mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-06 09:54:49 +00:00
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. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176464 91177308-0d34-0410-b5e6-96231b3b80d8
28 lines
773 B
ArmAsm
28 lines
773 B
ArmAsm
# 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
|