diff --git a/sdk/software/examples/asm/Makefile b/sdk/software/examples/asm/Makefile
index dfb310f..8e3e323 100644
--- a/sdk/software/examples/asm/Makefile
+++ b/sdk/software/examples/asm/Makefile
@@ -10,3 +10,6 @@ COMMON_DIR = ../../bsp
 GCC_DIR=../../../toolchains/loongson-gnu-toolchain-8.3-x86_64-loongarch32r-linux-gnusf-v2.0
 PICOLIBC_DIR=../../../toolchains/picolibc
 include ../../bsp/common.mk
+
+# Strip picolibc: no -lc -lm -lg -lsemihost, keep -lgcc only
+LDFLAGS := $(filter-out -lc -lm -lg -lsemihost,$(LDFLAGS))
diff --git a/sdk/software/examples/asm/dma.c b/sdk/software/examples/asm/dma.c
index 52fcc5e..312d33c 100644
--- a/sdk/software/examples/asm/dma.c
+++ b/sdk/software/examples/asm/dma.c
@@ -1,6 +1,6 @@
 #include "dma.h"
 
-void dma_start_transfer(int ch_id, uint32_t src, uint32_t dst, uint32_t bytes, uint32_t tag) {
+void dma_start_transfer(int ch_id, u32 src, u32 dst, u32 bytes, u32 tag) {
     volatile dma_ch_regs_t* ch = DMA_CH(ch_id);
 
     // 检查通道是否空闲 防止覆盖正在运行的任务
@@ -18,7 +18,7 @@ void dma_start_transfer(int ch_id, uint32_t src, uint32_t dst, uint32_t bytes, u
     // 置 Burst 属性并触发传输
     // AXI SIZE: 2 (代表 2^2 = 4 Bytes，与 32-bit 数据线匹配)
     // AXI LEN: 15 (代表 16 beats 突发传输，最高效)
-    uint32_t ctrl_val = CTRL_BURST_SIZE(2) | CTRL_BURST_LEN(63);
+    u32 ctrl_val = CTRL_BURST_SIZE(2) | CTRL_BURST_LEN(63);
     
     // 写入 CTRL 并拉高 Bit 0 (Start)
     ch->CTRL = ctrl_val | CTRL_START_BIT;
diff --git a/sdk/software/examples/asm/dma.h b/sdk/software/examples/asm/dma.h
index 8187fb9..5c60bcd 100644
--- a/sdk/software/examples/asm/dma.h
+++ b/sdk/software/examples/asm/dma.h
@@ -1,16 +1,15 @@
 #pragma once
 
-#include <stdint.h>
-
+typedef unsigned int u32;
 
 typedef struct {
-    volatile uint32_t SRC_ADDR;  // 0x00: 源地址
-    volatile uint32_t DST_ADDR;  // 0x04: 目的地址
-    volatile uint32_t LENGTH;    // 0x08: 传输总字节数
-    volatile uint32_t TAG;       // 0x0C: 软件 Tag (硬件不处理，留给软件标记任务用)
-    volatile uint32_t CTRL;      // 0x10: 控制寄存器 (配置 Burst 属性 + 启动)
-    volatile uint32_t STATUS;    // 0x14: 状态寄存器 (Busy, Done)
-    volatile uint32_t RESV[10];  // 0x18 ~ 0x3C: 保留空间，凑齐 0x40 字节
+    volatile u32 SRC_ADDR;  // 0x00: source address
+    volatile u32 DST_ADDR;  // 0x04: destination address
+    volatile u32 LENGTH;    // 0x08: transfer byte count
+    volatile u32 TAG;       // 0x0C: software tag (ignored by HW)
+    volatile u32 CTRL;      // 0x10: control (burst config + start)
+    volatile u32 STATUS;    // 0x14: status (busy, done)
+    volatile u32 RESV[10];  // 0x18 ~ 0x3C: padding to 0x40 bytes
 } dma_ch_regs_t;
 
