From f49bc3f1b19c24e4957bd3bc2dc08218f4707c55 Mon Sep 17 00:00:00 2001 From: Lang Hames Date: Thu, 24 Jul 2014 20:40:55 +0000 Subject: [X86] Optimize stackmap shadows on X86. This patch minimizes the number of nops that must be emitted on X86 to satisfy stackmap shadow constraints. To minimize the number of nops inserted, the X86AsmPrinter now records the size of the most recent stackmap's shadow in the StackMapShadowTracker class, and tracks the number of instruction bytes emitted since the that stackmap instruction was encountered. Padding is emitted (if it is required at all) immediately before the next stackmap/patchpoint instruction, or at the end of the basic block. This optimization should reduce code-size and improve performance for people using the llvm stackmap intrinsic on X86. llvm-svn: 213892 --- .../CodeGen/X86/stackmap-shadow-optimization.ll | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll (limited to 'llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll') diff --git a/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll b/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll new file mode 100644 index 00000000000..63debe396b6 --- /dev/null +++ b/llvm/test/CodeGen/X86/stackmap-shadow-optimization.ll @@ -0,0 +1,21 @@ +; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -disable-fp-elim | FileCheck %s + +; Check that the X86 stackmap shadow optimization is only outputting a 1-byte +; nop here. 8-bytes are requested, but 7 are covered by the code for the call to +; bar, the frame teardown and the return. +define void @shadow_optimization_test() { +entry: +; CHECK-LABEL: shadow_optimization_test: +; CHECK: callq _bar +; CHECK-NOT: nop +; CHECK: callq _bar +; CHECK: retq +; CHECK: nop + call void @bar() + tail call void (i64, i32, ...)* @llvm.experimental.stackmap(i64 0, i32 8) + call void @bar() + ret void +} + +declare void @llvm.experimental.stackmap(i64, i32, ...) +declare void @bar() \ No newline at end of file -- cgit v1.2.3