[PATCH] D156235: [MachineBlockPlacement] Remove the pad limit for no-fallthrough loops

[Momchil Velikov via Phabricator via llvm-commits]

chill updated this revision to Diff 545084.

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156235/new/

https://reviews.llvm.org/D156235

Files:
  llvm/lib/CodeGen/MachineBlockPlacement.cpp
  llvm/test/CodeGen/AArch64/loop-align-limit.ll
  llvm/test/CodeGen/AArch64/merge-store-dependency.ll


Index: llvm/test/CodeGen/AArch64/merge-store-dependency.ll
===================================================================
--- llvm/test/CodeGen/AArch64/merge-store-dependency.ll
+++ llvm/test/CodeGen/AArch64/merge-store-dependency.ll
@@ -19,12 +19,12 @@
 ; A53-NEXT:    mov x8, x0
 ; A53-NEXT:    mov x19, x8
 ; A53-NEXT:    mov w0, w1
-; A53-NEXT:    mov w9, #256
+; A53-NEXT:    mov w9, #256 // =0x100
 ; A53-NEXT:    stp x2, x3, [x8, #32]
 ; A53-NEXT:    mov x2, x8
 ; A53-NEXT:    str q0, [x19, #16]!
 ; A53-NEXT:    str w1, [x19]
-; A53-NEXT:    mov w1, #4
+; A53-NEXT:    mov w1, #4 // =0x4
 ; A53-NEXT:    str q0, [x8]
 ; A53-NEXT:    strh w9, [x8, #24]
 ; A53-NEXT:    str wzr, [x8, #20]
@@ -51,7 +51,7 @@
 ; A53-NEXT:    .cfi_restore w19
 ; A53-NEXT:    .cfi_restore w30
 ; A53-NEXT:    ret
-; A53-NEXT:    .p2align 4, , 8
+; A53-NEXT:    .p2align 4
 ; A53-NEXT:  .LBB0_4: // %while.body.i.split
 ; A53-NEXT:    // =>This Inner Loop Header: Depth=1
 ; A53-NEXT:    .cfi_restore_state
Index: llvm/test/CodeGen/AArch64/loop-align-limit.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AArch64/loop-align-limit.ll
@@ -0,0 +1,43 @@
+; RUN: llc                            < %s | FileCheck %s -check-prefixes CHECK,CHECK-NOLIMIT
+; RUN: llc -max-bytes-for-alignment=2 < %s | FileCheck %s -check-prefixes CHECK,CHECK-LIMIT
+target triple = "aarch64-linux"
+
+declare i1 @cond(i64, i64)
+declare i32 @h(i32)
+
+define i32 @g(ptr  %a, i64 %n, i32 %d) "tune-cpu"="neoverse-v1" {
+; CHECK-LABEL:        g:
+; CHECK:              b .LBB0_2
+; CHECK-NOLIMIT-NEXT: .p2align 5{{$}}
+; CHECK-LIMIT-NEXT:   .p2align 5, , 2
+; CHECK-NEXT:         // %if.end
+entry:
+  br label %loop
+
+loop:
+    %i = phi i64 [0, %entry], [%i.next, %if.end]
+    %s = phi i32 [0, %entry], [%s.next, %if.end]
+    %c = icmp slt i64 %i, %n
+    br i1 %c, label %loop.body, label %exit
+
+loop.body:
+    %p = getelementptr i32, ptr %a, i64 %i
+    %v = load i32, ptr %p
+    %c1 = icmp slt i32 %d, 1
+    br i1 %c1, label %if.then, label %if.end
+
+if.then:
+    %v0 = call i32 @h(i32 %v)
+    br label %if.end
+
+if.end:
+    %w = phi i32 [%v0, %if.then], [%v, %loop.body]
+    %s.next = add i32 %s, %w
+    %i.next = add i64 %i, 1
+    br label %loop
+
+
+exit:
+    ret i32 %s
+}
+
Index: llvm/lib/CodeGen/MachineBlockPlacement.cpp
===================================================================
--- llvm/lib/CodeGen/MachineBlockPlacement.cpp
+++ llvm/lib/CodeGen/MachineBlockPlacement.cpp
@@ -2950,7 +2950,12 @@
     // Force alignment if all the predecessors are jumps. We already checked
     // that the block isn't cold above.
     if (!LayoutPred->isSuccessor(ChainBB)) {
-      ChainBB->setAlignment(Align, MaxBytesForAlignment);
+      if (MaxBytesForAlignmentOverride.getNumOccurrences() == 0 &&
+          L->isInnermost() &&
+          (ChainBB == LoopHeader || MLI->getLoopFor(LayoutPred) != L))
+        ChainBB->setAlignment(Align, 0);
+      else
+        ChainBB->setAlignment(Align, MaxBytesForAlignment);
       continue;
     }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156235.545084.patch
Type: text/x-patch
Size: 3093 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230728/43fcdb48/attachment.bin>