caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1e2c5481502b305d2e38ce94defffb43b82dbe3c
clang-p2996/llvm/test/Transforms/InstCombine/vec_phi_extract.ll
Sanjay Patel e71b81cab0 [InstCombine] canonicalize trunc + insert as bitcast + shuffle, part 1 (2nd try) 
The first attempt was reverted because a clang test changed
unexpectedly - the file is already marked with a FIXME, so
I just updated it this time to pass.

Original commit message:
This is the main patch for converting a truncated scalar that is
inserted into a vector to bitcast+shuffle. We could go either way
on patterns like this, but this direction will allow collapsing a
pair of these sequences on the motivating example from issue

The patch is split into 3 parts to make it easier to see the
progression of tests diffs. We allow inserting/shuffling into a
different size vector for flexibility, so there are several test
variations. The length-changing is handled by shortening/padding
the shuffle mask with undef elements.

In part 1, handle the basic pattern:
inselt undef, (trunc T), IndexC --> shuffle (bitcast T), IdentityMask

Proof for the endian-dependency behaving as expected:
https://alive2.llvm.org/ce/z/BsA7yC

The TODO items for handling shifts and insert into an arbitrary base
vector value are implemented as follow-ups.

Differential Revision: https://reviews.llvm.org/D138872
2022-11-30 14:52:20 -05:00

