replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Enabling 3DNow! prefetch instruction for a few AMD processors: bobcat, jaguar, 

bulldozer and piledriver. Support for the instruction itself seems to have
already been added in r178040.

Differential Revision: http://llvm-reviews.chandlerc.com/D1933

llvm-svn: 192828
This commit is contained in:
Yunzhong Gao 2013-10-16 19:04:11 +00:00
parent 6174e5ee68
commit dfc277f350
3 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/X86/X86.td
View File

@ -292,19 +292,19 @@ def : Proc<"amdfam10", [FeatureSSE4A,
FeaturePOPCNT, FeatureSlowBTMem]>;
// Bobcat
def : Proc<"btver1", [FeatureSSSE3, FeatureSSE4A, FeatureCMPXCHG16B,
FeatureLZCNT, FeaturePOPCNT]>;
FeaturePRFCHW, FeatureLZCNT, FeaturePOPCNT]>;
// Jaguar
def : Proc<"btver2", [FeatureAVX, FeatureSSE4A, FeatureCMPXCHG16B,
FeatureAES, FeaturePCLMUL, FeatureBMI,
FeatureF16C, FeatureMOVBE, FeatureLZCNT,
FeaturePOPCNT]>;
FeaturePRFCHW, FeatureAES, FeaturePCLMUL,
FeatureBMI, FeatureF16C, FeatureMOVBE,
FeatureLZCNT, FeaturePOPCNT]>;
// Bulldozer
def : Proc<"bdver1", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B,
FeatureAES, FeaturePCLMUL,
FeatureAES, FeaturePRFCHW, FeaturePCLMUL,
FeatureLZCNT, FeaturePOPCNT]>;
// Piledriver
def : Proc<"bdver2", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B,
FeatureAES, FeaturePCLMUL,
FeatureAES, FeaturePRFCHW, FeaturePCLMUL,
FeatureF16C, FeatureLZCNT,
FeaturePOPCNT, FeatureBMI, FeatureTBM,
FeatureFMA]>;

2
llvm/lib/Target/X86/X86InstrInfo.td
View File

@ -687,7 +687,7 @@ def HasADX : Predicate<"Subtarget->hasADX()">;
def HasSHA : Predicate<"Subtarget->hasSHA()">;
def HasPRFCHW : Predicate<"Subtarget->hasPRFCHW()">;
def HasRDSEED : Predicate<"Subtarget->hasRDSEED()">;
def HasPrefetchW : Predicate<"Subtarget->has3DNow() || Subtarget->hasPRFCHW()">;
def HasPrefetchW : Predicate<"Subtarget->hasPRFCHW()">;
def FPStackf32 : Predicate<"!Subtarget->hasSSE1()">;
def FPStackf64 : Predicate<"!Subtarget->hasSSE2()">;
def HasCmpxchg16b: Predicate<"Subtarget->hasCmpxchg16b()">;

3
llvm/test/CodeGen/X86/prefetch.ll
View File

@ -2,6 +2,8 @@
; RUN: llc < %s -march=x86 -mattr=+avx | FileCheck %s
; RUN: llc < %s -march=x86 -mattr=+sse -mattr=+prfchw | FileCheck %s -check-prefix=PRFCHW
; RUN: llc < %s -march=x86 -mcpu=slm | FileCheck %s -check-prefix=SLM
; RUN: llc < %s -march=x86 -mcpu=btver2 | FileCheck %s -check-prefix=PRFCHW
; RUN: llc < %s -march=x86 -mcpu=btver2 -mattr=-prfchw | FileCheck %s -check-prefix=NOPRFCHW
; rdar://10538297
@ -12,6 +14,7 @@ entry:
; CHECK: prefetcht0
; CHECK: prefetchnta
; PRFCHW: prefetchw
; NOPRFCHW-NOT: prefetchw
; SLM: prefetchw
tail call void @llvm.prefetch( i8* %ptr, i32 0, i32 1, i32 1 )
tail call void @llvm.prefetch( i8* %ptr, i32 0, i32 2, i32 1 )