[llvm] [InstCombine] Remove some of the complexity-based canonicalization (PR #91185)
Nikita Popov via llvm-commits
llvm-commits at lists.llvm.org
Tue May 14 19:31:23 PDT 2024
================
@@ -9,96 +9,47 @@
define i64 @sum_2_at_with_int_conversion(ptr %A, ptr %B, i64 %N) {
; CHECK-LABEL: @sum_2_at_with_int_conversion(
-; CHECK-NEXT: at_with_int_conversion.exit11.peel:
+; CHECK-NEXT: entry:
; CHECK-NEXT: [[START_I:%.*]] = load ptr, ptr [[A:%.*]], align 8
; CHECK-NEXT: [[GEP_END_I:%.*]] = getelementptr i8, ptr [[A]], i64 8
; CHECK-NEXT: [[END_I:%.*]] = load ptr, ptr [[GEP_END_I]], align 8
; CHECK-NEXT: [[START_INT_I:%.*]] = ptrtoint ptr [[START_I]] to i64
; CHECK-NEXT: [[END_INT_I:%.*]] = ptrtoint ptr [[END_I]] to i64
; CHECK-NEXT: [[SUB_I:%.*]] = sub i64 [[END_INT_I]], [[START_INT_I]]
+; CHECK-NEXT: [[START_I1:%.*]] = load ptr, ptr [[B:%.*]], align 8
+; CHECK-NEXT: [[GEP_END_I2:%.*]] = getelementptr i8, ptr [[B]], i64 8
+; CHECK-NEXT: [[END_I3:%.*]] = load ptr, ptr [[GEP_END_I2]], align 8
+; CHECK-NEXT: [[START_INT_I4:%.*]] = ptrtoint ptr [[START_I1]] to i64
+; CHECK-NEXT: [[END_INT_I5:%.*]] = ptrtoint ptr [[END_I3]] to i64
+; CHECK-NEXT: [[SUB_I6:%.*]] = sub i64 [[END_INT_I5]], [[START_INT_I4]]
; CHECK-NEXT: [[SMAX:%.*]] = tail call i64 @llvm.smax.i64(i64 [[N:%.*]], i64 0)
-; CHECK-NEXT: [[GEP_END_I2:%.*]] = getelementptr i8, ptr [[B:%.*]], i64 8
-; CHECK-NEXT: [[START_I1_PEEL:%.*]] = load ptr, ptr [[B]], align 8
-; CHECK-NEXT: [[END_I3_PEEL:%.*]] = load ptr, ptr [[GEP_END_I2]], align 8
-; CHECK-NEXT: [[START_INT_I4_PEEL:%.*]] = ptrtoint ptr [[START_I1_PEEL]] to i64
-; CHECK-NEXT: [[END_INT_I5_PEEL:%.*]] = ptrtoint ptr [[END_I3_PEEL]] to i64
-; CHECK-NEXT: [[SUB_I6_PEEL:%.*]] = sub i64 [[END_INT_I5_PEEL]], [[START_INT_I4_PEEL]]
-; CHECK-NEXT: [[LV_I_PEEL:%.*]] = load i64, ptr [[START_I]], align 8
-; CHECK-NEXT: [[LV_I9_PEEL:%.*]] = load i64, ptr [[START_I1_PEEL]], align 8
-; CHECK-NEXT: [[SUM_NEXT_PEEL:%.*]] = add i64 [[LV_I_PEEL]], [[LV_I9_PEEL]]
-; CHECK-NEXT: [[EXITCOND_PEEL_NOT:%.*]] = icmp slt i64 [[N]], 1
-; CHECK-NEXT: br i1 [[EXITCOND_PEEL_NOT]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]]
-; CHECK: loop.preheader:
-; CHECK-NEXT: [[TMP0:%.*]] = add nsw i64 [[SMAX]], -1
-; CHECK-NEXT: [[UMIN:%.*]] = tail call i64 @llvm.umin.i64(i64 [[SUB_I6_PEEL]], i64 [[TMP0]])
-; CHECK-NEXT: [[TMP1:%.*]] = freeze i64 [[UMIN]]
-; CHECK-NEXT: [[UMIN15:%.*]] = tail call i64 @llvm.umin.i64(i64 [[TMP1]], i64 [[SUB_I]])
-; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[UMIN15]], 1
-; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 5
-; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[LOOP_PREHEADER20:%.*]], label [[VECTOR_PH:%.*]]
-; CHECK: vector.ph:
-; CHECK-NEXT: [[N_MOD_VF:%.*]] = and i64 [[TMP2]], 3
-; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
-; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i64 4, i64 [[N_MOD_VF]]
-; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP2]], [[TMP4]]
-; CHECK-NEXT: [[IND_END:%.*]] = add i64 [[N_VEC]], 1
-; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i64> <i64 poison, i64 0>, i64 [[SUM_NEXT_PEEL]], i64 0
-; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
-; CHECK: vector.body:
-; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <2 x i64> [ [[TMP5]], [[VECTOR_PH]] ], [ [[TMP12:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[VEC_PHI16:%.*]] = phi <2 x i64> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP13:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[OFFSET_IDX:%.*]] = or disjoint i64 [[INDEX]], 1
-; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i64, ptr [[START_I]], i64 [[OFFSET_IDX]]
-; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i8, ptr [[TMP6]], i64 16
-; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x i64>, ptr [[TMP6]], align 8
-; CHECK-NEXT: [[WIDE_LOAD17:%.*]] = load <2 x i64>, ptr [[TMP7]], align 8
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i64, ptr [[START_I1_PEEL]], i64 [[OFFSET_IDX]]
-; CHECK-NEXT: [[TMP9:%.*]] = getelementptr i8, ptr [[TMP8]], i64 16
-; CHECK-NEXT: [[WIDE_LOAD18:%.*]] = load <2 x i64>, ptr [[TMP8]], align 8
-; CHECK-NEXT: [[WIDE_LOAD19:%.*]] = load <2 x i64>, ptr [[TMP9]], align 8
-; CHECK-NEXT: [[TMP10:%.*]] = add <2 x i64> [[WIDE_LOAD]], [[VEC_PHI]]
-; CHECK-NEXT: [[TMP11:%.*]] = add <2 x i64> [[WIDE_LOAD17]], [[VEC_PHI16]]
-; CHECK-NEXT: [[TMP12]] = add <2 x i64> [[TMP10]], [[WIDE_LOAD18]]
-; CHECK-NEXT: [[TMP13]] = add <2 x i64> [[TMP11]], [[WIDE_LOAD19]]
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
-; CHECK: middle.block:
-; CHECK-NEXT: [[BIN_RDX:%.*]] = add <2 x i64> [[TMP13]], [[TMP12]]
-; CHECK-NEXT: [[TMP15:%.*]] = tail call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[BIN_RDX]])
-; CHECK-NEXT: br label [[LOOP_PREHEADER20]]
-; CHECK: loop.preheader20:
-; CHECK-NEXT: [[IV_PH:%.*]] = phi i64 [ 1, [[LOOP_PREHEADER]] ], [ [[IND_END]], [[MIDDLE_BLOCK]] ]
-; CHECK-NEXT: [[SUM_PH:%.*]] = phi i64 [ [[SUM_NEXT_PEEL]], [[LOOP_PREHEADER]] ], [ [[TMP15]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
-; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT11:%.*]] ], [ [[IV_PH]], [[LOOP_PREHEADER20]] ]
-; CHECK-NEXT: [[SUM:%.*]] = phi i64 [ [[SUM_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT11]] ], [ [[SUM_PH]], [[LOOP_PREHEADER20]] ]
-; CHECK-NEXT: [[INRANGE_I:%.*]] = icmp ult i64 [[SUB_I]], [[IV]]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT11:%.*]] ]
+; CHECK-NEXT: [[SUM:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[SUM_NEXT:%.*]], [[AT_WITH_INT_CONVERSION_EXIT11]] ]
+; CHECK-NEXT: [[INRANGE_I:%.*]] = icmp ugt i64 [[IV]], [[SUB_I]]
; CHECK-NEXT: br i1 [[INRANGE_I]], label [[ERROR_I:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT:%.*]]
; CHECK: error.i:
; CHECK-NEXT: tail call void @error()
; CHECK-NEXT: unreachable
; CHECK: at_with_int_conversion.exit:
-; CHECK-NEXT: [[INRANGE_I7:%.*]] = icmp ult i64 [[SUB_I6_PEEL]], [[IV]]
+; CHECK-NEXT: [[INRANGE_I7:%.*]] = icmp ugt i64 [[IV]], [[SUB_I6]]
; CHECK-NEXT: br i1 [[INRANGE_I7]], label [[ERROR_I10:%.*]], label [[AT_WITH_INT_CONVERSION_EXIT11]]
; CHECK: error.i10:
; CHECK-NEXT: tail call void @error()
; CHECK-NEXT: unreachable
; CHECK: at_with_int_conversion.exit11:
; CHECK-NEXT: [[GEP_IDX_I:%.*]] = getelementptr i64, ptr [[START_I]], i64 [[IV]]
; CHECK-NEXT: [[LV_I:%.*]] = load i64, ptr [[GEP_IDX_I]], align 8
-; CHECK-NEXT: [[GEP_IDX_I8:%.*]] = getelementptr i64, ptr [[START_I1_PEEL]], i64 [[IV]]
+; CHECK-NEXT: [[GEP_IDX_I8:%.*]] = getelementptr i64, ptr [[START_I1]], i64 [[IV]]
; CHECK-NEXT: [[LV_I9:%.*]] = load i64, ptr [[GEP_IDX_I8]], align 8
; CHECK-NEXT: [[ADD:%.*]] = add i64 [[LV_I]], [[SUM]]
; CHECK-NEXT: [[SUM_NEXT]] = add i64 [[ADD]], [[LV_I9]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV]], [[SMAX]]
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[EXIT:%.*]], label [[LOOP]]
; CHECK: exit:
-; CHECK-NEXT: [[SUM_NEXT_LCSSA:%.*]] = phi i64 [ [[SUM_NEXT_PEEL]], [[AT_WITH_INT_CONVERSION_EXIT11_PEEL:%.*]] ], [ [[SUM_NEXT]], [[AT_WITH_INT_CONVERSION_EXIT11]] ]
-; CHECK-NEXT: ret i64 [[SUM_NEXT_LCSSA]]
+; CHECK-NEXT: ret i64 [[SUM_NEXT]]
----------------
nikic wrote:
I've put up https://github.com/llvm/llvm-project/pull/92206 for the SCEV issue.
https://github.com/llvm/llvm-project/pull/91185
More information about the llvm-commits
mailing list