diff --git a/include/vm_asm_opt_riscv64.h b/include/vm_asm_opt_riscv64.h
index 4190298..2ab14be 100644
--- a/include/vm_asm_opt_riscv64.h
+++ b/include/vm_asm_opt_riscv64.h
@@ -122,10 +122,23 @@ static inline cell_t vm_pop_asm(VM *vm) {
         "lw      t0, %[dsp]\n\t"
         "bltz    t0, 1f\n\t"              /* branch if dsp < 0 (underflow) */
         "slli    t1, t0, 3\n\t"
-        "add     t1, %[stack], t1\n\t"
-        "ld      %[val], 0(t1)\n\t"
+        "add     t1, %[stack], t1\n\t"    /* t1 = &data_stack[dsp] (old dsp) */
         "addi    t0, t0, -1\n\t"
-        "sw      t0, %[dsp]\n\t"
+        "sw      t0, %[dsp]\n\t"          /* write dsp back BEFORE loading the
+                                              value: %[dsp] is a memory operand
+                                              referenced twice in this template
+                                              (read above, write here); loading
+                                              %[val] (a register output) before
+                                              this write-back let clang's
+                                              allocator reuse %[dsp]'s address
+                                              register for %[val], corrupting
+                                              the write-back — GCC happened to
+                                              pick different registers and
+                                              never hit it. Loading %[val] last
+                                              means %[dsp]'s final use has
+                                              already happened by the time the
+                                              output register is live. */
+        "ld      %[val], 0(t1)\n\t"
         "sw      zero, %[err]\n\t"
         "j       2f\n\t"
         "1:\n\t"
@@ -185,10 +198,11 @@ static inline cell_t vm_rpop_asm(VM *vm) {
         "lw      t0, %[rsp]\n\t"
         "bltz    t0, 1f\n\t"
         "slli    t1, t0, 3\n\t"
-        "add     t1, %[stack], t1\n\t"
-        "ld      %[val], 0(t1)\n\t"
+        "add     t1, %[stack], t1\n\t"    /* t1 = &return_stack[rsp] (old rsp) */
         "addi    t0, t0, -1\n\t"
-        "sw      t0, %[rsp]\n\t"
+        "sw      t0, %[rsp]\n\t"          /* write rsp back before loading the
+                                              value — see vm_pop_asm for why */
+        "ld      %[val], 0(t1)\n\t"
         "sw      zero, %[err]\n\t"
         "j       2f\n\t"
         "1:\n\t"