5 +88,5 @@
 }
 
-struct bench_sem {
+struct __attribute__((aligned(128))) bench_sem {
 	struct $thread * volatile ptr;
 };
Index: benchmark/readyQ/rq_bench.hpp
===================================================================
--- benchmark/readyQ/rq_bench.hpp	(revision 2c7eee0158db97464d1d3b620031d72e9b57e264)
+++ benchmark/readyQ/rq_bench.hpp	(revision b5d51b0425ffb223de40252899e6cd34651705f4)
@@ -75,5 +75,5 @@
 }
 
-class bench_sem {
+class __attribute__((aligned(128))) bench_sem {
 	Fibre * volatile ptr = nullptr;
 public: