[llvm] 92e0c0d - [DAG] Restrict insert_subvector undef, splat_veector, dontcare transform

[Philip Reames via llvm-commits]

Author: Philip Reames
Date: 2023-08-18T12:44:09-07:00
New Revision: 92e0c0dc1a4f015e05a54094a4a94ddb0c5d9112

URL: https://github.com/llvm/llvm-project/commit/92e0c0dc1a4f015e05a54094a4a94ddb0c5d9112
DIFF: https://github.com/llvm/llvm-project/commit/92e0c0dc1a4f015e05a54094a4a94ddb0c5d9112.diff

LOG: [DAG] Restrict insert_subvector undef, splat_veector, dontcare transform

On the extract_subvector side, we already have the restriction. With D158201, we'd start getting unprofitable splat combines unless we add the same one on the extract_subvector side.

Differential Revision: https://reviews.llvm.org/D158202

Added: 
    

Modified: 
    llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
    llvm/test/CodeGen/RISCV/rvv/splats-with-mixed-vl.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index c6a05ef809765d..e2889ead51a9eb 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -25620,7 +25620,8 @@ SDValue DAGCombiner::visitINSERT_SUBVECTOR(SDNode *N) {
   // Simplify scalar inserts into an undef vector:
   // insert_subvector undef, (splat X), N2 -> splat X
   if (N0.isUndef() && N1.getOpcode() == ISD::SPLAT_VECTOR)
-    return DAG.getNode(ISD::SPLAT_VECTOR, SDLoc(N), VT, N1.getOperand(0));
+    if (DAG.isConstantValueOfAnyType(N1.getOperand(0)) || N1.hasOneUse())
+      return DAG.getNode(ISD::SPLAT_VECTOR, SDLoc(N), VT, N1.getOperand(0));
 
   // If we are inserting a bitcast value into an undef, with the same
   // number of elements, just use the bitcast input of the extract.

diff  --git a/llvm/test/CodeGen/RISCV/rvv/splats-with-mixed-vl.ll b/llvm/test/CodeGen/RISCV/rvv/splats-with-mixed-vl.ll
index d9d6d4982d7777..fc67eec0f48a05 100644
--- a/llvm/test/CodeGen/RISCV/rvv/splats-with-mixed-vl.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/splats-with-mixed-vl.ll
@@ -159,10 +159,8 @@ define <vscale x 1 x i32> @extract_vector_multiuse2(ptr %p, ptr %p2, i32 %v) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a1, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
-; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v9, a2
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vse32.v v9, (a0)
+; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    ret
   %elt.head = insertelement <vscale x 1 x i32> poison, i32 %v, i32 0
   %splat = shufflevector <vscale x 1 x i32> %elt.head, <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer
@@ -177,10 +175,8 @@ define void @extract_vector_mixed1(ptr %p, ptr %p2, i32 %v) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a3, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
-; CHECK-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v9, a2
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vse32.v v9, (a0)
+; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    vsetvli a0, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vse32.v v8, (a1)
 ; CHECK-NEXT:    ret
@@ -200,8 +196,6 @@ define void @extract_vector_mixed2(ptr %p, ptr %p2, i32 %v) {
 ; CHECK-NEXT:    vsetvli a3, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
 ; CHECK-NEXT:    vse32.v v8, (a0)
-; CHECK-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v8, a2
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; CHECK-NEXT:    vse32.v v8, (a1)
 ; CHECK-NEXT:    ret
@@ -219,12 +213,9 @@ define void @extract_vector_mixed3(ptr %p, ptr %p2, i32 %v) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a3, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vmv.v.x v8, a2
-; CHECK-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
-; CHECK-NEXT:    vmv.v.x v9, a2
-; CHECK-NEXT:    vsetvli a2, zero, e32, mf2, ta, ma
 ; CHECK-NEXT:    vse32.v v8, (a0)
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
-; CHECK-NEXT:    vse32.v v9, (a1)
+; CHECK-NEXT:    vse32.v v8, (a1)
 ; CHECK-NEXT:    ret
   %elt.head = insertelement <vscale x 1 x i32> poison, i32 %v, i32 0
   %splat = shufflevector <vscale x 1 x i32> %elt.head, <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer