[PATCH] D98247: [X86][AMX] Prevent transforming load pointer from <256 x i32>* to x86_amx*.

[LuoYuanke via Phabricator via llvm-commits]

LuoYuanke updated this revision to Diff 329823.
LuoYuanke added a comment.

Rebase.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98247/new/

https://reviews.llvm.org/D98247

Files:
  llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
  llvm/test/Transforms/InstCombine/X86/x86-amx.ll


Index: llvm/test/Transforms/InstCombine/X86/x86-amx.ll
===================================================================
--- llvm/test/Transforms/InstCombine/X86/x86-amx.ll
+++ llvm/test/Transforms/InstCombine/X86/x86-amx.ll
@@ -9,22 +9,22 @@
 ; CHECK:       for.cond9:
 ; CHECK-NEXT:    br i1 undef, label [[FOR_BODY14:%.*]], label [[EXIT:%.*]]
 ; CHECK:       for.body14:
-; CHECK-NEXT:    [[TMP0:%.*]] = bitcast <256 x i32>* [[ARRAYIDX16:%.*]] to x86_amx*
-; CHECK-NEXT:    [[T51:%.*]] = load x86_amx, x86_amx* [[TMP0]], align 64
+; CHECK-NEXT:    [[T5:%.*]] = load <256 x i32>, <256 x i32>* [[ARRAYIDX16:%.*]], align 64
 ; CHECK-NEXT:    br label [[FOR_COND18:%.*]]
 ; CHECK:       for.cond18:
-; CHECK-NEXT:    [[TMP1:%.*]] = phi x86_amx [ [[T51]], [[FOR_BODY14]] ], [ [[T11:%.*]], [[FOR_BODY24:%.*]] ]
+; CHECK-NEXT:    [[SUB_C_SROA_0_0:%.*]] = phi <256 x i32> [ [[T5]], [[FOR_BODY14]] ], [ [[T12:%.*]], [[FOR_BODY24:%.*]] ]
 ; CHECK-NEXT:    br i1 undef, label [[FOR_BODY24]], label [[FOR_COND_CLEANUP23:%.*]]
 ; CHECK:       for.cond.cleanup23:
-; CHECK-NEXT:    [[TMP2:%.*]] = bitcast x86_amx [[TMP1]] to <256 x i32>
-; CHECK-NEXT:    store <256 x i32> [[TMP2]], <256 x i32>* [[ARRAYIDX16]], align 64
+; CHECK-NEXT:    store <256 x i32> [[SUB_C_SROA_0_0]], <256 x i32>* [[ARRAYIDX16]], align 64
 ; CHECK-NEXT:    br label [[FOR_COND9]]
 ; CHECK:       for.body24:
 ; CHECK-NEXT:    [[T6:%.*]] = load <256 x i32>, <256 x i32>* [[ARRAYIDX29:%.*]], align 64
 ; CHECK-NEXT:    [[T7:%.*]] = load <256 x i32>, <256 x i32>* [[ARRAYIDX35:%.*]], align 64
+; CHECK-NEXT:    [[T8:%.*]] = bitcast <256 x i32> [[SUB_C_SROA_0_0]] to x86_amx
 ; CHECK-NEXT:    [[T9:%.*]] = bitcast <256 x i32> [[T6]] to x86_amx
 ; CHECK-NEXT:    [[T10:%.*]] = bitcast <256 x i32> [[T7]] to x86_amx
-; CHECK-NEXT:    [[T11]] = call x86_amx @llvm.x86.tdpbssd.internal(i16 1, i16 4, i16 4, x86_amx [[TMP1]], x86_amx [[T9]], x86_amx [[T10]])
+; CHECK-NEXT:    [[T11:%.*]] = call x86_amx @llvm.x86.tdpbssd.internal(i16 1, i16 4, i16 4, x86_amx [[T8]], x86_amx [[T9]], x86_amx [[T10]])
+; CHECK-NEXT:    [[T12]] = bitcast x86_amx [[T11]] to <256 x i32>
 ; CHECK-NEXT:    br label [[FOR_COND18]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
Index: llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
===================================================================
--- llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -2395,6 +2395,12 @@
         continue;
 
       if (auto *LI = dyn_cast<LoadInst>(IncValue)) {
+        // Don't transform "load <256 x i32>, <256 x i32>*" to
+        // "load x86_amx, x86_amx*", because we don't have a corresponding
+        // instruction to load x86_amx. Doing the transform causes trouble
+        // to lower "load x86_amx" instruction in backend.
+        if (DestTy->isX86_AMXTy())
+          return nullptr;
         // If there is a sequence of one or more load instructions, each loaded
         // value is used as address of later load instruction, bitcast is
         // necessary to change the value type, don't optimize it. For


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D98247.329823.patch
Type: text/x-patch
Size: 3123 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210311/f4f0fdb4/attachment.bin>