Automerge: [LV] Don't skip instrs with side-effects in reg pressure computation. (#126415)

calculateRegisterUsage adds end points for each user of an instruction
to Ends and ignores instructions not added to it, i.e. instructions with
no users.

This means things like stores aren't included, which in turn means
values that are only used in stores are also not included for
consideration. This means we underestimate the register usage in cases
where the only users are things like stores.

Update the code to don't skip instructions without users (i.e. not in
Ends) if they have side-effects.

PR: llvm/llvm-project#126415

Author: fhahn

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -5270,8 +5270,9 @@ LoopVectorizationCostModel::calculateRegisterUsage(ArrayRef<ElementCount> VFs) {
     for (Instruction *ToRemove : List)
       OpenIntervals.erase(ToRemove);
 
-    // Ignore instructions that are never used within the loop.
-    if (!Ends.count(I))
+    // Ignore instructions that are never used within the loop and do not have
+    // side-effects.
+    if (!Ends.count(I) && !I->mayHaveSideEffects())
       continue;
 
     // Skip ignored values.

llvm/test/Transforms/LoopVectorize/AArch64/reg-usage.ll

@@ -15,8 +15,9 @@
 define void @get_invariant_reg_usage(ptr %z) {
 ; CHECK-LABEL: LV: Checking a loop in 'get_invariant_reg_usage'
 ; CHECK: LV(REG): VF = vscale x 16
-; CHECK-NEXT: LV(REG): Found max usage: 1 item
+; CHECK-NEXT: LV(REG): Found max usage: 2 item
 ; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 3 registers
+; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 1 registers 
 ; CHECK-NEXT: LV(REG): Found invariant usage: 2 item
 ; CHECK-NEXT: LV(REG): RegisterClass: Generic::ScalarRC, 2 registers
 ; CHECK-NEXT: LV(REG): RegisterClass: Generic::VectorRC, 8 registers

llvm/test/Transforms/LoopVectorize/LoongArch/reg-usage.ll

@@ -15,8 +15,9 @@ define void @bar(ptr %A, i32 signext %n) {
 ; CHECK-SCALAR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 1 registers
 ; CHECK-SCALAR-NEXT: LV: The target has 30 registers of LoongArch::GPRRC register class
 ; CHECK-SCALAR-NEXT: LV: The target has 32 registers of LoongArch::FPRRC register class
-; CHECK-VECTOR:      LV(REG): Found max usage: 1 item
+; CHECK-VECTOR:      LV(REG): Found max usage: 2 item
 ; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::VRRC, 3 registers
+; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 1 registers
 ; CHECK-VECTOR-NEXT: LV(REG): Found invariant usage: 1 item
 ; CHECK-VECTOR-NEXT: LV(REG): RegisterClass: LoongArch::GPRRC, 1 registers
 ; CHECK-VECTOR-NEXT: LV: The target has 32 registers of LoongArch::VRRC register class

llvm/test/Transforms/LoopVectorize/PowerPC/reg-usage.ll

@@ -179,7 +179,7 @@ define void @double_(ptr nocapture %A, i32 %n) nounwind uwtable ssp {
 
 ;CHECK-PWR9: LV(REG): VF = 1
 ;CHECK-PWR9: LV(REG): Found max usage: 2 item
-;CHECK-PWR9-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 2 registers
+;CHECK-PWR9-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 3 registers
 ;CHECK-PWR9-NEXT: LV(REG): RegisterClass: PPC::VSXRC, 5 registers
 ;CHECK-PWR9: LV(REG): Found invariant usage: 1 item
 ;CHECK-PWR9-NEXT: LV(REG): RegisterClass: PPC::GPRRC, 1 registers
@@ -248,7 +248,7 @@ define void @fp16_(ptr nocapture readonly %pIn, ptr nocapture %pOut, i32 %numRow
 ;CHECK-LABEL: fp16_
 ;CHECK: LV(REG): VF = 1
 ;CHECK: LV(REG): Found max usage: 2 item
-;CHECK: LV(REG): RegisterClass: PPC::GPRRC, 4 registers
+;CHECK: LV(REG): RegisterClass: PPC::GPRRC, 5 registers
 ;CHECK: LV(REG): RegisterClass: PPC::VSXRC, 2 registers
 entry:
   %tmp.0.extract.trunc = trunc i32 %scale.coerce to i16

llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll

@@ -128,8 +128,9 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LV(REG): At #5 Interval # 3
 ; CHECK-NEXT:  LV(REG): At #6 Interval # 3
 ; CHECK-NEXT:  LV(REG): At #7 Interval # 3
-; CHECK-NEXT:  LV(REG): At #9 Interval # 1
-; CHECK-NEXT:  LV(REG): At #10 Interval # 2
+; CHECK-NEXT:  LV(REG): At #8 Interval # 3
+; CHECK-NEXT:  LV(REG): At #9 Interval # 2
+; CHECK-NEXT:  LV(REG): At #10 Interval # 3
 ; CHECK-NEXT:  LV(REG): VF = vscale x 4
 ; CHECK-NEXT:  LV(REG): Found max usage: 2 item
 ; CHECK-NEXT:  LV(REG): RegisterClass: RISCV::GPRRC, 3 registers
@@ -377,8 +378,9 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LV(REG): At #5 Interval # 3
 ; CHECK-NEXT:  LV(REG): At #6 Interval # 3
 ; CHECK-NEXT:  LV(REG): At #7 Interval # 3
-; CHECK-NEXT:  LV(REG): At #9 Interval # 1
-; CHECK-NEXT:  LV(REG): At #10 Interval # 2
+; CHECK-NEXT:  LV(REG): At #8 Interval # 3
+; CHECK-NEXT:  LV(REG): At #9 Interval # 2
+; CHECK-NEXT:  LV(REG): At #10 Interval # 3
 ; CHECK-NEXT:  LV(REG): VF = vscale x 4
 ; CHECK-NEXT:  LV(REG): Found max usage: 2 item
 ; CHECK-NEXT:  LV(REG): RegisterClass: RISCV::GPRRC, 3 registers