[mlir][llvm] Add llvm.vector.deinterleave2 intrinsic

[mub-at-arm]

Added LLVM vector deinterleave2 intrinsic to the MLIR LLVM dialect. The deinterleave intrinsic takes a vector and returns two vectors with the first having even elements and second with odd elements from the input array. Reverse of interleave.

[github-actions]

Thank you for submitting a Pull Request (PR) to the LLVM Project!

This PR will be automatically labeled and the relevant teams will be
notified.

If you wish to, you can add reviewers by using the "Reviewers" section on this page.

If this is not working for you, it is probably because you do not have write
permissions for the repository. In which case you can instead tag reviewers by
name in a comment by using @ followed by their GitHub username.

If you have received no comments on your PR for a week, you can request a review
by "ping"ing the PR by adding a comment “Ping”. The common courtesy "ping" rate
is once a week. Please remember that you are asking for valuable time from other developers.

If you have further questions, they may be answered by the LLVM GitHub User Guide.

You can also ask questions in a comment on this PR, on the LLVM Discord or on the forums.

[llvmbot]

@llvm/pr-subscribers-mlir

@llvm/pr-subscribers-mlir-llvm

Author: Mubashar Ahmad (mub-at-arm)

Changes

Added LLVM vector deinterleave2 intrinsic to the MLIR LLVM dialect. The deinterleave intrinsic takes a vector and returns two vectors with the first having even elements and second with odd elements from the input array. Reverse of interleave.

---

Full diff: https://github.com/llvm/llvm-project/pull/91986.diff

4 Files Affected:

• (modified) mlir/include/mlir/Dialect/LLVMIR/LLVMIntrinsicOps.td (+6)
• (modified) mlir/test/Dialect/LLVMIR/roundtrip.mlir (+7)
• (modified) mlir/test/Target/LLVMIR/Import/intrinsic.ll (+9)
• (modified) mlir/test/Target/LLVMIR/llvmir-intrinsics.mlir (+13)

diff --git a/mlir/include/mlir/Dialect/LLVMIR/LLVMIntrinsicOps.td b/mlir/include/mlir/Dialect/LLVMIR/LLVMIntrinsicOps.td
index 759cbe6c15647..97213dccfac07 100644
--- a/mlir/include/mlir/Dialect/LLVMIR/LLVMIntrinsicOps.td
+++ b/mlir/include/mlir/Dialect/LLVMIR/LLVMIntrinsicOps.td
@@ -1074,6 +1074,12 @@ def LLVM_vector_interleave2
         ]>,
         Arguments<(ins LLVM_AnyVector:$vec1, LLVM_AnyVector:$vec2)>;
 
+def LLVM_vector_deinterleave2
+    : LLVM_IntrOp<"vector.deinterleave2",
+        /*overloadedResults=*/[], /*overloadedOperands=*/[0],
+        /*traits=*/[Pure], /*numResults=*/2>,
+        Arguments<(ins LLVM_AnyVector:$vec)>;
+
 //
 // LLVM Vector Predication operations.
 //
diff --git a/mlir/test/Dialect/LLVMIR/roundtrip.mlir b/mlir/test/Dialect/LLVMIR/roundtrip.mlir
index 3b94db389f549..d1bf3368a996d 100644
--- a/mlir/test/Dialect/LLVMIR/roundtrip.mlir
+++ b/mlir/test/Dialect/LLVMIR/roundtrip.mlir
@@ -349,6 +349,13 @@ func.func @vector_interleave2(%vec1: vector<[4]xf16>, %vec2 : vector<[4]xf16>) {
   return
 }
 
+// CHECK-LABEL: @vector_deinterleave2
+func.func @vector_deinterleave2(%vec: vector<[8]xf16>) {
+  // CHECK: = "llvm.intr.vector.deinterleave2" ({{.*}}) : (vector<[8]xf16) -> !llvm.struct<(vector<[4]xf16>, vector<[4]xf16>)>
+  %0 = "llvm.intr.vector.deinterleave2"(%vec) : (vector<[8]xf16>) -> !llvm.struct<(vector<[4]xf16>, vector<[4]xf16>)>
+  return
+}
+
 // CHECK-LABEL: @alloca
 func.func @alloca(%size : i64) {
   // CHECK: llvm.alloca %{{.*}} x i32 : (i64) -> !llvm.ptr
diff --git a/mlir/test/Target/LLVMIR/Import/intrinsic.ll b/mlir/test/Target/LLVMIR/Import/intrinsic.ll
index bf6847a32ff4f..28d9aef2432d8 100644
--- a/mlir/test/Target/LLVMIR/Import/intrinsic.ll
+++ b/mlir/test/Target/LLVMIR/Import/intrinsic.ll
@@ -786,6 +786,15 @@ define void @vector_extract(<vscale x 4 x float> %0) {
   ret void
 }
 
