6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-26 12:20:42 +00:00
Code Issues Projects Releases Wiki Activity

[IR] Make {extract,insert}element accept an index of any integer type.

Browse Source 
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

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207801 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Michael J. Spencer
2014-05-01 22:12:39 +00:00
parent 6010d958a0
commit d4b4f2d340
7 changed files with 57 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/IR/Constants.cpp
+3 -3
View File
@@ -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))