[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

diff --git a/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index 78403424da63f627b4a077a2ea7c44cc621ef83a..c12a57a06d66bbb331e0503d572f6dbcbfa485ee 100644 (file)
--- a/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -73,11 +73,12 @@ public:
 };
 
 class X86AsmBackend : public MCAsmBackend {
-  StringRef CPU;
+  const StringRef CPU;
   bool HasNopl;
+  const uint64_t MaxNopLength;
 public:
   X86AsmBackend(const Target &T, StringRef _CPU)
-    : MCAsmBackend(), CPU(_CPU) {
+    : MCAsmBackend(), CPU(_CPU), MaxNopLength(_CPU == "slm" ? 7 : 15) {
     HasNopl = CPU != "generic" && CPU != "i386" && CPU != "i486" &&
               CPU != "i586" && CPU != "pentium" && CPU != "pentium-mmx" &&
               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
   // needed, then emit a nop of the remaining length.
   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;
     for (uint8_t i = 0; i < Prefixes; i++)
       OW->Write8(0x66);

diff --git a/test/MC/X86/x86_long_nop.s b/test/MC/X86/x86_long_nop.s
index ac1bc08ff38ba85ca87f90a1f9b174ba5ed861f4..eee840c5a9777c9f442fc957d0f6322aec651b24 100644 (file)
--- a/test/MC/X86/x86_long_nop.s
+++ b/test/MC/X86/x86_long_nop.s
@@ -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=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-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
 # capable of using long NOPs.
@@ -13,3 +14,12 @@ inc %eax
 # CHECK-NEXT: 10:  nop
 # CHECK-NEXT: 1f:  nop
 # 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

diff --git a/test/MC/X86/x86_nop.s b/test/MC/X86/x86_nop.s
index 059f591168d5883d0ee40adc3881ca28912944f1..572487bfdaca33b3345ac51a8fb2cb25c2df28be 100644 (file)
--- a/test/MC/X86/x86_nop.s
+++ b/test/MC/X86/x86_nop.s
@@ -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=c3-2 %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=slm %s | llvm-objdump -d - | FileCheck --check-prefix=NOPL %s
 
 
 inc %eax