From cb3924b6059db3762743d52901f25e98824fe0e0 Mon Sep 17 00:00:00 2001
From: Andreu Carminati <andreu.carminati@amd.com>
Date: Mon, 11 Nov 2024 12:34:17 +0000
Subject: [PATCH] [AIEX] Shift G_CONCAT_VECTORS closer to the user

When commiting applyUpdToConcat. This enables more postinc combiner cases.
---
 llvm/lib/Target/AIE/AIECombinerHelper.cpp     | 17 +++++++++-
 .../AIE/GlobalISel/combine-upd-concat.mir     | 33 +++++++++++++++++++
 2 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/AIE/AIECombinerHelper.cpp b/llvm/lib/Target/AIE/AIECombinerHelper.cpp
index 066484417e62..92a192b39acc 100644
--- a/llvm/lib/Target/AIE/AIECombinerHelper.cpp
+++ b/llvm/lib/Target/AIE/AIECombinerHelper.cpp
@@ -1367,10 +1367,25 @@ bool llvm::matchUpdToConcat(MachineInstr &MI, MachineRegisterInfo &MRI,
   return true;
 }
 
+/// Find a use of \p MI in the same block where it can be moved
+MachineInstr &findClosestToUseInsertPoint(MachineInstr &MI,
+                                          MachineRegisterInfo &MRI) {
+
+  for (auto &User : MRI.use_instructions(MI.getOperand(0).getReg())) {
+    if (User.isPHI())
+      continue;
+    if (User.getParent() == MI.getParent() && canDelayMemOp(MI, User, MRI))
+      return User;
+  }
+
+  return MI;
+}
+
 void llvm::applyUpdToConcat(MachineInstr &MI, MachineRegisterInfo &MRI,
                             MachineIRBuilder &B,
                             std::map<unsigned, Register> &IndexRegMap) {
-  B.setInstrAndDebugLoc(MI);
+  B.setDebugLoc(MI.getDebugLoc());
+  B.setInstr(findClosestToUseInsertPoint(MI, MRI));
 
   SmallVector<Register, 4> SrcRegs;
   for (unsigned Op = 0; Op < IndexRegMap.size(); Op++) {
diff --git a/llvm/test/CodeGen/AIE/GlobalISel/combine-upd-concat.mir b/llvm/test/CodeGen/AIE/GlobalISel/combine-upd-concat.mir
index c17fddf54b75..705a68302a3f 100644
--- a/llvm/test/CodeGen/AIE/GlobalISel/combine-upd-concat.mir
+++ b/llvm/test/CodeGen/AIE/GlobalISel/combine-upd-concat.mir
@@ -178,3 +178,36 @@ body:             |
     $wh0 = COPY %254:_(<8 x s32>)
     $wh1 = COPY %255:_(<8 x s32>)
 ...
+
+---
+name:            upd_I512.I256_shift_insert_point
+body:             |
+  bb.0:
+    liveins: $p0, $wl2, $wl3
+    ; CHECK-LABEL: name: upd_I512.I256_shift_insert_point
+    ; CHECK: liveins: $p0, $wl2, $wl3
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<32 x s8>) = COPY $wl2
+    ; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(<32 x s8>) = COPY $wl3
+    ; CHECK-NEXT: [[INT:%[0-9]+]]:_(<64 x s8>) = G_INTRINSIC intrinsic(@llvm.aie2.v64int8)
+    ; CHECK-NEXT: [[BITCAST:%[0-9]+]]:_(<16 x s32>) = G_BITCAST [[INT]](<64 x s8>)
+    ; CHECK-NEXT: [[BITCAST1:%[0-9]+]]:_(<8 x s32>) = G_BITCAST [[COPY]](<32 x s8>)
+    ; CHECK-NEXT: [[BITCAST2:%[0-9]+]]:_(<8 x s32>) = G_BITCAST [[COPY1]](<32 x s8>)
+    ; CHECK-NEXT: $x1 = COPY [[BITCAST]](<16 x s32>)
+    ; CHECK-NEXT: $x2 = COPY [[BITCAST]](<16 x s32>)
+    ; CHECK-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s32>) = G_CONCAT_VECTORS [[BITCAST1]](<8 x s32>), [[BITCAST2]](<8 x s32>)
+    ; CHECK-NEXT: $x0 = COPY [[CONCAT_VECTORS]](<16 x s32>)
+    %95:_(<32 x s8>) = COPY $wl2
+    %98:_(<32 x s8>) = COPY $wl3
+    %8:_(<64 x s8>) = G_INTRINSIC intrinsic(@llvm.aie2.v64int8)
+    %9:_(<16 x s32>) = G_BITCAST %8(<64 x s8>)
+    %21:_(s32) = G_CONSTANT i32 0
+    %51:_(s32) = G_CONSTANT i32 1
+    %96:_(<8 x s32>) = G_BITCAST %95(<32 x s8>)
+    %97:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.aie2.upd.I512.I256), %9(<16 x s32>), %96(<8 x s32>), %21(s32)
+    %99:_(<8 x s32>) = G_BITCAST %98(<32 x s8>)
+    %100:_(<16 x s32>) = G_INTRINSIC intrinsic(@llvm.aie2.upd.I512.I256), %97(<16 x s32>), %99(<8 x s32>), %51(s32)
+    $x1 = COPY %9:_(<16 x s32>)
+    $x2 = COPY %9:_(<16 x s32>)
+    $x0 = COPY %100:_(<16 x s32>)
+...