166 lines
7.1 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
define void @f(i64 %val, i32 %limit, ptr %ptr) {
; CHECK-LABEL: @f(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = trunc i64 [[VAL:%.*]] to i32
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP5:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[END:%.*]] = icmp ult i32 [[TMP1]], [[LIMIT:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[TMP1]], 10
; CHECK-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP3]]
; CHECK-NEXT: store i32 [[TMP2]], ptr [[TMP4]], align 4
; CHECK-NEXT: [[TMP5]] = add i32 [[TMP1]], 16
; CHECK-NEXT: br i1 [[END]], label [[LOOP]], label [[RET:%.*]]
; CHECK: ret:
; CHECK-NEXT: ret void
;
entry:
%tempvector = insertelement <16 x i64> undef, i64 %val, i32 0
%vector = shufflevector <16 x i64> %tempvector, <16 x i64> undef, <16 x i32> zeroinitializer
%0 = add <16 x i64> %vector, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
%1 = trunc <16 x i64> %0 to <16 x i32>
br label %loop
loop:
%2 = phi <16 x i32> [ %1, %entry ], [ %inc, %loop ]
%elt = extractelement <16 x i32> %2, i32 0
%end = icmp ult i32 %elt, %limit
%3 = add i32 10, %elt
%4 = sext i32 %elt to i64
%5 = getelementptr i32, ptr %ptr, i64 %4
store i32 %3, ptr %5
%inc = add <16 x i32> %2, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
br i1 %end, label %loop, label %ret
ret:
ret void
}
define void @copy(i64 %val, i32 %limit, ptr %ptr) {
; CHECK-LABEL: @copy(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = trunc i64 [[VAL:%.*]] to i32
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP5:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[END:%.*]] = icmp ult i32 [[TMP1]], [[LIMIT:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[TMP1]], 10
; CHECK-NEXT: [[TMP3:%.*]] = sext i32 [[TMP1]] to i64
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP3]]
; CHECK-NEXT: store i32 [[TMP2]], ptr [[TMP4]], align 4
; CHECK-NEXT: [[TMP5]] = add i32 [[TMP1]], 16
; CHECK-NEXT: br i1 [[END]], label [[LOOP]], label [[RET:%.*]]
; CHECK: ret:
; CHECK-NEXT: ret void
;
entry:
%tempvector = insertelement <16 x i64> undef, i64 %val, i32 0
%vector = shufflevector <16 x i64> %tempvector, <16 x i64> undef, <16 x i32> zeroinitializer
%0 = add <16 x i64> %vector, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
%1 = trunc <16 x i64> %0 to <16 x i32>
br label %loop
loop:
%2 = phi <16 x i32> [ %1, %entry ], [ %inc, %loop ]
%elt = extractelement <16 x i32> %2, i32 0
%eltcopy = extractelement <16 x i32> %2, i32 0
%end = icmp ult i32 %elt, %limit
%3 = add i32 10, %eltcopy
%4 = sext i32 %elt to i64
%5 = getelementptr i32, ptr %ptr, i64 %4
store i32 %3, ptr %5
%inc = add <16 x i32> %2, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
br i1 %end, label %loop, label %ret
ret:
ret void
}
define void @nocopy(i64 %val, i32 %limit, ptr %ptr) {
; CHECK-LABEL: @nocopy(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[VEC_VAL:%.*]] = bitcast i64 [[VAL:%.*]] to <2 x i32>
; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <2 x i32> [[VEC_VAL]], <2 x i32> poison, <16 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = add <16 x i32> [[TMP0]], <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[TMP2:%.*]] = phi <16 x i32> [ [[TMP1]], [[ENTRY:%.*]] ], [ [[INC:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[ELT:%.*]] = extractelement <16 x i32> [[TMP2]], i64 0
; CHECK-NEXT: [[ELTCOPY:%.*]] = extractelement <16 x i32> [[TMP2]], i64 1
; CHECK-NEXT: [[END:%.*]] = icmp ult i32 [[ELT]], [[LIMIT:%.*]]
; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[ELTCOPY]], 10
; CHECK-NEXT: [[TMP4:%.*]] = sext i32 [[ELT]] to i64
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr i32, ptr [[PTR:%.*]], i64 [[TMP4]]
; CHECK-NEXT: store i32 [[TMP3]], ptr [[TMP5]], align 4
; CHECK-NEXT: [[INC]] = add <16 x i32> [[TMP2]], <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
; CHECK-NEXT: br i1 [[END]], label [[LOOP]], label [[RET:%.*]]
; CHECK: ret:
; CHECK-NEXT: ret void
;
entry:
%tempvector = insertelement <16 x i64> undef, i64 %val, i32 0
%vector = shufflevector <16 x i64> %tempvector, <16 x i64> undef, <16 x i32> zeroinitializer
%0 = add <16 x i64> %vector, <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7, i64 8, i64 9, i64 10, i64 11, i64 12, i64 13, i64 14, i64 15>
%1 = trunc <16 x i64> %0 to <16 x i32>
br label %loop
loop:
%2 = phi <16 x i32> [ %1, %entry ], [ %inc, %loop ]
%elt = extractelement <16 x i32> %2, i32 0
%eltcopy = extractelement <16 x i32> %2, i32 1
%end = icmp ult i32 %elt, %limit
%3 = add i32 10, %eltcopy
%4 = sext i32 %elt to i64
%5 = getelementptr i32, ptr %ptr, i64 %4
store i32 %3, ptr %5
%inc = add <16 x i32> %2, <i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
br i1 %end, label %loop, label %ret
ret:
ret void
}
define i1 @g(<3 x i32> %input_2, i1 %c1) {
; CHECK-LABEL: @g(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <3 x i32> [[INPUT_2:%.*]], i64 0
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[TMP1:%.*]] = phi i32 [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP4:%.*]], [[FOR_BODY:%.*]] ]
; CHECK-NEXT: [[TMP2:%.*]] = phi i32 [ poison, [[ENTRY]] ], [ [[TMP3:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: br i1 [[C1:%.*]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP3]] = add i32 [[TMP2]], -1
; CHECK-NEXT: [[SUB44_ELT:%.*]] = sub i32 0, [[TMP2]]
; CHECK-NEXT: [[TMP4]] = sdiv i32 [[TMP1]], [[SUB44_ELT]]
; CHECK-NEXT: br label [[FOR_COND]]
; CHECK: for.end:
; CHECK-NEXT: [[TOBOOL313:%.*]] = icmp eq i32 [[TMP1]], 0
; CHECK-NEXT: ret i1 [[TOBOOL313]]
;
entry:
br label %for.cond
for.cond:
%input_2.addr.0 = phi <3 x i32> [ %input_2, %entry ], [ %div45, %for.body ]
%input_1.addr.1 = phi <3 x i32> [ poison, %entry ], [ %dec43, %for.body ]
br i1 %c1, label %for.end, label %for.body
for.body:
%dec43 = add <3 x i32> %input_1.addr.1, <i32 -1, i32 -1, i32 -1>
%sub44 = sub <3 x i32> <i32 -1, i32 -1, i32 -1>, %dec43
%div45 = sdiv <3 x i32> %input_2.addr.0, %sub44
br label %for.cond
for.end:
%0 = extractelement <3 x i32> %input_2.addr.0, i32 0
%.89 = select i1 false, i32 0, i32 %0
%tobool313 = icmp eq i32 %.89, 0
ret i1 %tobool313
}
Reference in New Issue View Git Blame Copy Permalink