[PowerPC] Add missing legalization for vector BSWAP

We somehow missed doing this when we were working on Power9 exploitation.
This just adds the missing legalization and cost for producing the vector
intrinsics.

Differential revision: https://reviews.llvm.org/D70436

1 files changed, 97 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/PowerPC/vectorize-bswap.ll b/llvm/test/Transforms/LoopVectorize/PowerPC/vectorize-bswap.ll
new file mode 100644
index 00000000000..d9e517805ea
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/PowerPC/vectorize-bswap.ll
@@ -0,0 +1,97 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -loop-vectorize -mtriple=powerpc64le-unknown-unknown \
+; RUN:   -force-target-max-vector-interleave=1 -mcpu=pwr9 < %s | FileCheck %s
+define dso_local void @test(i32* %Arr, i32 signext %Len) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp slt i32 0, [[LEN:%.*]]
+; CHECK-NEXT:    br i1 [[CMP1]], label [[FOR_BODY_LR_PH:%.*]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK:       for.body.lr.ph:
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[LEN]], 4
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[LEN]], 4
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[LEN]], [[N_MOD_VF]]
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> undef, i32 [[INDEX]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> undef, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = sext i32 [[TMP0]] to i64
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[ARR:%.*]], i64 [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4
+; CHECK-NEXT:    [[TMP5:%.*]] = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> [[WIDE_LOAD]])
+; CHECK-NEXT:    [[TMP6:%.*]] = sext i32 [[TMP0]] to i64
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[ARR]], i64 [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[TMP7]], i32 0
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[TMP5]], <4 x i32>* [[TMP9]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[LEN]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND_FOR_COND_CLEANUP_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_LR_PH]] ]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.for.cond.cleanup_crit_edge:
+; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    br label [[FOR_END:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_02:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; CHECK-NEXT:    [[IDXPROM:%.*]] = sext i32 [[I_02]] to i64
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[ARR]], i64 [[IDXPROM]]
+; CHECK-NEXT:    [[TMP11:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[TMP12:%.*]] = call i32 @llvm.bswap.i32(i32 [[TMP11]])
+; CHECK-NEXT:    [[IDXPROM1:%.*]] = sext i32 [[I_02]] to i64
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[ARR]], i64 [[IDXPROM1]]
+; CHECK-NEXT:    store i32 [[TMP12]], i32* [[ARRAYIDX2]], align 4
+; CHECK-NEXT:    br label [[FOR_INC]]
+; CHECK:       for.inc:
+; CHECK-NEXT:    [[INC]] = add nsw i32 [[I_02]], 1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[INC]], [[LEN]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_FOR_COND_CLEANUP_CRIT_EDGE]], !llvm.loop !2
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %cmp1 = icmp slt i32 0, %Len
+  br i1 %cmp1, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  br label %for.body
+
+for.cond.for.cond.cleanup_crit_edge:              ; preds = %for.inc
+  br label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond.for.cond.cleanup_crit_edge, %entry
+  br label %for.end
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.inc
+  %i.02 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %idxprom = sext i32 %i.02 to i64
+  %arrayidx = getelementptr inbounds i32, i32* %Arr, i64 %idxprom
+  %0 = load i32, i32* %arrayidx, align 4
+  %1 = call i32 @llvm.bswap.i32(i32 %0)
+  %idxprom1 = sext i32 %i.02 to i64
+  %arrayidx2 = getelementptr inbounds i32, i32* %Arr, i64 %idxprom1
+  store i32 %1, i32* %arrayidx2, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %inc = add nsw i32 %i.02, 1
+  %cmp = icmp slt i32 %inc, %Len
+  br i1 %cmp, label %for.body, label %for.cond.for.cond.cleanup_crit_edge
+
+for.end:                                          ; preds = %for.cond.cleanup
+  ret void
+}
+
+; Function Attrs: nounwind readnone speculatable willreturn
+declare i32 @llvm.bswap.i32(i32)