Bump X86 Darwin MaxVectorAlign to 64, for AVX512.

[ab]

Summary

Without this, 64-byte vector types (__m512), specified to be 64-byte aligned in the AVX512 draft SysV ABI, will only be 32-byte aligned.

One might raise a couple valid concerns:

• this doesn't change alignment of anything other than clang-generated vector code. So malloc() and all will still only be 16-byte aligned.
• we've gotten to a point where unaligned accesses are good enough, why care about alignment?

To which I pedantically counter:

• there's precedent: AVX bumped alignment to 32, so vector users are already familiar with the issue.
• because the spec says so ;)

[rjmccall]

Should we conditionalize this on whether AVX (for 32-byte) and AVX-512 (for 64-byte) are enabled? I'm willing to accept that we shouldn't; just want to hear your thoughts.

[ab]

In D10724#194990, @rjmccall wrote:

Should we conditionalize this on whether AVX (for 32-byte) and AVX-512 (for 64-byte) are enabled? I'm willing to accept that we shouldn't; just want to hear your thoughts.

I think that would make sense.

I thought I saw a justification for unconditionally using 256 in the original AVX patch, but now that I look again I don't think there is one, and I can't think of one.

[rjmccall]

Okay. Go ahead and send a patch to do that, then, please.

lib/Basic/Targets.cpp

 
 class DarwinI386TargetInfo : public DarwinTargetInfo<X86_32TargetInfo> {
 public:
   DarwinI386TargetInfo(const llvm::Triple &Triple)
       : DarwinTargetInfo<X86_32TargetInfo>(Triple) {
     LongDoubleWidth = 128;
     LongDoubleAlign = 128;
     SuitableAlign = 128;
-    MaxVectorAlign = 256;
+    MaxVectorAlign = 512;
     SizeType = UnsignedLong;
     IntPtrType = SignedLong;
     DescriptionString = "e-m:o-p:32:32-f64:32:64-f80:128-n8:16:32-S128";
     HasAlignMac68kSupport = true;
   }
 
 };
 
public:
   }
 };
 
 class DarwinX86_64TargetInfo : public DarwinTargetInfo<X86_64TargetInfo> {
 public:
   DarwinX86_64TargetInfo(const llvm::Triple &Triple)
       : DarwinTargetInfo<X86_64TargetInfo>(Triple) {
     Int64Type = SignedLongLong;
-    MaxVectorAlign = 256;
+    MaxVectorAlign = 512;
     // The 64-bit iOS simulator uses the builtin bool type for Objective-C.
     llvm::Triple T = llvm::Triple(Triple);
     if (T.isiOS())
       UseSignedCharForObjCBool = false;
     DescriptionString = "e-m:o-i64:64-f80:128-n8:16:32:64-S128";
   }
 };
 

test/CodeGen/vector-alignment.c

 // RUN: %clang_cc1 -w -triple x86_64-apple-darwin10 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -w -triple i386-apple-darwin10 -emit-llvm -o - %s | FileCheck %s
 // rdar://11759609
 
 // At or below target max alignment with no aligned attribute should align based
 // on the size of vector.
 double __attribute__((vector_size(16))) v1;
 // CHECK: @v1 {{.*}}, align 16
 double __attribute__((vector_size(32))) v2;
 // CHECK: @v2 {{.*}}, align 32
+double __attribute__((vector_size(64))) v3;
+// CHECK: @v3 {{.*}}, align 64
 
 // Alignment above target max alignment with no aligned attribute should align
 // based on the target max.
-double __attribute__((vector_size(64))) v3;
-// CHECK: @v3 {{.*}}, align 32
 double __attribute__((vector_size(1024))) v4;
-// CHECK: @v4 {{.*}}, align 32
+// CHECK: @v4 {{.*}}, align 64
 
 // Aliged attribute should always override.
 double __attribute__((vector_size(16), aligned(16))) v5;
 // CHECK: @v5 {{.*}}, align 16
-double __attribute__((vector_size(16), aligned(64))) v6;
-// CHECK: @v6 {{.*}}, align 64
+double __attribute__((vector_size(16), aligned(128))) v6;
+// CHECK: @v6 {{.*}}, align 128
 double __attribute__((vector_size(32), aligned(16))) v7;
 // CHECK: @v7 {{.*}}, align 16
-double __attribute__((vector_size(32), aligned(64))) v8;
-// CHECK: @v8 {{.*}}, align 64
+double __attribute__((vector_size(32), aligned(128))) v8;
+// CHECK: @v8 {{.*}}, align 128
 
 // Check non-power of 2 widths.
 double __attribute__((vector_size(24))) v9;
 // CHECK: @v9 {{.*}}, align 32
 double __attribute__((vector_size(40))) v10;
-// CHECK: @v10 {{.*}}, align 32
+// CHECK: @v10 {{.*}}, align 64
 
 // Check non-power of 2 widths with aligned attribute.
-double __attribute__((vector_size(24), aligned(64))) v11;
-// CHECK: @v11 {{.*}}, align 64
+double __attribute__((vector_size(24), aligned(128))) v11;
+// CHECK: @v11 {{.*}}, align 128
 double __attribute__((vector_size(80), aligned(16))) v12;
 // CHECK: @v12 {{.*}}, align 16