[InstCombine] allow more than one use for vector bitcast folding with selects

The motivating example for this transform is similar to D20774 where bitcasts interfere
with a single cmp/select sequence, but in this case we have 2 uses of each bitcast to 
produce min and max ops:

define void @minmax_bc_store(<4 x float> %a, <4 x float> %b, <4 x float>* %ptr1, <4 x float>* %ptr2) {
  %cmp = fcmp olt <4 x float> %a, %b
  %bc1 = bitcast <4 x float> %a to <4 x i32>
  %bc2 = bitcast <4 x float> %b to <4 x i32>
  %sel1 = select <4 x i1> %cmp, <4 x i32> %bc1, <4 x i32> %bc2
  %sel2 = select <4 x i1> %cmp, <4 x i32> %bc2, <4 x i32> %bc1
  %bc3 = bitcast <4 x float>* %ptr1 to <4 x i32>*
  store <4 x i32> %sel1, <4 x i32>* %bc3
  %bc4 = bitcast <4 x float>* %ptr2 to <4 x i32>*
  store <4 x i32> %sel2, <4 x i32>* %bc4
  ret void
}

With this patch, we move the selects up to use the input args which allows getting rid of
all of the bitcasts:

define void @minmax_bc_store(<4 x float> %a, <4 x float> %b, <4 x float>* %ptr1, <4 x float>* %ptr2) {
  %cmp = fcmp olt <4 x float> %a, %b
  %sel1.v = select <4 x i1> %cmp, <4 x float> %a, <4 x float> %b
  %sel2.v = select <4 x i1> %cmp, <4 x float> %b, <4 x float> %a
  store <4 x float> %sel1.v, <4 x float>* %ptr1, align 16
  store <4 x float> %sel2.v, <4 x float>* %ptr2, align 16
  ret void
}

The asm for x86 SSE then improves from:

movaps  %xmm0, %xmm2
cmpltps %xmm1, %xmm2
movaps  %xmm2, %xmm3
andnps  %xmm1, %xmm3
movaps  %xmm2, %xmm4
andnps  %xmm0, %xmm4
andps %xmm2, %xmm0
orps  %xmm3, %xmm0
andps %xmm1, %xmm2
orps  %xmm4, %xmm2
movaps  %xmm0, (%rdi)
movaps  %xmm2, (%rsi)

To:

movaps  %xmm0, %xmm2
minps %xmm1, %xmm2
maxps %xmm0, %xmm1
movaps  %xmm2, (%rdi)
movaps  %xmm1, (%rsi)

The TODO comments show that we're limiting this transform only to vectors and only to bitcasts
because we need to improve other transforms or risk creating worse codegen.

Differential Revision: http://reviews.llvm.org/D21190

llvm-svn: 273011

0 files changed, 0 insertions, 0 deletions