[llvm] 13188bc - [GlobalISel]: Simplify udiv lowering by determining known zeros (#89678)

[via llvm-commits]

Author: AtariDreams
Date: 2024-04-24T22:14:02+02:00
New Revision: 13188bcd9f748dee13cf848340833f6eec2d90d4

URL: https://github.com/llvm/llvm-project/commit/13188bcd9f748dee13cf848340833f6eec2d90d4
DIFF: https://github.com/llvm/llvm-project/commit/13188bcd9f748dee13cf848340833f6eec2d90d4.diff

LOG: [GlobalISel]: Simplify udiv lowering by determining known zeros (#89678)

Added: 
    

Modified: 
    llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
    llvm/test/CodeGen/AArch64/GlobalISel/combine-udiv.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
index 050f42e9039b34..653e7689b57743 100644
--- a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
@@ -5069,6 +5069,9 @@ MachineInstr *CombinerHelper::buildUDivUsingMul(MachineInstr &MI) {
   const unsigned EltBits = ScalarTy.getScalarSizeInBits();
   LLT ShiftAmtTy = getTargetLowering().getPreferredShiftAmountTy(Ty);
   LLT ScalarShiftAmtTy = ShiftAmtTy.getScalarType();
+
+  unsigned KnownLeadingZeros =
+      KB ? KB->getKnownBits(LHS).countMinLeadingZeros() : 0;
   auto &MIB = Builder;
 
   bool UseNPQ = false;
@@ -5086,8 +5089,12 @@ MachineInstr *CombinerHelper::buildUDivUsingMul(MachineInstr &MI) {
     // at the end.
     // TODO: Use undef values for divisor of 1.
     if (!Divisor.isOne()) {
+
+      // UnsignedDivisionByConstantInfo doesn't work correctly if leading zeros
+      // in the dividend exceeds the leading zeros for the divisor.
       UnsignedDivisionByConstantInfo magics =
-          UnsignedDivisionByConstantInfo::get(Divisor);
+          UnsignedDivisionByConstantInfo::get(
+              Divisor, std::min(KnownLeadingZeros, Divisor.countl_zero()));
 
       Magic = std::move(magics.Magic);
 

diff  --git a/llvm/test/CodeGen/AArch64/GlobalISel/combine-udiv.ll b/llvm/test/CodeGen/AArch64/GlobalISel/combine-udiv.ll
index 9a525151ca328b..c97a00ccdd4557 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/combine-udiv.ll
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/combine-udiv.ll
@@ -243,3 +243,29 @@ define <8 x i16> @pr38477(<8 x i16> %a0) {
   %1 = udiv <8 x i16> %a0, <i16 1, i16 119, i16 73, i16 -111, i16 -3, i16 118, i16 32, i16 31>
   ret <8 x i16> %1
 }
+
+define i32 @udiv_div_by_180(i32 %x)
+; SDAG-LABEL: udiv_div_by_180:
+; SDAG:       // %bb.0:
+; SDAG-NEXT:    mov w8, #5826 // =0x16c2
+; SDAG-NEXT:    and w9, w0, #0xff
+; SDAG-NEXT:    movk w8, #364, lsl #16
+; SDAG-NEXT:    umull x8, w9, w8
+; SDAG-NEXT:    lsr x0, x8, #32
+; SDAG-NEXT:    // kill: def $w0 killed $w0 killed $x0
+; SDAG-NEXT:    ret
+;
+; GISEL-LABEL: udiv_div_by_180:
+; GISEL:       // %bb.0:
+; GISEL-NEXT:    uxtb w8, w0
+; GISEL-NEXT:    mov w9, #5826 // =0x16c2
+; GISEL-NEXT:    movk w9, #364, lsl #16
+; GISEL-NEXT:    umull x8, w8, w9
+; GISEL-NEXT:    lsr x0, x8, #32
+; GISEL-NEXT:    // kill: def $w0 killed $w0 killed $x0
+; GISEL-NEXT:    ret
+{
+  %truncate = and i32 %x, 255
+  %udiv = udiv i32 %truncate, 180
+  ret i32 %udiv
+}