[X86] Limit maximum nop length on Silvermont

Silvermont can only decode one instruction per cycle if the instruction exceeds 8 bytes.
Also in Silvermont instructions with more than 3 prefixes will cause 3 cycle penalty.
Maximum nop length is limited to 7 bytes when used for padding on Silvermont.
For other x86 processors max nop length remains unchanged 15 bytes.

Differential Revision: http://reviews.llvm.org/D4374


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212321 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Alexey Volkov 2014-07-04 07:14:56 +00:00
parent 546cfbfd0a
commit 1bd30dce7b
3 changed files with 15 additions and 3 deletions

View File

@ -73,11 +73,12 @@ public:
}; };
class X86AsmBackend : public MCAsmBackend { class X86AsmBackend : public MCAsmBackend {
StringRef CPU; const StringRef CPU;
bool HasNopl; bool HasNopl;
const uint64_t MaxNopLength;
public: public:
X86AsmBackend(const Target &T, StringRef _CPU) X86AsmBackend(const Target &T, StringRef _CPU)
: MCAsmBackend(), CPU(_CPU) { : MCAsmBackend(), CPU(_CPU), MaxNopLength(_CPU == "slm" ? 7 : 15) {
HasNopl = CPU != "generic" && CPU != "i386" && CPU != "i486" && HasNopl = CPU != "generic" && CPU != "i386" && CPU != "i486" &&
CPU != "i586" && CPU != "pentium" && CPU != "pentium-mmx" && CPU != "i586" && CPU != "pentium" && CPU != "pentium-mmx" &&
CPU != "i686" && CPU != "k6" && CPU != "k6-2" && CPU != "k6-3" && CPU != "i686" && CPU != "k6" && CPU != "k6-2" && CPU != "k6-3" &&
@ -331,7 +332,7 @@ bool X86AsmBackend::writeNopData(uint64_t Count, MCObjectWriter *OW) const {
// 15 is the longest single nop instruction. Emit as many 15-byte nops as // 15 is the longest single nop instruction. Emit as many 15-byte nops as
// needed, then emit a nop of the remaining length. // needed, then emit a nop of the remaining length.
do { do {
const uint8_t ThisNopLength = (uint8_t) std::min(Count, (uint64_t) 15); const uint8_t ThisNopLength = (uint8_t) std::min(Count, MaxNopLength);
const uint8_t Prefixes = ThisNopLength <= 10 ? 0 : ThisNopLength - 10; const uint8_t Prefixes = ThisNopLength <= 10 ? 0 : ThisNopLength - 10;
for (uint8_t i = 0; i < Prefixes; i++) for (uint8_t i = 0; i < Prefixes; i++)
OW->Write8(0x66); OW->Write8(0x66);

View File

@ -2,6 +2,7 @@
# RUN: llvm-mc -filetype=obj -arch=x86 -triple=i686-pc-linux-gnu %s | llvm-objdump -d -no-show-raw-insn - | FileCheck %s # RUN: llvm-mc -filetype=obj -arch=x86 -triple=i686-pc-linux-gnu %s | llvm-objdump -d -no-show-raw-insn - | FileCheck %s
# RUN: llvm-mc -filetype=obj -arch=x86 -triple=x86_64-apple-darwin10.0 %s | llvm-objdump -d -no-show-raw-insn - | FileCheck %s # RUN: llvm-mc -filetype=obj -arch=x86 -triple=x86_64-apple-darwin10.0 %s | llvm-objdump -d -no-show-raw-insn - | FileCheck %s
# RUN: llvm-mc -filetype=obj -arch=x86 -triple=i686-apple-darwin8 %s | llvm-objdump -d -no-show-raw-insn - | FileCheck %s # RUN: llvm-mc -filetype=obj -arch=x86 -triple=i686-apple-darwin8 %s | llvm-objdump -d -no-show-raw-insn - | FileCheck %s
# RUN: llvm-mc -filetype=obj -arch=x86 -triple=i686-pc-linux-gnu -mcpu=slm %s | llvm-objdump -d -no-show-raw-insn - | FileCheck --check-prefix=SLM %s
# Ensure alignment directives also emit sequences of 15-byte NOPs on processors # Ensure alignment directives also emit sequences of 15-byte NOPs on processors
# capable of using long NOPs. # capable of using long NOPs.
@ -13,3 +14,12 @@ inc %eax
# CHECK-NEXT: 10: nop # CHECK-NEXT: 10: nop
# CHECK-NEXT: 1f: nop # CHECK-NEXT: 1f: nop
# CHECK-NEXT: 20: inc # CHECK-NEXT: 20: inc
# On Silvermont we emit only 7 byte NOPs since longer NOPs are not profitable
# SLM: 0: inc
# SLM-NEXT: 1: nop
# SLM-NEXT: 8: nop
# SLM-NEXT: f: nop
# SLM-NEXT: 16: nop
# SLM-NEXT: 1d: nop
# SLM-NEXT: 20: inc

View File

@ -14,6 +14,7 @@
# RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=c3 %s | llvm-objdump -d - | FileCheck %s # RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=c3 %s | llvm-objdump -d - | FileCheck %s
# RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=c3-2 %s | llvm-objdump -d - | FileCheck %s # RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=c3-2 %s | llvm-objdump -d - | FileCheck %s
# RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=core2 %s | llvm-objdump -d - | FileCheck --check-prefix=NOPL %s # RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=core2 %s | llvm-objdump -d - | FileCheck --check-prefix=NOPL %s
# RUN: llvm-mc -filetype=obj -triple=i686-pc-linux -mcpu=slm %s | llvm-objdump -d - | FileCheck --check-prefix=NOPL %s
inc %eax inc %eax