From 4c8979cd4d19814b8de2e45bd4cc42a5d99ebe19 Mon Sep 17 00:00:00 2001 From: David Sehr Date: Tue, 5 Mar 2013 00:02:23 +0000 Subject: The current X86 NOP padding uses one long NOP followed by the remainder in one-byte NOPs. If the processor actually executes those NOPs, as it sometimes does with aligned bundling, this can have a performance impact. From my micro-benchmarks run on my one machine, a 15-byte NOP followed by twelve one-byte NOPs is about 20% worse than a 15 followed by a 12. This patch changes NOP emission to emit as many 15-byte (the maximum) as possible followed by at most one shorter NOP. llvm-svn: 176464 --- llvm/test/MC/X86/AlignedBundling/long-nop-pad.s | 27 +++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 llvm/test/MC/X86/AlignedBundling/long-nop-pad.s (limited to 'llvm/test/MC') diff --git a/llvm/test/MC/X86/AlignedBundling/long-nop-pad.s b/llvm/test/MC/X86/AlignedBundling/long-nop-pad.s new file mode 100644 index 00000000000..ea33e2889b9 --- /dev/null +++ b/llvm/test/MC/X86/AlignedBundling/long-nop-pad.s @@ -0,0 +1,27 @@ +# RUN: llvm-mc -filetype=obj -triple x86_64-pc-linux-gnu %s -o - \ +# RUN: | llvm-objdump -disassemble -no-show-raw-insn - | FileCheck %s + +# Test that long nops are generated for padding where possible. + + .text +foo: + .bundle_align_mode 5 + +# This callq instruction is 5 bytes long + .bundle_lock align_to_end + callq bar + .bundle_unlock +# To align this group to a bundle end, we need a 15-byte NOP and a 12-byte NOP. +# CHECK: 0: nop +# CHECK-NEXT: f: nop +# CHECK-NEXT: 1b: callq + +# This push instruction is 1 byte long + .bundle_lock align_to_end + push %rax + .bundle_unlock +# To align this group to a bundle end, we need two 15-byte NOPs, and a 1-byte. +# CHECK: 20: nop +# CHECK-NEXT: 2f: nop +# CHECK-NEXT: 3e: nop +# CHECK-NEXT: 3f: pushq -- cgit v1.2.3