[AArch64] Tweak truncate costs for some scalable vector types (#119542)

== We were previously returning an invalid cost when truncating
anything to <vscale x 2 x i1>, which is incorrect since we can
generate perfectly good code for this.

== The costs for truncating legal or unpacked types to predicates
seemed overly optimistic. For example, when truncating
<vscale x 8 x i16> to <vscale x 8 x i1> we typically do
something like

  and z0.h, z0.h, #0x1
  cmpne   p0.h, p0/z, z0.h, #0

I guess it might depend upon whether the input value is
generated in the same block or not and if we can avoid the
inreg zero-extend. However, it feels safe to take the more
conservative cost here.

== The costs for some truncates such as

  trunc <vscale x 2 x i32> %a to <vscale x 2 x i16>

were 1, whereas in actual fact they are free and no instructions
are required.

== Also, for this

  trunc <vscale x 8 x i32> %a to <vscale x 8 x i16>

it's just a single uzp1 instruction so I reduced the cost to 1.

In general, I've added costs for all cases where the destination
type is legal or unpacked. One unfortunate side effect of this
is the costs for some fixed-width truncates when using SVE now
look too optimistic.

Author: david-arm

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -2782,22 +2782,39 @@ InstructionCost AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
       {ISD::TRUNCATE, MVT::v16i32, MVT::v16i64, 4}, // 4 x uzp1
 
       // Truncations on nxvmiN
-      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i16, 1},
-      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i32, 1},
-      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i64, 1},
-      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i16, 1},
-      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i32, 1},
-      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i64, 2},
-      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i16, 1},
-      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i32, 3},
-      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i64, 5},
-      {ISD::TRUNCATE, MVT::nxv16i1, MVT::nxv16i8, 1},
-      {ISD::TRUNCATE, MVT::nxv2i16, MVT::nxv2i32, 1},
-      {ISD::TRUNCATE, MVT::nxv2i32, MVT::nxv2i64, 1},
-      {ISD::TRUNCATE, MVT::nxv4i16, MVT::nxv4i32, 1},
-      {ISD::TRUNCATE, MVT::nxv4i32, MVT::nxv4i64, 2},
-      {ISD::TRUNCATE, MVT::nxv8i16, MVT::nxv8i32, 3},
-      {ISD::TRUNCATE, MVT::nxv8i32, MVT::nxv8i64, 6},
+      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i8, 2},
+      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i16, 2},
+      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i32, 2},
+      {ISD::TRUNCATE, MVT::nxv2i1, MVT::nxv2i64, 2},
+      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i8, 2},
+      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i16, 2},
+      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i32, 2},
+      {ISD::TRUNCATE, MVT::nxv4i1, MVT::nxv4i64, 5},
+      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i8, 2},
+      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i16, 2},
+      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i32, 5},
+      {ISD::TRUNCATE, MVT::nxv8i1, MVT::nxv8i64, 11},
+      {ISD::TRUNCATE, MVT::nxv16i1, MVT::nxv16i8, 2},
+      {ISD::TRUNCATE, MVT::nxv2i8, MVT::nxv2i16, 0},
+      {ISD::TRUNCATE, MVT::nxv2i8, MVT::nxv2i32, 0},
+      {ISD::TRUNCATE, MVT::nxv2i8, MVT::nxv2i64, 0},
+      {ISD::TRUNCATE, MVT::nxv2i16, MVT::nxv2i32, 0},
+      {ISD::TRUNCATE, MVT::nxv2i16, MVT::nxv2i64, 0},
+      {ISD::TRUNCATE, MVT::nxv2i32, MVT::nxv2i64, 0},
+      {ISD::TRUNCATE, MVT::nxv4i8, MVT::nxv4i16, 0},
+      {ISD::TRUNCATE, MVT::nxv4i8, MVT::nxv4i32, 0},
+      {ISD::TRUNCATE, MVT::nxv4i8, MVT::nxv4i64, 1},
+      {ISD::TRUNCATE, MVT::nxv4i16, MVT::nxv4i32, 0},
+      {ISD::TRUNCATE, MVT::nxv4i16, MVT::nxv4i64, 1},
+      {ISD::TRUNCATE, MVT::nxv4i32, MVT::nxv4i64, 1},
+      {ISD::TRUNCATE, MVT::nxv8i8, MVT::nxv8i16, 0},
+      {ISD::TRUNCATE, MVT::nxv8i8, MVT::nxv8i32, 1},
+      {ISD::TRUNCATE, MVT::nxv8i8, MVT::nxv8i64, 3},
+      {ISD::TRUNCATE, MVT::nxv8i16, MVT::nxv8i32, 1},
+      {ISD::TRUNCATE, MVT::nxv8i16, MVT::nxv8i64, 3},
+      {ISD::TRUNCATE, MVT::nxv16i8, MVT::nxv16i16, 1},
+      {ISD::TRUNCATE, MVT::nxv16i8, MVT::nxv16i32, 3},
+      {ISD::TRUNCATE, MVT::nxv16i8, MVT::nxv16i64, 7},
 
