ARM cost model: Increase the cost for vector casts that use the stack

Increase the cost of v8/v16-i8 to v8/v16-i32 casts and truncates as the backend
currently lowers those using stack accesses.

This was responsible for a significant degradation on
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
where we vectorize one loop to a vector factor of 16. After this patch we select
a vector factor of 4 which will generate reasonable code.

unsigned char cle[32];

void test(short c) {
  unsigned short compte;
  for (compte = 0; compte <= 31; compte++) {
    cle[compte] = cle[compte] ^ c;
  }
}

radar://13220512

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176898 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 22 insertions, 0 deletions

diff --git a/lib/Target/ARM/ARMTargetTransformInfo.cpp b/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 01c04b48cf..eef282e709 100644
--- a/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -194,6 +194,14 @@ unsigned ARMTTI::getCastInstrCost(unsigned Opcode, Type *Dst,
     { ISD::TRUNCATE,    MVT::v4i32, MVT::v4i64, 0 },
     { ISD::TRUNCATE,    MVT::v4i16, MVT::v4i32, 1 },
 
+    // Operations that we legalize using load/stores to the stack.
+    { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8, 16*2 + 4*4 },
+    { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8, 16*2 + 4*3 },
+    { ISD::SIGN_EXTEND, MVT::v8i32, MVT::v8i8, 8*2 + 2*4 },
+    { ISD::ZERO_EXTEND, MVT::v8i32, MVT::v8i8, 8*2 + 2*3 },
+    { ISD::TRUNCATE,    MVT::v16i8, MVT::v16i32, 4*1 + 16*2 + 2*1 },
+    { ISD::TRUNCATE,    MVT::v8i8, MVT::v8i32, 2*1 + 8*2 + 1 },
+
     // Vector float <-> i32 conversions.
     { ISD::SINT_TO_FP,  MVT::v4f32, MVT::v4i32, 1 },
     { ISD::UINT_TO_FP,  MVT::v4f32, MVT::v4i32, 1 },
diff --git a/test/Analysis/CostModel/ARM/cast.ll b/test/Analysis/CostModel/ARM/cast.ll
index 464b6ece0e..779c4384e8 100644
--- a/test/Analysis/CostModel/ARM/cast.ll
+++ b/test/Analysis/CostModel/ARM/cast.ll
@@ -152,6 +152,20 @@ define i32 @casts() {
   ; CHECK: cost of 10 {{.*}} uitofp
   %r69 = uitofp i64 undef to double
 
+  ; Vector cast cost of instructions lowering the cast to the stack.
+  ; CHECK: cost of 24 {{.*}} sext
+  %r70 = sext <8 x i8> undef to <8 x i32>
+  ; CHECK: cost of 48 {{.*}} sext
+  %r71 = sext <16 x i8> undef to <16 x i32>
+  ; CHECK: cost of 22 {{.*}} zext
+  %r72 = zext <8 x i8> undef to <8 x i32>
+  ; CHECK: cost of 44 {{.*}} zext
+  %r73 = zext <16 x i8> undef to <16 x i32>
+  ; CHECK: cost of 19 {{.*}} trunc
+  %r74 = trunc <8 x i32> undef to <8 x i8>
+  ; CHECK: cost of 38 {{.*}} trunc
+  %r75 = trunc <16 x i32> undef to <16 x i8>
+
   ;CHECK: cost of 0 {{.*}} ret
   ret i32 undef
 }