[X86] Add prefer-128-bit subtarget feature.

Summary:
Similar to the previous prefer-256-bit flag. We might want to
enable this by default some CPUs. This just starts the initial
work to implement and prove that it effects TTI's vector width.

Reviewers: RKSimon, echristo, spatel, atdt

Reviewed By: RKSimon

Subscribers: lebedev.ri, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67311

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@371319 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86.td b/lib/Target/X86/X86.td
index da7ec0ab74ded70e4c4d05114a80ea7a6a1407b1..96d2422825392d00d2326894c29ed2d72562375f 100644 (file)
--- a/lib/Target/X86/X86.td
+++ b/lib/Target/X86/X86.td
@@ -378,6 +378,10 @@ def FeatureHasFastGather
     : SubtargetFeature<"fast-gather", "HasFastGather", "true",
                        "Indicates if gather is reasonably fast">;
 
+def FeaturePrefer128Bit
+    : SubtargetFeature<"prefer-128-bit", "Prefer128Bit", "true",
+                       "Prefer 128-bit AVX instructions">;
+
 def FeaturePrefer256Bit
     : SubtargetFeature<"prefer-256-bit", "Prefer256Bit", "true",
                        "Prefer 256-bit AVX instructions">;

diff --git a/lib/Target/X86/X86Subtarget.cpp b/lib/Target/X86/X86Subtarget.cpp
index c826fdf6964b9ccbba99bb5707d9859e191beeaf..933d31575225826cb89fd00205e1d04f7fa918c2 100644 (file)
--- a/lib/Target/X86/X86Subtarget.cpp
+++ b/lib/Target/X86/X86Subtarget.cpp
@@ -307,6 +307,8 @@ void X86Subtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
   // Consume the vector width attribute or apply any target specific limit.
   if (PreferVectorWidthOverride)
     PreferVectorWidth = PreferVectorWidthOverride;
+  else if (Prefer128Bit)
+    PreferVectorWidth = 128;
   else if (Prefer256Bit)
     PreferVectorWidth = 256;
 }

diff --git a/lib/Target/X86/X86Subtarget.h b/lib/Target/X86/X86Subtarget.h
index 46e777da15ff1162f1057d844ca3ed0c76e0b2e2..ce926b40ac3761c67cbed2d19e1c018cc58e735a 100644 (file)
--- a/lib/Target/X86/X86Subtarget.h
+++ b/lib/Target/X86/X86Subtarget.h
@@ -436,6 +436,9 @@ protected:
   // FIXME: this is a known good value for Yonah. How about others?
   unsigned MaxInlineSizeThreshold = 128;
 
+  /// Indicates target prefers 128 bit instructions.
+  bool Prefer128Bit = false;
+
   /// Indicates target prefers 256 bit instructions.
   bool Prefer256Bit = false;
 

diff --git a/lib/Target/X86/X86TargetTransformInfo.h b/lib/Target/X86/X86TargetTransformInfo.h
index 7545ef502bbbc0152006a1ddb030489cffa3a5f3..27d3b65c25bf4c222db17595d46c8048d25651e1 100644 (file)
--- a/lib/Target/X86/X86TargetTransformInfo.h
+++ b/lib/Target/X86/X86TargetTransformInfo.h
@@ -83,6 +83,7 @@ class X86TTIImpl : public BasicTTIImplBase<X86TTIImpl> {
       X86::FeatureSlowUAMem32,
 
       // Based on whether user set the -mprefer-vector-width command line.
+      X86::FeaturePrefer128Bit,
       X86::FeaturePrefer256Bit,
 
       // CPU name enums. These just follow CPU string.

diff --git a/test/Transforms/SLPVectorizer/X86/arith-add.ll b/test/Transforms/SLPVectorizer/X86/arith-add.ll
index 5c6430c689f5c701cf3cc6e280f4789e93af48a0..f1d16ed75c772cdc68ab5257e8db4e6a82c33bbb 100644 (file)
--- a/test/Transforms/SLPVectorizer/X86/arith-add.ll
+++ b/test/Transforms/SLPVectorizer/X86/arith-add.ll
@@ -1,8 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -mtriple=x86_64-unknown -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=slm -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SLM
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=knl -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512F
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=-prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512BW
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=+prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2

diff --git a/test/Transforms/SLPVectorizer/X86/arith-fp.ll b/test/Transforms/SLPVectorizer/X86/arith-fp.ll
index 119cf594c905db633158b643a23179973ffb17d3..1858e3a63cec7d827df9d6fa0547e403c91d9cd6 100644 (file)
--- a/test/Transforms/SLPVectorizer/X86/arith-fp.ll
+++ b/test/Transforms/SLPVectorizer/X86/arith-fp.ll
@@ -1,9 +1,11 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -mtriple=x86_64-unknown -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=slm -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SLM
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512BW
 
 ;
 ; 128-bit Vectors

diff --git a/test/Transforms/SLPVectorizer/X86/arith-mul.ll b/test/Transforms/SLPVectorizer/X86/arith-mul.ll
index 8a01c85bcdb2749f958b72ed2bcbda44aefcd8e0..d39fd2269f2782fcc28bf69dd957ae52a254af65 100644 (file)
--- a/test/Transforms/SLPVectorizer/X86/arith-mul.ll
+++ b/test/Transforms/SLPVectorizer/X86/arith-mul.ll
@@ -1,8 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -mtriple=x86_64-unknown -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=slm -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SLM
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=knl -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512F
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=-prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512BW
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=+prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2

diff --git a/test/Transforms/SLPVectorizer/X86/arith-sub.ll b/test/Transforms/SLPVectorizer/X86/arith-sub.ll
index 28c807408b7dffe9257c160c05acc7827976c480..acfc08d17fb00c9325c92aff037d192d73378ce4 100644 (file)
--- a/test/Transforms/SLPVectorizer/X86/arith-sub.ll
+++ b/test/Transforms/SLPVectorizer/X86/arith-sub.ll
@@ -1,8 +1,10 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -mtriple=x86_64-unknown -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=slm -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SLM
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
-; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX1
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=corei7-avx -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=-prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2
+; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=core-avx2 -mattr=+prefer-128-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=knl -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512F
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=-prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512BW
 ; RUN: opt < %s -mtriple=x86_64-unknown -mcpu=skx -mattr=+prefer-256-bit -basicaa -slp-vectorizer -S | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX2