diff --git a/README.adoc b/README.adoc
index dc3e426..b7c4c0e 100644
--- a/README.adoc
+++ b/README.adoc
@@ -17523,7 +17523,7 @@ Also keep in mind that fused multiply add is FMADD.
 
 Examples at: xref:simd-assembly[xrefstyle=full]
 
-===== ARMv8 aarch64 ld2 instruction
+===== ARMv8 aarch64 LD2 instruction
 
 Example: link:userland/arch/aarch64/ld2.S[]
 
diff --git a/userland/arch/aarch64/inline_asm/wfe_ldxr_str.cpp b/userland/arch/aarch64/inline_asm/wfe_ldxr_str.cpp
index 3e1bee9..b08cc07 100644
--- a/userland/arch/aarch64/inline_asm/wfe_ldxr_str.cpp
+++ b/userland/arch/aarch64/inline_asm/wfe_ldxr_str.cpp
@@ -14,7 +14,7 @@ std::atomic_ulong done;
 int futex = 1;
 
 void myfunc() {
-    __asm__ __volatile__ ("ldxr x0, [%0];wfe;wfe" : : "r" (&futex) : "x0");
+    __asm__ __volatile__ ("sevl;wfe;ldxr x0, [%0];wfe" : : "r" (&futex) : "x0");
     done.store(futex);
 }
 
diff --git a/userland/arch/aarch64/inline_asm/wfe_ldxr_stxr.cpp b/userland/arch/aarch64/inline_asm/wfe_ldxr_stxr.cpp
index a2d63c6..fc29e67 100644
--- a/userland/arch/aarch64/inline_asm/wfe_ldxr_stxr.cpp
+++ b/userland/arch/aarch64/inline_asm/wfe_ldxr_stxr.cpp
@@ -14,7 +14,7 @@ std::atomic_ulong done;
 int futex = 1;
 
 void myfunc() {
-    __asm__ __volatile__ ("ldxr x0, [%0];wfe;wfe" : : "r" (&futex) : "x0");
+    __asm__ __volatile__ ("sevl;wfe;ldxr x0, [%0];wfe" : : "r" (&futex) : "x0");
     done.store(futex);
 }
 
@@ -28,7 +28,7 @@ int main(int argc, char **argv) {
     thread = std::thread(myfunc);
     while (!done.load()) {
         if (do_sev) {
-            __asm__ __volatile__ ("mov x0, 1;ldxr x0, [%0];stxr w1, x0, [%0]" : : "r" (&futex) : "x0", "x1");
+            __asm__ __volatile__ ("ldxr x0, [%0];mov x0, 1;stxr w1, x0, [%0]" : : "r" (&futex) : "x0", "x1");
         }
     }
     thread.join();