[PATCH] D85989: [X86] Add feature for Fast Short REP MOV (FSRM) for Icelake or newer.
Hiroshi Yamauchi via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Aug 14 12:38:42 PDT 2020
yamauchi created this revision.
yamauchi added reviewers: davidxl, craig.topper.
Herald added a subscriber: hiraditya.
Herald added a project: LLVM.
yamauchi requested review of this revision.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D85989
Files:
llvm/lib/Target/X86/X86.td
llvm/lib/Target/X86/X86InstrInfo.td
llvm/lib/Target/X86/X86Subtarget.h
Index: llvm/lib/Target/X86/X86Subtarget.h
===================================================================
--- llvm/lib/Target/X86/X86Subtarget.h
+++ llvm/lib/Target/X86/X86Subtarget.h
@@ -302,6 +302,9 @@
/// True if the processor has enhanced REP MOVSB/STOSB.
bool HasERMSB = false;
+ /// True if the processor has fast short REP MOV.
+ bool HasFSRM = false;
+
/// True if the short functions should be padded to prevent
/// a stall when returning too early.
bool PadShortFunctions = false;
@@ -692,6 +695,7 @@
bool hasMacroFusion() const { return HasMacroFusion; }
bool hasBranchFusion() const { return HasBranchFusion; }
bool hasERMSB() const { return HasERMSB; }
+ bool hasFSRM() const { return HasFSRM; }
bool hasSlowDivide32() const { return HasSlowDivide32; }
bool hasSlowDivide64() const { return HasSlowDivide64; }
bool padShortFunctions() const { return PadShortFunctions; }
Index: llvm/lib/Target/X86/X86InstrInfo.td
===================================================================
--- llvm/lib/Target/X86/X86InstrInfo.td
+++ llvm/lib/Target/X86/X86InstrInfo.td
@@ -1016,6 +1016,7 @@
def HasFastLZCNT : Predicate<"Subtarget->hasFastLZCNT()">;
def HasFastSHLDRotate : Predicate<"Subtarget->hasFastSHLDRotate()">;
def HasERMSB : Predicate<"Subtarget->hasERMSB()">;
+def HasFSRM : Predicate<"Subtarget->hasFSRM()">;
def HasMFence : Predicate<"Subtarget->hasMFence()">;
def UseIndirectThunkCalls : Predicate<"Subtarget->useIndirectThunkCalls()">;
def NotUseIndirectThunkCalls : Predicate<"!Subtarget->useIndirectThunkCalls()">;
Index: llvm/lib/Target/X86/X86.td
===================================================================
--- llvm/lib/Target/X86/X86.td
+++ llvm/lib/Target/X86/X86.td
@@ -372,6 +372,12 @@
"ermsb", "HasERMSB", "true",
"REP MOVS/STOS are fast">;
+// Icelake and newer processors have Fast Short REP MOV.
+def FeatureFSRM
+ : SubtargetFeature<
+ "fsrm", "HasFSRM", "true",
+ "REP MOVSB of short lengths is faster">;
+
// Bulldozer and newer processors can merge CMP/TEST (but not other
// instructions) with conditional branches.
def FeatureBranchFusion
@@ -713,7 +719,8 @@
FeatureVPOPCNTDQ,
FeatureGFNI,
FeatureCLWB,
- FeatureRDPID];
+ FeatureRDPID,
+ FeatureFSRM];
list<SubtargetFeature> ICLTuning = CNLTuning;
list<SubtargetFeature> ICLFeatures =
!listconcat(CNLFeatures, ICLAdditionalFeatures);
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D85989.285735.patch
Type: text/x-patch
Size: 2740 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200814/9bca67e9/attachment.bin>
More information about the llvm-commits
mailing list