X86 cost model: Adjust cost for custom lowered vector multiplies

This matters for example in following matrix multiply:

int **mmult(int rows, int cols, int **m1, int **m2, int **m3) {
  int i, j, k, val;
  for (i=0; i<rows; i++) {
    for (j=0; j<cols; j++) {
      val = 0;
      for (k=0; k<cols; k++) {
        val += m1[i][k] * m2[k][j];
      }
      m3[i][j] = val;
    }
  }
  return(m3);
}

Taken from the test-suite benchmark Shootout.

We estimate the cost of the multiply to be 2 while we generate 9 instructions
for it and end up being quite a bit slower than the scalar version (48% on my
machine).

Also, properly differentiate between avx1 and avx2. On avx-1 we still split the
vector into 2 128bits and handle the subvector muls like above with 9
instructions.
Only on avx-2 will we have a cost of 9 for v4i64.

I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an
add instead of a mul because with a mul we now no longer vectorize. I did
verify that the mul would be indeed more expensive when vectorized with 3
kernels:

for (i ...)
   r += a[i] * 3;
for (i ...)
  m1[i] = m1[i] * 3; // This matches the test case in avx1.ll
and a matrix multiply.

In each case the vectorized version was considerably slower.

radar://13304919

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176403 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 32 insertions, 0 deletions

diff --git a/test/Analysis/CostModel/X86/arith.ll b/test/Analysis/CostModel/X86/arith.ll
index ae78d44aeb..f0521bae48 100644
--- a/test/Analysis/CostModel/X86/arith.ll
+++ b/test/Analysis/CostModel/X86/arith.ll
@@ -1,4 +1,6 @@
 ; RUN: opt < %s  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
+; RUN: opt < %s  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core2 | FileCheck %s --check-prefix=SSE3
+; RUN: opt < %s  -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core-avx2 | FileCheck %s --check-prefix=AVX2
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
@@ -32,7 +34,37 @@ define i32 @xor(i32 %arg) {
   ret i32 undef
 }
 
+; CHECK: mul
+define void @mul() {
+  ; A <2 x i32> gets expanded to a <2 x i64> vector.
+  ; A <2 x i64> vector multiply is implemented using
+  ; 3 PMULUDQ and 2 PADDS and 4 shifts.
+  ;CHECK: cost of 9 {{.*}} mul
+  %A0 = mul <2 x i32> undef, undef
+  ;CHECK: cost of 9 {{.*}} mul
+  %A1 = mul <2 x i64> undef, undef
+  ;CHECK: cost of 18 {{.*}} mul
+  %A2 = mul <4 x i64> undef, undef
+  ret void
+}
+
+; SSE3: sse3mull
+define void @sse3mull() {
+  ; SSE3: cost of 6 {{.*}} mul
+  %A0 = mul <4 x i32> undef, undef
+  ret void
+  ; SSE3: avx2mull
+}
+
+; AVX2: avx2mull
+define void @avx2mull() {
+  ; AVX2: cost of 9 {{.*}} mul
+  %A0 = mul <4 x i64> undef, undef
+  ret void
+  ; AVX2: fmul
+}
 
+; CHECK: fmul
 define i32 @fmul(i32 %arg) {
   ;CHECK: cost of 1 {{.*}} fmul
   %A = fmul <4 x float> undef, undef