Fix incorrect selection of AVX512 sqrt when OptForSize is on

Summary:
When optimizing for size, sqrt calls can be incorrectly selected as
AVX512 VSQRT instructions.  This is because X86InstrAVX512.td has a
`Requires<[OptForSize]>` in its `avx512_sqrt_scalar` multiclass
definition.  Even if the target does not support AVX512, the class can
apparently still be chosen, leading to an incorrect selection of
`vsqrtss`.

In PR26625, this lead to an assertion: Reg >= X86::FP0 && Reg <=
X86::FP6 && "Expected FP register!", because the `vsqrtss` instruction
requires an XMM register, which is not available on i686 CPUs.

Reviewers: grosbach, resistor, joker.eph

Subscribers: spatel, emaste, llvm-commits

Differential Revision: http://reviews.llvm.org/D17414

llvm-svn: 261360

2 files changed, 21 insertions, 1 deletions

diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td
index a7a5a129f81..4076c7e1ec1 100644
--- a/llvm/lib/Target/X86/X86InstrAVX512.td
+++ b/llvm/lib/Target/X86/X86InstrAVX512.td
@@ -6005,7 +6005,7 @@ multiclass avx512_sqrt_scalar<bits<8> opc, string OpcodeStr,X86VectorVTInfo _,
 
   def : Pat<(_.EltVT (OpNode (load addr:$src))),
             (!cast<Instruction>(NAME#SUFF#Zm)
-                (_.EltVT (IMPLICIT_DEF)), addr:$src)>, Requires<[OptForSize]>;
+                (_.EltVT (IMPLICIT_DEF)), addr:$src)>, Requires<[HasAVX512, OptForSize]>;
 }
 
 multiclass avx512_sqrt_scalar_all<bits<8> opc, string OpcodeStr> {
diff --git a/llvm/test/CodeGen/X86/pr26625.ll b/llvm/test/CodeGen/X86/pr26625.ll
new file mode 100644
index 00000000000..1b2e227bb59
--- /dev/null
+++ b/llvm/test/CodeGen/X86/pr26625.ll
@@ -0,0 +1,20 @@
+; RUN: llc < %s -mcpu=i686 2>&1 | FileCheck %s
+; PR26625
+
+target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
+target triple = "i386"
+
+define float @x0(float %f) #0 {
+entry:
+  %call = tail call float @sqrtf(float %f) #1
+  ret float %call
+; CHECK-LABEL: x0:
+; CHECK: flds
+; CHECK-NEXT: fsqrt
+; CHECK-NOT: vsqrtss
+}
+
+declare float @sqrtf(float) #0
+
+attributes #0 = { nounwind optsize readnone }
+attributes #1 = { nounwind optsize readnone }