[llvm] [VPlan] Handle VPWidenCastRecipe without underlying value in EVL transform (PR #120194)

Mel Chen via llvm-commits llvm-commits at lists.llvm.org
Mon Dec 16 23:52:58 PST 2024


================
@@ -1058,6 +1058,125 @@ loop:
 exit:
   ret void
 }
+
+define void @truncate_to_minimal_bitwidths_widen_cast_recipe(ptr noalias %dst, ptr noalias %src, i32 %mvx) {
+; IF-EVL-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
+; IF-EVL-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
+; IF-EVL-NEXT:  [[ENTRY:.*:]]
+; IF-EVL-NEXT:    [[CMP111:%.*]] = icmp sgt i32 [[MVX]], 0
+; IF-EVL-NEXT:    br i1 [[CMP111]], label %[[FOR_BODY13_PREHEADER:.*]], label %[[FOR_COND_CLEANUP12:.*]]
+; IF-EVL:       [[FOR_BODY13_PREHEADER]]:
+; IF-EVL-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
+; IF-EVL-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; IF-EVL:       [[VECTOR_PH]]:
+; IF-EVL-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 16
+; IF-EVL-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], 1
+; IF-EVL-NEXT:    [[N_RND_UP:%.*]] = add i64 [[WIDE_TRIP_COUNT]], [[TMP2]]
+; IF-EVL-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
+; IF-EVL-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
+; IF-EVL-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; IF-EVL-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 16
+; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[MVX]], i64 0
+; IF-EVL-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
+; IF-EVL-NEXT:    [[TMP5:%.*]] = trunc <vscale x 16 x i32> [[BROADCAST_SPLAT]] to <vscale x 16 x i16>
+; IF-EVL-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <vscale x 16 x ptr> poison, ptr [[DST]], i64 0
+; IF-EVL-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <vscale x 16 x ptr> [[BROADCAST_SPLATINSERT2]], <vscale x 16 x ptr> poison, <vscale x 16 x i32> zeroinitializer
+; IF-EVL-NEXT:    br label %[[VECTOR_BODY:.*]]
+; IF-EVL:       [[VECTOR_BODY]]:
+; IF-EVL-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[EVL_BASED_IV:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; IF-EVL-NEXT:    [[AVL:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 16, i1 true)
+; IF-EVL-NEXT:    [[TMP7:%.*]] = add i64 [[EVL_BASED_IV]], 0
+; IF-EVL-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP7]]
+; IF-EVL-NEXT:    [[TMP9:%.*]] = getelementptr i8, ptr [[TMP8]], i32 0
+; IF-EVL-NEXT:    [[VP_OP_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr align 1 [[TMP9]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP10:%.*]] = call <vscale x 16 x i16> @llvm.vp.zext.nxv16i16.nxv16i8(<vscale x 16 x i8> [[VP_OP_LOAD]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[VP_OP:%.*]] = call <vscale x 16 x i16> @llvm.vp.mul.nxv16i16(<vscale x 16 x i16> [[TMP5]], <vscale x 16 x i16> [[TMP10]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[VP_OP1:%.*]] = call <vscale x 16 x i16> @llvm.vp.lshr.nxv16i16(<vscale x 16 x i16> [[VP_OP]], <vscale x 16 x i16> trunc (<vscale x 16 x i32> splat (i32 1) to <vscale x 16 x i16>), <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP11:%.*]] = call <vscale x 16 x i8> @llvm.vp.trunc.nxv16i8.nxv16i16(<vscale x 16 x i16> [[VP_OP1]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP11]], <vscale x 16 x ptr> align 1 [[BROADCAST_SPLAT3]], <vscale x 16 x i1> splat (i1 true), i32 [[TMP6]])
+; IF-EVL-NEXT:    [[TMP12:%.*]] = zext i32 [[TMP6]] to i64
+; IF-EVL-NEXT:    [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
