; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 2
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv32 -mattr=+v | FileCheck --check-prefixes=CHECK,RV32 %s
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64 -mattr=+v | FileCheck --check-prefixes=CHECK,RV64 %s

; The mask here interleaves (%v1, %v0), not (%v0, %v1): it should still be cheap.
define <4 x i8> @interleave2_v2i8(<2 x i8> %v0, <2 x i8> %v1) {
; CHECK-LABEL: 'interleave2_v2i8'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %concat = shufflevector <2 x i8> %v0, <2 x i8> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = shufflevector <4 x i8> %concat, <4 x i8> poison, <4 x i32> <i32 2, i32 0, i32 3, i32 1>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i8> %res
;
  %concat = shufflevector <2 x i8> %v0, <2 x i8> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %res = shufflevector <4 x i8> %concat, <4 x i8> poison, <4 x i32> <i32 2, i32 0, i32 3, i32 1>
  ret <4 x i8> %res
}

define <8 x i8> @interleave2_v8i8(<4 x i8> %v0, <4 x i8> %v1) {
; CHECK-LABEL: 'interleave2_v8i8'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %concat = shufflevector <4 x i8> %v0, <4 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res = shufflevector <8 x i8> %concat, <8 x i8> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %res
;
  %concat = shufflevector <4 x i8> %v0, <4 x i8> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %res = shufflevector <8 x i8> %concat, <8 x i8> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
  ret <8 x i8> %res
}

define <8 x i32> @interleave2_v8i32(<4 x i32> %v0, <4 x i32> %v1) {
; CHECK-LABEL: 'interleave2_v8i32'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %concat = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = shufflevector <8 x i32> %concat, <8 x i32> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %res
;
  %concat = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %res = shufflevector <8 x i32> %concat, <8 x i32> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
  ret <8 x i32> %res
}

; Should be expensive on RV32 because it can't widen
define <8 x i64> @interleave2_v8i64(<4 x i64> %v0, <4 x i64> %v1) {
; RV32-LABEL: 'interleave2_v8i64'
; RV32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV32-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %res = shufflevector <8 x i64> %concat, <8 x i64> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
; RV32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %res
;
; RV64-LABEL: 'interleave2_v8i64'
; RV64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; RV64-NEXT:  Cost Model: Found an estimated cost of 22 for instruction: %res = shufflevector <8 x i64> %concat, <8 x i64> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
; RV64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i64> %res
;
  %concat = shufflevector <4 x i64> %v0, <4 x i64> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %res = shufflevector <8 x i64> %concat, <8 x i64> poison, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
  ret <8 x i64> %res
}

; TODO: getInstructionCost doesn't call getShuffleCost here because the shuffle changes length
define {<4 x i8>, <4 x i8>} @deinterleave_2(<8 x i8> %v) {
; CHECK-LABEL: 'deinterleave_2'
; CHECK-NEXT:  Cost Model: Found an estimated cost of -1 for instruction: %v0 = shufflevector <8 x i8> %v, <8 x i8> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
; CHECK-NEXT:  Cost Model: Found an estimated cost of -1 for instruction: %v1 = shufflevector <8 x i8> %v, <8 x i8> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
; CHECK-NEXT:  Cost Model: Found an estimated cost of -1 for instruction: %res0 = insertvalue { <4 x i8>, <4 x i8> } poison, <4 x i8> %v0, 0
; CHECK-NEXT:  Cost Model: Found an estimated cost of -1 for instruction: %res1 = insertvalue { <4 x i8>, <4 x i8> } %res0, <4 x i8> %v1, 1
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret { <4 x i8>, <4 x i8> } %res1
;
  %v0 = shufflevector <8 x i8> %v, <8 x i8> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
  %v1 = shufflevector <8 x i8> %v, <8 x i8> poison, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
  %res0 = insertvalue {<4 x i8>, <4 x i8>} poison, <4 x i8> %v0, 0
  %res1 = insertvalue {<4 x i8>, <4 x i8>} %res0, <4 x i8> %v1, 1
  ret {<4 x i8>, <4 x i8>} %res1
}