diff --git a/libcpu/arm/cortex-a/context_gcc.S b/libcpu/arm/cortex-a/context_gcc.S
index da6e6507df2..087c4fe14b3 100644
--- a/libcpu/arm/cortex-a/context_gcc.S
+++ b/libcpu/arm/cortex-a/context_gcc.S
@@ -97,7 +97,9 @@ rt_hw_context_switch:
     tst  r6, #(1<<30)
     beq 1f
     vstmdb sp!, {d0-d15}
-    vstmdb sp!, {d16-d31}
+#ifdef RT_USING_VFPD32	/*there art 32 double float registers to save*/
+    vstmdb sp!, {d16-d31}	@ save the upper 16 registers
+#endif
     vmrs r5, fpscr
     stmfd sp!, {r5}
 1:
@@ -237,7 +239,9 @@ rt_hw_context_switch_exit:
     beq 1f
     ldmfd sp!, {r5}
     vmsr fpscr, r5
-    vldmia sp!, {d16-d31}
+#ifdef RT_USING_VFPD32	/*there art 32 double float registers to restore*/
+    vldmia sp!, {d16-d31}	@ restore the upper 16 registers
+#endif
     vldmia sp!, {d0-d15}
 1:
 #endif
diff --git a/libcpu/arm/cortex-a/start_gcc.S b/libcpu/arm/cortex-a/start_gcc.S
index 606620ecfc4..1c8e833dfd0 100644
--- a/libcpu/arm/cortex-a/start_gcc.S
+++ b/libcpu/arm/cortex-a/start_gcc.S
@@ -458,13 +458,30 @@ vector_irq:
 
 #else
     stmfd   sp!, {r0-r12,lr}
+#ifdef RT_USING_FPU
+    vstmdb sp!, {d0-d15}
+#ifdef RT_USING_VFPD32	/*there art 32 double float registers to save*/
+    vstmdb sp!, {d16-d31}	@ save the upper 16 registers
+#endif
+    vmrs r5, fpscr
+    stmfd sp!, {r5}
+#endif
 
     bl      rt_interrupt_enter
     bl      rt_hw_trap_irq
     bl      rt_interrupt_leave
 
-    /* if rt_thread_switch_interrupt_flag set, jump to
-     * rt_hw_context_switch_interrupt_do and don't return */
+#ifdef RT_USING_FPU
+    ldmfd sp!, {r5}
+    vmsr fpscr, r5
+#ifdef RT_USING_VFPD32	/*there art 32 double float registers to restore*/
+    vldmia sp!, {d16-d31}	@ restore the upper 16 registers
+#endif
+    vldmia sp!, {d0-d15}
+#endif
+
+    @ if rt_thread_switch_interrupt_flag set, jump to
+    @ rt_hw_context_switch_interrupt_do and don't return
     ldr     r0, =rt_thread_switch_interrupt_flag
     ldr     r1, [r0]
     cmp     r1, #1