 // DMA 控制器基地址
@@ -26,5 +25,5 @@ typedef struct {
 #define STATUS_BUSY_BIT      (1 << 0)
 #define STATUS_DONE_BIT      (1 << 1)
 
-void dma_start_transfer(int ch_id, uint32_t src, uint32_t dst, uint32_t bytes, uint32_t tag);
+void dma_start_transfer(int ch_id, u32 src, u32 dst, u32 bytes, u32 tag);
 void dma_wait_polling(int ch_id);
\ No newline at end of file
diff --git a/sdk/software/examples/asm/user-sample.c b/sdk/software/examples/asm/user-sample.c
index cfa8e97..3653892 100644
--- a/sdk/software/examples/asm/user-sample.c
+++ b/sdk/software/examples/asm/user-sample.c
@@ -10,16 +10,14 @@
  *   4. XOR bank toggle      → avoids g%2 recomputation per iteration
  */
 
-#include <stdint.h>
-
 #include <dma.h>
 
 /* ─── UART 16550 direct access (bypasses slow printf/picolibc) ──────── */
-#define UART_THR (*(volatile uint8_t *)0xbf000000)
-#define UART_LSR (*(volatile uint8_t *)0xbf000005)
+#define UART_THR (*(volatile unsigned char *)0xbf000000)
+#define UART_LSR (*(volatile unsigned char *)0xbf000005)
 #define LSR_THRE  0x20
 
-static inline void uart_tx(uint8_t c) {
+static inline void uart_tx(unsigned char c) {
     while (!(UART_LSR & LSR_THRE)) {}
     UART_THR = c;
 }
@@ -28,10 +26,10 @@ static void uart_puts(const char *s) {
     while (*s) uart_tx(*s++);
 }
 
-static void uart_puthex(uint32_t val) {
+static void uart_puthex(unsigned int val) {
     int i;
     for (i = 28; i >= 0; i -= 4) {
-        uint8_t nibble = (val >> i) & 0xF;
+        unsigned char nibble = (val >> i) & 0xF;
         uart_tx(nibble < 10 ? '0' + nibble : 'a' + nibble - 10);
     }
 }
@@ -86,19 +84,19 @@ int main(void)
     if (MATMUL_GROUP_NUM <= 0) return 0;
 
     /* ── Hot-path local volatile pointers (one-time addr calc) ──────── */
-    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 unsigned int *mat_status = (volatile unsigned int *)MATMUL_STATUS;
+    volatile unsigned int *mat_ctrl   = (volatile unsigned int *)MATMUL_CTRL;
+    volatile unsigned int *mat_crc    = (volatile unsigned int *)MATMUL_CRC;
     volatile dma_ch_regs_t *ch0   = DMA_CH(0);
     volatile dma_ch_regs_t *ch1   = DMA_CH(1);
 
-    uint32_t crc;
+    unsigned int crc;
     int g, bank;
 
     // Ping-Pong Register Address Arrays (Physical for DMA)
-    uint32_t phys_bank_AB[2] = {MATMUL_PHYS_B0_AB, MATMUL_PHYS_B1_AB};
-    uint32_t phys_bank_C[2]  = {MATMUL_PHYS_B0_C,  MATMUL_PHYS_B1_C};
-    uint32_t ctrl_start[2]   = {CTRL_START_B0, CTRL_START_B1};
+    unsigned int phys_bank_AB[2] = {MATMUL_PHYS_B0_AB, MATMUL_PHYS_B1_AB};
+    unsigned int phys_bank_C[2]  = {MATMUL_PHYS_B0_C,  MATMUL_PHYS_B1_C};
+    unsigned int ctrl_start[2]   = {CTRL_START_B0, CTRL_START_B1};
 
     /* ── Start marker (must be first output) ──────────────────── */
     uart_puts("MATMUL_START\r\n");