Merge pull request python#35 from tiran/perf-arm64

tiran · Aug 21, 2022 · f4a3ea4 · f4a3ea4
2 parents daacbf5 + dfecbc5
commit f4a3ea4
Show file tree

Hide file tree

Showing 3 changed files with 19 additions and 7 deletions.
diff --git a/Objects/asm_trampoline.S b/Objects/asm_trampoline.S
@@ -12,10 +12,19 @@ _Py_trampoline_func_start:
     pop    %rbp
     ret
 #endif // __x86_64__
-#ifdef __aarch64__
-    TODO
+#if defined(__aarch64__) && defined(__AARCH64EL__) && !defined(__ILP32__)
+    // ARM64 little endian, 64bit ABI
+    // generate with aarch64-linux-gnu-gcc 12.1
+    stp     x29, x30, [sp, -16]!
+    mov     x29, sp
+    mov     x4, x0
+    mov     x0, x1
+    mov     x1, x2
+    mov     w2, w3
+    blr     x4
+    ldp     x29, x30, [sp], 16
+    ret
 #endif
     .globl	_Py_trampoline_func_end
 _Py_trampoline_func_end:
     .section        .note.GNU-stack,"",@progbits
-
diff --git a/configure b/configure
diff --git a/configure.ac b/configure.ac
@@ -3428,8 +3428,9 @@ AC_MSG_RESULT($SHLIBS)
 dnl perf trampoline is Linux specific and requires an arch-specific
 dnl trampoline in asssembly.
 AC_MSG_CHECKING([perf trampoline])
-AS_CASE([$host],
-  [x86_64-*-linux-*], [perf_trampoline=yes],
+AS_CASE([$PLATFORM_TRIPLET],
+  [x86_64-linux-gnu], [perf_trampoline=yes],
+  [aarch64-linux-gnu], [perf_trampoline=yes],
   [perf_trampoline=no]
 )
 AC_MSG_RESULT([$perf_trampoline])