[PATCH] D141576: [CodeGen] Prevent overlapping subregs in getCoveringSubRegIndexes

[Pierre van Houtryve via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGfd3300123de4: [CodeGen] Prevent overlapping subregs in getCoveringSubRegIndexes (authored by Pierre-vh).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D141576/new/

https://reviews.llvm.org/D141576

Files:
  llvm/lib/CodeGen/TargetRegisterInfo.cpp
  llvm/test/CodeGen/AMDGPU/extend-phi-subrange-not-in-parent.mir
  llvm/test/CodeGen/AMDGPU/split-liverange-overlapping-copies.mir


Index: llvm/test/CodeGen/AMDGPU/split-liverange-overlapping-copies.mir
===================================================================
--- llvm/test/CodeGen/AMDGPU/split-liverange-overlapping-copies.mir
+++ llvm/test/CodeGen/AMDGPU/split-liverange-overlapping-copies.mir
@@ -41,7 +41,8 @@
   ; CHECK-NEXT:   successors: %bb.3(0x80000000)
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   undef %6.sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15_sub16:av_1024_align2 = COPY [[COPY]].sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15_sub16 {
-  ; CHECK-NEXT:     internal %6.sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30_sub31:av_1024_align2 = COPY [[COPY]].sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30_sub31
+  ; CHECK-NEXT:     internal %6.sub17_lo16_sub17_hi16_sub18_lo16_sub18_hi16_sub19_lo16_sub19_hi16_sub20_lo16_sub20_hi16_sub21_lo16_sub21_hi16_sub22_lo16_sub22_hi16_sub23_lo16_sub23_hi16_sub24_lo16_sub24_hi16_sub25_lo16_sub25_hi16_sub26_lo16_sub26_hi16_sub27_lo16_sub27_hi16_sub28_lo16_sub28_hi16:av_1024_align2 = COPY [[COPY]].sub17_lo16_sub17_hi16_sub18_lo16_sub18_hi16_sub19_lo16_sub19_hi16_sub20_lo16_sub20_hi16_sub21_lo16_sub21_hi16_sub22_lo16_sub22_hi16_sub23_lo16_sub23_hi16_sub24_lo16_sub24_hi16_sub25_lo16_sub25_hi16_sub26_lo16_sub26_hi16_sub27_lo16_sub27_hi16_sub28_lo16_sub28_hi16
+  ; CHECK-NEXT:     internal %6.sub29_sub30_sub31:av_1024_align2 = COPY [[COPY]].sub29_sub30_sub31
   ; CHECK-NEXT:   }
   ; CHECK-NEXT:   %6.sub0:av_1024_align2 = IMPLICIT_DEF
   ; CHECK-NEXT:   S_NOP 0, implicit %6.sub0
@@ -116,7 +117,8 @@
   ; CHECK-NEXT:   successors: %bb.3(0x80000000)
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   undef %6.sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15_sub16:av_1024 = COPY [[COPY]].sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15_sub16 {
-  ; CHECK-NEXT:     internal %6.sub15_sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30:av_1024 = COPY [[COPY]].sub15_sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30
+  ; CHECK-NEXT:     internal %6.sub17_lo16_sub17_hi16_sub18_lo16_sub18_hi16_sub19_lo16_sub19_hi16_sub20_lo16_sub20_hi16_sub21_lo16_sub21_hi16_sub22_lo16_sub22_hi16_sub23_lo16_sub23_hi16_sub24_lo16_sub24_hi16_sub25_lo16_sub25_hi16_sub26_lo16_sub26_hi16_sub27_lo16_sub27_hi16_sub28_lo16_sub28_hi16:av_1024 = COPY [[COPY]].sub17_lo16_sub17_hi16_sub18_lo16_sub18_hi16_sub19_lo16_sub19_hi16_sub20_lo16_sub20_hi16_sub21_lo16_sub21_hi16_sub22_lo16_sub22_hi16_sub23_lo16_sub23_hi16_sub24_lo16_sub24_hi16_sub25_lo16_sub25_hi16_sub26_lo16_sub26_hi16_sub27_lo16_sub27_hi16_sub28_lo16_sub28_hi16