       // The number of shll instructions for the extension.
       {ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i16, 3},

llvm/test/Analysis/CostModel/AArch64/sve-cast.ll

@@ -418,27 +418,27 @@ define void @trunc() {
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i8i16 = trunc <2 x i16> undef to <2 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i8i32 = trunc <2 x i32> undef to <2 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i8i64 = trunc <2 x i64> undef to <2 x i8>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s2i16i32 = trunc <2 x i32> undef to <2 x i16>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i16i32 = trunc <2 x i32> undef to <2 x i16>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i16i64 = trunc <2 x i64> undef to <2 x i16>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s2i32i64 = trunc <2 x i64> undef to <2 x i32>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s2i32i64 = trunc <2 x i64> undef to <2 x i32>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i16 = trunc <4 x i16> undef to <4 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i32 = trunc <4 x i32> undef to <4 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i64 = trunc <4 x i64> undef to <4 x i8>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i16i32 = trunc <4 x i32> undef to <4 x i16>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i16i32 = trunc <4 x i32> undef to <4 x i16>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i16i64 = trunc <4 x i64> undef to <4 x i16>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i16 = trunc <8 x i16> undef to <8 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i32 = trunc <8 x i32> undef to <8 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i64 = trunc <8 x i64> undef to <8 x i8>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i16i64 = trunc <8 x i64> undef to <8 x i16>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i16 = trunc <16 x i16> undef to <16 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i32 = trunc <16 x i32> undef to <16 x i8>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i64 = trunc <16 x i64> undef to <16 x i8>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i16i64 = trunc <16 x i64> undef to <16 x i16>
-; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
+; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
 ; SVE128-NO-NEON-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; FIXED-MIN-256-LABEL: 'trunc'
@@ -463,19 +463,19 @@ define void @trunc() {
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i64 = trunc <4 x i64> undef to <4 x i8>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i16i32 = trunc <4 x i32> undef to <4 x i16>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i16i64 = trunc <4 x i64> undef to <4 x i16>
-; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
+; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i8i16 = trunc <8 x i16> undef to <8 x i8>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i32 = trunc <8 x i32> undef to <8 x i8>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i64 = trunc <8 x i64> undef to <8 x i8>
-; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
+; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i16i64 = trunc <8 x i64> undef to <8 x i16>
-; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
+; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i16 = trunc <16 x i16> undef to <16 x i8>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i32 = trunc <16 x i32> undef to <16 x i8>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i64 = trunc <16 x i64> undef to <16 x i8>
-; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
+; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i16i64 = trunc <16 x i64> undef to <16 x i16>
-; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
+; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
 ; FIXED-MIN-256-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 ; FIXED-MIN-2048-LABEL: 'trunc'
@@ -500,19 +500,19 @@ define void @trunc() {
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i8i64 = trunc <4 x i64> undef to <4 x i8>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i16i32 = trunc <4 x i32> undef to <4 x i16>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i16i64 = trunc <4 x i64> undef to <4 x i16>
-; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
+; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s4i32i64 = trunc <4 x i64> undef to <4 x i32>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i8i16 = trunc <8 x i16> undef to <8 x i8>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i32 = trunc <8 x i32> undef to <8 x i8>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i8i64 = trunc <8 x i64> undef to <8 x i8>
-; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
+; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i16i32 = trunc <8 x i32> undef to <8 x i16>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i16i64 = trunc <8 x i64> undef to <8 x i16>
-; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
+; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s8i32i64 = trunc <8 x i64> undef to <8 x i32>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i16 = trunc <16 x i16> undef to <16 x i8>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i32 = trunc <16 x i32> undef to <16 x i8>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i8i64 = trunc <16 x i64> undef to <16 x i8>
-; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
+; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i16i32 = trunc <16 x i32> undef to <16 x i16>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i16i64 = trunc <16 x i64> undef to <16 x i16>
-; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
+; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %s16i32i64 = trunc <16 x i64> undef to <16 x i32>
 ; FIXED-MIN-2048-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %r8 = trunc i8 undef to i1