[PATCH] D116469: [AMDGPU] Correct the known bits calculation for MUL_I24.

[Craig Topper via Phabricator via llvm-commits]

craig.topper updated this revision to Diff 399897.
craig.topper added a comment.

Rebase with test. Test will be added in a separate review.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D116469/new/

https://reviews.llvm.org/D116469

Files:
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/amdgpu-mul24-knownbits.ll


Index: llvm/test/CodeGen/AMDGPU/amdgpu-mul24-knownbits.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/amdgpu-mul24-knownbits.ll
+++ llvm/test/CodeGen/AMDGPU/amdgpu-mul24-knownbits.ll
@@ -33,7 +33,11 @@
 ; GCN-LABEL: f:
 ; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN-NEXT:    v_mov_b32_e32 v0, 0
+; GCN-NEXT:    s_mov_b32 s4, 0xffff80
+; GCN-NEXT:    v_or_b32_e32 v0, s4, v0
+; GCN-NEXT:    v_or_b32_e32 v1, s4, v1
+; GCN-NEXT:    v_mul_i32_i24_e32 v0, v0, v1
+; GCN-NEXT:    v_lshrrev_b32_e32 v0, 14, v0
 ; GCN-NEXT:    s_setpc_b64 s[30:31]
   %xx = or i32 %x, -128 ; 0xffffff80
   %yy = or i32 %y, -128 ; 0xffffff80
Index: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -4626,11 +4626,12 @@
     RHSKnown = RHSKnown.trunc(24);
 
     if (Opc == AMDGPUISD::MUL_I24) {
-      unsigned LHSValBits = 24 - LHSKnown.countMinSignBits();
-      unsigned RHSValBits = 24 - RHSKnown.countMinSignBits();
-      unsigned MaxValBits = std::min(LHSValBits + RHSValBits, 32u);
-      if (MaxValBits >= 32)
+      unsigned LHSValBits = LHSKnown.countMaxSignificantBits();
+      unsigned RHSValBits = RHSKnown.countMaxSignificantBits();
+      unsigned MaxValBits = LHSValBits + RHSValBits;
+      if (MaxValBits > 32)
         break;
+      unsigned SignBits = 32 - MaxValBits + 1;
       bool LHSNegative = LHSKnown.isNegative();
       bool LHSNonNegative = LHSKnown.isNonNegative();
       bool LHSPositive = LHSKnown.isStrictlyPositive();
@@ -4639,16 +4640,16 @@
       bool RHSPositive = RHSKnown.isStrictlyPositive();
 
       if ((LHSNonNegative && RHSNonNegative) || (LHSNegative && RHSNegative))
-        Known.Zero.setHighBits(32 - MaxValBits);
+        Known.Zero.setHighBits(SignBits);
       else if ((LHSNegative && RHSPositive) || (LHSPositive && RHSNegative))
-        Known.One.setHighBits(32 - MaxValBits);
+        Known.One.setHighBits(SignBits);
     } else {
-      unsigned LHSValBits = 24 - LHSKnown.countMinLeadingZeros();
-      unsigned RHSValBits = 24 - RHSKnown.countMinLeadingZeros();
-      unsigned MaxValBits = std::min(LHSValBits + RHSValBits, 32u);
+      unsigned LHSValBits = LHSKnown.countMaxActiveBits();
+      unsigned RHSValBits = RHSKnown.countMaxActiveBits();
+      unsigned MaxValBits = LHSValBits + RHSValBits;
       if (MaxValBits >= 32)
         break;
-      Known.Zero.setHighBits(32 - MaxValBits);
+      Known.Zero.setBitsFrom(MaxValBits);
     }
     break;
   }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D116469.399897.patch
Type: text/x-patch
Size: 2666 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220114/cb3a9d6f/attachment.bin>