+  ; CHECK-NEXT:     internal %6.sub29_sub30:av_1024 = COPY [[COPY]].sub29_sub30
   ; CHECK-NEXT:   }
   ; CHECK-NEXT:   %6.sub0:av_1024 = IMPLICIT_DEF
   ; CHECK-NEXT:   %6.sub31:av_1024 = IMPLICIT_DEF
Index: llvm/test/CodeGen/AMDGPU/extend-phi-subrange-not-in-parent.mir
===================================================================
--- llvm/test/CodeGen/AMDGPU/extend-phi-subrange-not-in-parent.mir
+++ llvm/test/CodeGen/AMDGPU/extend-phi-subrange-not-in-parent.mir
@@ -36,7 +36,8 @@
   ; CHECK-NEXT:   successors: %bb.3(0x80000000)
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   undef %6.sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15_sub16:av_1024_align2 = COPY [[COPY]].sub1_sub2_sub3_sub4_sub5_sub6_sub7_sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15_sub16 {
-  ; CHECK-NEXT:     internal %6.sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30_sub31:av_1024_align2 = COPY [[COPY]].sub16_sub17_sub18_sub19_sub20_sub21_sub22_sub23_sub24_sub25_sub26_sub27_sub28_sub29_sub30_sub31
+  ; CHECK-NEXT:     internal %6.sub17_lo16_sub17_hi16_sub18_lo16_sub18_hi16_sub19_lo16_sub19_hi16_sub20_lo16_sub20_hi16_sub21_lo16_sub21_hi16_sub22_lo16_sub22_hi16_sub23_lo16_sub23_hi16_sub24_lo16_sub24_hi16_sub25_lo16_sub25_hi16_sub26_lo16_sub26_hi16_sub27_lo16_sub27_hi16_sub28_lo16_sub28_hi16:av_1024_align2 = COPY [[COPY]].sub17_lo16_sub17_hi16_sub18_lo16_sub18_hi16_sub19_lo16_sub19_hi16_sub20_lo16_sub20_hi16_sub21_lo16_sub21_hi16_sub22_lo16_sub22_hi16_sub23_lo16_sub23_hi16_sub24_lo16_sub24_hi16_sub25_lo16_sub25_hi16_sub26_lo16_sub26_hi16_sub27_lo16_sub27_hi16_sub28_lo16_sub28_hi16
+  ; CHECK-NEXT:     internal %6.sub29_sub30_sub31:av_1024_align2 = COPY [[COPY]].sub29_sub30_sub31
   ; CHECK-NEXT:   }
   ; CHECK-NEXT:   %6.sub0:av_1024_align2 = IMPLICIT_DEF
   ; CHECK-NEXT:   S_NOP 0, implicit %6.sub0
Index: llvm/lib/CodeGen/TargetRegisterInfo.cpp
===================================================================
--- llvm/lib/CodeGen/TargetRegisterInfo.cpp
+++ llvm/lib/CodeGen/TargetRegisterInfo.cpp
@@ -571,10 +571,14 @@
         break;
       }
 
-      // Try to cover as much of the remaining lanes as possible but
-      // as few of the already covered lanes as possible.
-      int Cover = (SubRegMask & LanesLeft).getNumLanes() -
-                  (SubRegMask & ~LanesLeft).getNumLanes();
+      // Do not cover already-covered lanes to avoid creating cycles
+      // in copy bundles (= bundle contains copies that write to the
+      // registers).
+      if ((SubRegMask & ~LanesLeft).any())
+        continue;
+
+      // Try to cover as many of the remaining lanes as possible.
+      const int Cover = (SubRegMask & LanesLeft).getNumLanes();
       if (Cover > BestCover) {
         BestCover = Cover;
         BestIdx = Idx;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D141576.490067.patch
Type: text/x-patch
Size: 5646 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230118/916b7ae9/attachment-0001.bin>