[SLP]Improve final minbitwidth analysis attempt.

Added part for demanded bits analysis in the IsPotentiallyTruncated to
improve minbitwidth analysis final attempts.

Metric: size..text

Program                                                                                                                                                size..text
                                                                                                                                                       results     results0    diff
                                                                           test-suite :: MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm.test    43069.00    42973.00 -0.2%
                                                                                  test-suite :: MultiSource/Benchmarks/mediabench/gsm/toast/toast.test    43066.00    42970.00 -0.2%

Extra trunc instructions are emitted to operate with <32 x i8> instead
of <32 x i16>, will be removed in the next patches.

Reviewers: RKSimon

Reviewed By: RKSimon

Pull Request: #87786

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -14160,6 +14160,11 @@ bool BoUpSLP::collectValuesToDemote(
     unsigned BitWidth1 = OrigBitWidth - NumSignBits;
     if (!isKnownNonNegative(V, SimplifyQuery(*DL)))
       ++BitWidth1;
+    if (auto *I = dyn_cast<Instruction>(V)) {
+      APInt Mask = DB->getDemandedBits(I);
+      unsigned BitWidth2 = Mask.getBitWidth() - Mask.countl_zero();
+      BitWidth1 = std::min(BitWidth1, BitWidth2);
+    }
     BitWidth = std::max(BitWidth, BitWidth1);
     return BitWidth > 0 && OrigBitWidth >= (BitWidth * 2);
   };

llvm/test/Transforms/SLPVectorizer/AArch64/extractelements-to-shuffle.ll

@@ -81,8 +81,9 @@ define void @dist_vec(ptr nocapture noundef readonly %pA, ptr nocapture noundef
 ; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <2 x i64> [[TMP4FT_0_LCSSA]], <2 x i64> [[TMP4TF_0_LCSSA]], <2 x i32> <i32 1, i32 3>
 ; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <2 x i64> [[TMP4FF_0_LCSSA]], <2 x i64> [[TMP4TT_0_LCSSA]], <2 x i32> <i32 1, i32 3>
 ; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <2 x i64> [[TMP13]], <2 x i64> [[TMP14]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP16:%.*]] = add <4 x i64> [[TMP12]], [[TMP15]]
-; CHECK-NEXT:    [[TMP17:%.*]] = trunc <4 x i64> [[TMP16]] to <4 x i32>
+; CHECK-NEXT:    [[TMP16:%.*]] = trunc <4 x i64> [[TMP12]] to <4 x i32>
+; CHECK-NEXT:    [[TMP57:%.*]] = trunc <4 x i64> [[TMP15]] to <4 x i32>
+; CHECK-NEXT:    [[TMP17:%.*]] = add <4 x i32> [[TMP16]], [[TMP57]]
 ; CHECK-NEXT:    [[AND:%.*]] = and i32 [[NUMBEROFBOOLS]], 127
 ; CHECK-NEXT:    [[CMP86284:%.*]] = icmp ugt i32 [[AND]], 31
 ; CHECK-NEXT:    br i1 [[CMP86284]], label [[WHILE_BODY88:%.*]], label [[WHILE_END122:%.*]]

llvm/test/Transforms/SLPVectorizer/RISCV/trunc-to-large-than-bw.ll

@@ -8,10 +8,11 @@ define i32 @test() {
 ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call <4 x i64> @llvm.experimental.vp.strided.load.v4i64.p0.i64(ptr align 8 @c, i64 24, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, i32 4)
-; CHECK-NEXT:    [[TMP1:%.*]] = trunc <4 x i64> [[TMP0]] to <4 x i32>
-; CHECK-NEXT:    [[TMP2:%.*]] = and <4 x i32> [[TMP1]], <i32 65535, i32 65535, i32 65535, i32 65535>
-; CHECK-NEXT:    [[TMP3:%.*]] = xor <4 x i32> [[TMP2]], <i32 65535, i32 65535, i32 65535, i32 65535>
-; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[TMP3]])
+; CHECK-NEXT:    [[TMP1:%.*]] = trunc <4 x i64> [[TMP0]] to <4 x i16>
+; CHECK-NEXT:    [[TMP2:%.*]] = and <4 x i16> [[TMP1]], <i16 -1, i16 -1, i16 -1, i16 -1>
+; CHECK-NEXT:    [[TMP3:%.*]] = xor <4 x i16> [[TMP2]], <i16 -1, i16 -1, i16 -1, i16 -1>
+; CHECK-NEXT:    [[TMP4:%.*]] = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> [[TMP3]])
+; CHECK-NEXT:    [[TMP5:%.*]] = zext i16 [[TMP4]] to i32
 ; CHECK-NEXT:    [[TMP6:%.*]] = call i32 @llvm.umax.i32(i32 [[TMP5]], i32 1)
 ; CHECK-NEXT:    ret i32 [[TMP6]]
 ;

llvm/test/Transforms/SLPVectorizer/X86/int-bitcast-minbitwidth.ll

@@ -7,9 +7,10 @@ define void @t(i64 %v) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i64> poison, i64 [[V]], i32 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i64> [[TMP0]], <4 x i64> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = trunc <4 x i64> [[TMP1]] to <4 x i32>
-; CHECK-NEXT:    [[TMP3:%.*]] = mul <4 x i32> [[TMP2]], <i32 5, i32 6, i32 3, i32 2>
-; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> [[TMP3]])
+; CHECK-NEXT:    [[TMP2:%.*]] = trunc <4 x i64> [[TMP1]] to <4 x i16>
+; CHECK-NEXT:    [[TMP3:%.*]] = mul <4 x i16> [[TMP2]], <i16 5, i16 6, i16 3, i16 2>
+; CHECK-NEXT:    [[TMP4:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP3]])
+; CHECK-NEXT:    [[TMP5:%.*]] = sext i16 [[TMP4]] to i32
 ; CHECK-NEXT:    [[TMP6:%.*]] = and i32 [[TMP5]], 65535
 ; CHECK-NEXT:    store i32 [[TMP6]], ptr null, align 4
 ; CHECK-NEXT:    ret void