+; IF-EVL-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; IF-EVL-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; IF-EVL-NEXT:    br i1 [[TMP13]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP47:![0-9]+]]
+; IF-EVL:       [[MIDDLE_BLOCK]]:
+; IF-EVL-NEXT:    br i1 true, label %[[FOR_COND_CLEANUP12_LOOPEXIT:.*]], label %[[SCALAR_PH]]
+; IF-EVL:       [[SCALAR_PH]]:
+; IF-EVL-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[FOR_BODY13_PREHEADER]] ]
+; IF-EVL-NEXT:    br label %[[FOR_BODY13:.*]]
+; IF-EVL:       [[FOR_COND_CLEANUP12_LOOPEXIT]]:
+; IF-EVL-NEXT:    br label %[[FOR_COND_CLEANUP12]]
+; IF-EVL:       [[FOR_COND_CLEANUP12]]:
+; IF-EVL-NEXT:    ret void
+; IF-EVL:       [[FOR_BODY13]]:
+; IF-EVL-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
+; IF-EVL-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
+; IF-EVL-NEXT:    [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX15]], align 1
+; IF-EVL-NEXT:    [[CONV:%.*]] = zext i8 [[TMP14]] to i32
+; IF-EVL-NEXT:    [[MUL16:%.*]] = mul i32 [[MVX]], [[CONV]]
+; IF-EVL-NEXT:    [[SHR35:%.*]] = lshr i32 [[MUL16]], 1
+; IF-EVL-NEXT:    [[CONV36:%.*]] = trunc i32 [[SHR35]] to i8
+; IF-EVL-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
+; IF-EVL-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; IF-EVL-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; IF-EVL-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]], !llvm.loop [[LOOP48:![0-9]+]]
+;
+; NO-VP-LABEL: define void @truncate_to_minimal_bitwidths_widen_cast_recipe(
+; NO-VP-SAME: ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[MVX:%.*]]) #[[ATTR0]] {
+; NO-VP-NEXT:  [[ENTRY:.*:]]
+; NO-VP-NEXT:    [[CMP111:%.*]] = icmp sgt i32 [[MVX]], 0
+; NO-VP-NEXT:    br i1 [[CMP111]], label %[[FOR_BODY13_PREHEADER:.*]], label %[[FOR_COND_CLEANUP12:.*]]
+; NO-VP:       [[FOR_BODY13_PREHEADER]]:
+; NO-VP-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext nneg i32 [[MVX]] to i64
+; NO-VP-NEXT:    br label %[[FOR_BODY13:.*]]
+; NO-VP:       [[FOR_COND_CLEANUP12_LOOPEXIT:.*]]:
+; NO-VP-NEXT:    br label %[[FOR_COND_CLEANUP12]]
+; NO-VP:       [[FOR_COND_CLEANUP12]]:
+; NO-VP-NEXT:    ret void
+; NO-VP:       [[FOR_BODY13]]:
+; NO-VP-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[FOR_BODY13_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR_BODY13]] ]
+; NO-VP-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[INDVARS_IV]]
+; NO-VP-NEXT:    [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX15]], align 1
+; NO-VP-NEXT:    [[CONV:%.*]] = zext i8 [[TMP0]] to i32
+; NO-VP-NEXT:    [[MUL16:%.*]] = mul i32 [[MVX]], [[CONV]]
+; NO-VP-NEXT:    [[SHR35:%.*]] = lshr i32 [[MUL16]], 1
+; NO-VP-NEXT:    [[CONV36:%.*]] = trunc i32 [[SHR35]] to i8
+; NO-VP-NEXT:    store i8 [[CONV36]], ptr [[DST]], align 1
+; NO-VP-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; NO-VP-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; NO-VP-NEXT:    br i1 [[EXITCOND_NOT]], label %[[FOR_COND_CLEANUP12_LOOPEXIT]], label %[[FOR_BODY13]]
+;
+entry:
+  %cmp111 = icmp sgt i32 %mvx, 0
+  br i1 %cmp111, label %for.body13.preheader, label %for.cond.cleanup12
+
+for.body13.preheader:                             ; preds = %entry
+  %wide.trip.count = zext nneg i32 %mvx to i64
+  br label %for.body13
+
+for.cond.cleanup12.loopexit:                      ; preds = %for.body13
+  br label %for.cond.cleanup12
----------------
Mel-Chen wrote:

Clean up this bb if possible. 

https://github.com/llvm/llvm-project/pull/120194


More information about the llvm-commits mailing list