From 1f10c5ea943b0f13df9d61ca22dc964760ecc45f Mon Sep 17 00:00:00 2001
From: "Michael J. Spencer" <bigcheesegs@gmail.com>
Date: Thu, 1 May 2014 22:12:39 +0000
Subject: [IR] Make {extract,insert}element accept an index of any integer
 type.

Given the following C code llvm currently generates suboptimal code for
x86-64:

__m128 bss4( const __m128 *ptr, size_t i, size_t j )
{
    float f = ptr[i][j];
    return (__m128) { f, f, f, f };
}

=================================================

define <4 x float> @_Z4bss4PKDv4_fmm(<4 x float>* nocapture readonly %ptr, i64 %i, i64 %j) #0 {
  %a1 = getelementptr inbounds <4 x float>* %ptr, i64 %i
  %a2 = load <4 x float>* %a1, align 16, !tbaa !1
  %a3 = trunc i64 %j to i32
  %a4 = extractelement <4 x float> %a2, i32 %a3
  %a5 = insertelement <4 x float> undef, float %a4, i32 0
  %a6 = insertelement <4 x float> %a5, float %a4, i32 1
  %a7 = insertelement <4 x float> %a6, float %a4, i32 2
  %a8 = insertelement <4 x float> %a7, float %a4, i32 3
  ret <4 x float> %a8
}

=================================================

        shlq    $4, %rsi
        addq    %rdi, %rsi
        movslq  %edx, %rax
        vbroadcastss    (%rsi,%rax,4), %xmm0
        retq

=================================================

The movslq is uneeded, but is present because of the trunc to i32 and then
sext back to i64 that the backend adds for vbroadcastss.

We can't remove it because it changes the meaning. The IR that clang
generates is already suboptimal. What clang really should emit is:

  %a4 = extractelement <4 x float> %a2, i64 %j

This patch makes that legal. A separate patch will teach clang to do it.

Differential Revision: http://reviews.llvm.org/D3519

llvm-svn: 207801
---
 llvm/lib/IR/Constants.cpp | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'llvm/lib/IR/Constants.cpp')

diff --git a/llvm/lib/IR/Constants.cpp b/llvm/lib/IR/Constants.cpp
index 54be9802920..bb8d60b234f 100644
--- a/llvm/lib/IR/Constants.cpp
+++ b/llvm/lib/IR/Constants.cpp
@@ -1937,8 +1937,8 @@ ConstantExpr::getFCmp(unsigned short pred, Constant *LHS, Constant *RHS) {
 Constant *ConstantExpr::getExtractElement(Constant *Val, Constant *Idx) {
   assert(Val->getType()->isVectorTy() &&
          "Tried to create extractelement operation on non-vector type!");
-  assert(Idx->getType()->isIntegerTy(32) &&
-         "Extractelement index must be i32 type!");
+  assert(Idx->getType()->isIntegerTy() &&
+         "Extractelement index must be an integer type!");
 
   if (Constant *FC = ConstantFoldExtractElementInstruction(Val, Idx))
     return FC;          // Fold a few common cases.
@@ -1958,7 +1958,7 @@ Constant *ConstantExpr::getInsertElement(Constant *Val, Constant *Elt,
          "Tried to create insertelement operation on non-vector type!");
   assert(Elt->getType() == Val->getType()->getVectorElementType() &&
          "Insertelement types must match!");
-  assert(Idx->getType()->isIntegerTy(32) &&
+  assert(Idx->getType()->isIntegerTy() &&
          "Insertelement index must be i32 type!");
 
   if (Constant *FC = ConstantFoldInsertElementInstruction(Val, Elt, Idx))
-- 
cgit v1.2.3