+; CHECK-LABEL: llvm.func @vector_deinterleave2
+define void @vector_deinterleave2(<4 x double> %0, <vscale x 8 x i32> %1) {
+  ; llvm.intr.vector.deinterleave2 %{{.*}} : (vector<4xf64>) -> !llvm.struct<(vector<2xf64>, vector<2xf64>)>
+  %3 = call { <2 x double>, <2 x double> } @llvm.vector.deinterleave2.v4f64(<4 x double> %0);
+  ; llvm.intr.vector.deinterleave2 %{{.*}} : (vector<[8]xi32>) -> !llvm.struct<(vector<[4]xi32>, vector<[4]xi32>)>
+  %4 = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %1);
+  ret void
+}
+
 ; CHECK-LABEL:  llvm.func @vector_predication_intrinsics
 define void @vector_predication_intrinsics(<8 x i32> %0, <8 x i32> %1, <8 x float> %2, <8 x float> %3, <8 x i64> %4, <8 x double> %5, <8 x ptr> %6, i32 %7, float %8, ptr %9, ptr %10, <8 x i1> %11, i32 %12) {
   ; CHECK: "llvm.intr.vp.add"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) : (vector<8xi32>, vector<8xi32>, vector<8xi1>, i32) -> vector<8xi32>
diff --git a/mlir/test/Target/LLVMIR/llvmir-intrinsics.mlir b/mlir/test/Target/LLVMIR/llvmir-intrinsics.mlir
index db5184a63d983..238c3e4263cb0 100644
--- a/mlir/test/Target/LLVMIR/llvmir-intrinsics.mlir
+++ b/mlir/test/Target/LLVMIR/llvmir-intrinsics.mlir
@@ -942,6 +942,17 @@ llvm.func @vector_insert_extract(%f256: vector<8xi32>, %f128: vector<4xi32>,
   llvm.return
 }
 
+// CHECK-LABEL: @vector_deinterleave2
+llvm.func @vector_deinterleave2(%vec1: vector<4xf64>, %vec2: vector<[8]xi32>) {
+  // CHECK: call { <2 x double>, <2 x double> } @llvm.vector.deinterleave2.v4f64(<4 x double> %{{.*}})
+  %0 = "llvm.intr.vector.deinterleave2" (%vec1) :
+              (vector<4xf64>) -> !llvm.struct<(vector<2xf64>, vector<2xf64>)>
+  // CHECK: call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %{{.*}})
+  %1 = "llvm.intr.vector.deinterleave2" (%vec2) :
+              (vector<[8]xi32>) -> !llvm.struct<(vector<[4]xi32>, vector<[4]xi32>)>
+  llvm.return
+}
+
 // CHECK-LABEL: @lifetime
 llvm.func @lifetime(%p: !llvm.ptr) {
   // CHECK: call void @llvm.lifetime.start
@@ -1148,6 +1159,8 @@ llvm.func @experimental_constrained_fptrunc(%s: f64, %v: vector<4xf32>) {
 // CHECK-DAG: declare <8 x i32> @llvm.vector.extract.v8i32.nxv4i32(<vscale x 4 x i32>, i64 immarg)
 // CHECK-DAG: declare <4 x i32> @llvm.vector.extract.v4i32.nxv4i32(<vscale x 4 x i32>, i64 immarg)
 // CHECK-DAG: declare <2 x i32> @llvm.vector.extract.v2i32.v8i32(<8 x i32>, i64 immarg)
+// CHECK-DAG: declare { <2 x double>, <2 x double> } @llvm.vector.deinterleave2.v4f64(<4 x double>)
+// CHECK-DAG: declare { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32>)
 // CHECK-DAG: declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture)
 // CHECK-DAG: declare void @llvm.lifetime.end.p0(i64 immarg, ptr nocapture)
 // CHECK-DAG: declare ptr @llvm.invariant.start.p0(i64 immarg, ptr nocapture)

[MacDue]

LGTM! Welcome to the project 😄

[github-actions]

@mub-at-arm Congratulations on having your first Pull Request (PR) merged into the LLVM Project!

Your changes will be combined with recent changes from other authors, then tested
by our build bots. If there is a problem with a build, you may receive a report in an email or a comment on this PR.

Please check whether problems have been caused by your change specifically, as
the builds can include changes from many authors. It is not uncommon for your
change to be included in a build that fails due to someone else's changes, or
infrastructure issues.

How to do this, and the rest of the post-merge process, is covered in detail here.

If your change does cause a problem, it may be reverted, or you can revert it yourself.
This is a normal part of LLVM development. You can fix your changes and open a new PR to merge them again.

If you don't get any reports, no action is required from you. Your changes are working as expected, well done!