From 2820a5b9e974456ace273fbfeea2747dca94c212 Mon Sep 17 00:00:00 2001
From: Adam Nemet <anemet@apple.com>
Date: Wed, 9 Jul 2014 18:22:33 +0000
Subject: [PATCH] [X86] AVX512: Enable it in the Loop Vectorizer

This lets us experiment with 512-bit vectorization without passing
force-vector-width manually.

The code generated for a simple integer memset loop is properly vectorized.
Disassembly is still broken for it though :(.

llvm-svn: 212634
---
 .../lib/Target/X86/X86TargetTransformInfo.cpp |  6 +++-
 .../Transforms/LoopVectorize/X86/avx512.ll    | 35 +++++++++++++++++++
 2 files changed, 40 insertions(+), 1 deletion(-)
 create mode 100644 llvm/test/Transforms/LoopVectorize/X86/avx512.ll

diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index be9caba506da..c961e2f5b2c8 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -144,13 +144,17 @@ unsigned X86TTI::getNumberOfRegisters(bool Vector) const {
   if (Vector && !ST->hasSSE1())
     return 0;
 
-  if (ST->is64Bit())
+  if (ST->is64Bit()) {
+    if (Vector && ST->hasAVX512())
+      return 32;
     return 16;
+  }
   return 8;
 }
 
 unsigned X86TTI::getRegisterBitWidth(bool Vector) const {
   if (Vector) {
+    if (ST->hasAVX512()) return 512;
     if (ST->hasAVX()) return 256;
     if (ST->hasSSE1()) return 128;
     return 0;
diff --git a/llvm/test/Transforms/LoopVectorize/X86/avx512.ll b/llvm/test/Transforms/LoopVectorize/X86/avx512.ll
new file mode 100644
index 000000000000..a2208668177d
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/X86/avx512.ll
@@ -0,0 +1,35 @@
+; RUN: opt -mattr=+avx512f --loop-vectorize -S < %s | llc -mattr=+avx512f | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.9.0"
+
+; Verify that we generate 512-bit wide vectors for a basic integer memset
+; loop.
+
+; CHECK-LABEL: f:
+; CHECK: vmovdqu32 %zmm{{.}}, (
+; CHECK-NOT: %ymm
+
+define void @f(i32* %a, i32 %n) {
+entry:
+  %cmp4 = icmp sgt i32 %n, 0
+  br i1 %cmp4, label %for.body.preheader, label %for.end
+
+for.body.preheader:                               ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  store i32 %n, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end.loopexit, label %for.body
+
+for.end.loopexit:                                 ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.end.loopexit, %entry
+  ret void
+}