diff --git a/sdk/software/examples/asm/user-sample.c b/sdk/software/examples/asm/user-sample.c
index 124aa31..7f98fd8 100644
--- a/sdk/software/examples/asm/user-sample.c
+++ b/sdk/software/examples/asm/user-sample.c
@@ -11,11 +11,8 @@
  */
 
 #include <stdio.h>
-#include <stdbool.h>
 #include <stdint.h>
 
-#include <common_func.h>
-#include <confreg_time.h>
 #include <dma.h>
 
 /* ─── Configurable group count (default 5000) ──────────────────────── */
@@ -68,14 +65,13 @@ int main(void)
     if (MATMUL_GROUP_NUM <= 0) return 0;
 
     /* ── Hot-path local volatile pointers (one-time addr calc) ──────── */
-    volatile uint32_t *extram     = (volatile uint32_t *)EXTRAM_BASE_UNCACHED;
     volatile uint32_t *mat_status = (volatile uint32_t *)MATMUL_STATUS;
     volatile uint32_t *mat_ctrl   = (volatile uint32_t *)MATMUL_CTRL;
     volatile uint32_t *mat_crc    = (volatile uint32_t *)MATMUL_CRC;
     volatile dma_ch_regs_t *ch0   = DMA_CH(0);
     volatile dma_ch_regs_t *ch1   = DMA_CH(1);
 
-    uint32_t crc, t_prologue, t_mainloop, t_epilogue;
+    uint32_t crc;
     int g, bank;
 
     // Ping-Pong Register Address Arrays (Physical for DMA)
@@ -93,7 +89,6 @@ int main(void)
     /* ═══════════════════════════════════════════════════════════════
      * PROLOGUE: Load group 0 → Bank 0, start IP, pre-fire group 1
      * ═══════════════════════════════════════════════════════════════ */
-    t_prologue = get_ns();
 
     // DMA Ch0: Load group 0 A+B (128 bytes) → IP Bank 0
     ch0->SRC_ADDR = EXTRAM_PHYS_AB(0);
@@ -116,8 +111,6 @@ int main(void)
         ch0->CTRL     = DMA_CTRL_VAL;
     }
 
-    t_prologue = get_ns() - t_prologue;
-
     /* ═══════════════════════════════════════════════════════════════
      * MAIN LOOP: Fully-pipelined — pre-fire DMA load at loop tail
      *
@@ -130,7 +123,6 @@ int main(void)
      *   Ch1:         | store g-1 |              | store g |
      *   IP :         | compute g |              | compute g+1 |
      * ═══════════════════════════════════════════════════════════════ */
-    t_mainloop = get_ns();
     bank = 1;  // cur_bank for iteration g=1; prev_bank = bank ^ 1
 
     for (g = 1; g < MATMUL_GROUP_NUM; g++) {
@@ -175,12 +167,10 @@ int main(void)
         // Toggle bank for next iteration
         bank ^= 1;
     }
-    t_mainloop = get_ns() - t_mainloop;
 
     /* ═══════════════════════════════════════════════════════════════
      * EPILOGUE: Flush the final group
      * ═══════════════════════════════════════════════════════════════ */
-    t_epilogue = get_ns();
 
     // Wait for last IP computation
     while (!(*mat_status & STATUS_DONE)) {}
@@ -198,18 +188,10 @@ int main(void)
     while (!(ch1->STATUS & STATUS_DONE_BIT)) {}
     ch1->STATUS = STATUS_DONE_BIT;
 
-    t_epilogue = get_ns() - t_epilogue;
-
     /* ── Read hardware CRC32 ──────────────────────────────────── */
     crc = *mat_crc;
 
-    /* ── Standard markers (required by test harness) ────────────── */
     printf("MATMUL_CRC32=%08lx\n", (unsigned long)crc);
-    printf("TIME_PROLOGUE=%lu\n", (unsigned long)t_prologue);
-    printf("TIME_LOOP=%lu\n", (unsigned long)t_mainloop);
-    printf("TIME_LOOP_PER=%lu\n", (unsigned long)(t_mainloop / MATMUL_GROUP_NUM));
-    printf("TIME_EPILOGUE=%lu\n", (unsigned long)t_epilogue);
-    printf("TIME_TOTAL=%lu\n", (unsigned long)(t_prologue + t_mainloop + t_epilogue));
     printf("MATMUL_DONE\n");
 
     return 0;