],
)

cc_library(
    name = "permutation",
    hdrs = ["permutation.h"],
    compatible_with = get_compatible_with_portable(),
    deps = [
        "@llvm-project//llvm:Support",
        "@llvm-project//mlir:Support",
    ],
)

tf_cc_test(
    name = "permutation_test",
    srcs = ["permutation_test.cc"],
    deps = [
        ":permutation",
        "@com_google_googletest//:gtest_main",

		t.Skip("Too long for race mode")
	}
	testenv.ParallelOn64Bit(t)
	h := newHashSet()
	permutation(t, h, []uint32{0, 1, 2, 3, 4, 5, 6, 7}, 8)
	permutation(t, h, []uint32{0, 1 << 29, 2 << 29, 3 << 29, 4 << 29, 5 << 29, 6 << 29, 7 << 29}, 8)
	permutation(t, h, []uint32{0, 1}, 20)
	permutation(t, h, []uint32{0, 1 << 31}, 20)
	permutation(t, h, []uint32{0, 1, 2, 3, 4, 5, 6, 7, 1 << 29, 2 << 29, 3 << 29, 4 << 29, 5 << 29, 6 << 29, 7 << 29}, 6)
}

				p = append(p, i)
			}
			permutations = [][]int{p}
		}
		for _, permutation := range permutations {
			name := tc.name + fmt.Sprintf(" permutation %v", permutation)
			t.Run(name, func(t *testing.T) {
				multimap := NewBiMultimap()
				for i := range permutation {
					tc.ops[i](multimap)
					// Run consistency check after every operation.
					err := consistencyCheck(multimap)
					if err != nil {

//
//  The update needs permuting to be in the form (a,b,d,e,f) so that the update
//  window dims are the trailing dimensions.
//
// To canonicalize the updates above, replace the updates with:
//   transpose(updates, permutation={3,4,0,1,2})
//
// Note: NormalizeIndexVector is assumed to have run on the indices already so
// that the index_vector_dim is the trailing dimension in `indices`.
LogicalResult CanonicalizeScatterUpdates(

      redux_op);
}

TF::TransposeOp createTransposeOp(Value value, Location loc,
                                  llvm::ArrayRef<int32_t> permutation,
                                  PatternRewriter* rewriter) {
  auto perm_op = createI32ConstantOp(permutation, loc, rewriter);
  auto value_type = mlir::cast<RankedTensorType>(value.getType());
  auto shape = value_type.getShape();

#define R_x110	R27


// V0-V7 are A-H
// V8-V23 are used for the message schedule
#define KI	V24
#define FUNC	V25
#define S0	V26
#define S1	V27
#define s0	V28
#define s1	V29
#define LEMASK	V31 // Permutation control register for little endian

// 4 copies of each Kt, to fill all 4 words of a vector register
DATA  ·kcon+0x000(SB)/8, $0x428a2f98428a2f98
DATA  ·kcon+0x008(SB)/8, $0x428a2f98428a2f98

          PushTransposeThroughEwisePass> {
 public:
  MLIR_DEFINE_EXPLICIT_INTERNAL_INLINE_TYPE_ID(PushTransposeThroughEwisePass)
  void runOnOperation() override;
};

// Compute the permutation that would take `arr` to the identity.
llvm::SmallVector<int32_t> InvertPermutation(llvm::SmallVector<int32_t> arr) {
  llvm::SmallVector<int32_t> inverse_arr(arr.size());
  for (int32_t i = 0; i < arr.size(); ++i) {

#define R_x110	R27


// V0-V7 are A-H
// V8-V23 are used for the message schedule
#define KI	V24
#define FUNC	V25
#define S0	V26
#define S1	V27
#define s0	V28
#define s1	V29
#define LEMASK	V31 // Permutation control register for little endian

// 4 copies of each Kt, to fill all 4 words of a vector register
DATA  ·kcon+0x000(SB)/8, $0x428a2f98428a2f98
DATA  ·kcon+0x008(SB)/8, $0x428a2f98428a2f98

    return;
  }
  if (const auto* op = op_union.AsStablehloTransposeOptions()) {
    if (!op->permutation.empty()) {
      attributes.emplace_back(builder.getNamedAttr(
          "permutation",
          BuildVhloTensorV1Attr({static_cast<int64_t>(op->permutation.size())},
                                op->permutation, builder)));
    }
    return;
  }
  if (const auto* op = op_union.AsStablehloRngBitGeneratorOptions()) {

  });

  // Sorts the retvals by name so the order is deterministic.
  std::sort(retvals.begin(), retvals.end(),
            [](Node* a, Node* b) { return a->name() < b->name(); });

  // Computes the permutation to produce the correct argument order, and update
  // the argument indices.
  int variable_start_index = num_args;
  for (int i = 0; i < num_args; ++i) {
    int index;