Skip to content

[GlobalISel] Add identity fold for fadd -0.0 #73296

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 25, 2023
Merged

[GlobalISel] Add identity fold for fadd -0.0 #73296

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 9 additions & 1 deletion llvm/include/llvm/Target/GlobalISel/Combine.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -473,6 +473,13 @@ def right_identity_zero: GICombineRule<
(apply (GIReplaceReg $dst, $lhs))
>;

def right_identity_neg_zero_fp: GICombineRule<
(defs root:$dst),
(match (G_FADD $dst, $x, $y):$root,
[{ return Helper.matchConstantFPOp(${y}, -0.0); }]),
(apply (GIReplaceReg $dst, $x))
>;

// Fold x op 1 -> x
def right_identity_one_int: GICombineRule<
(defs root:$dst),
Expand Down Expand Up @@ -1250,7 +1257,8 @@ def identity_combines : GICombineGroup<[select_same_val, right_identity_zero,
add_sub_reg, buildvector_identity_fold,
trunc_buildvector_fold,
trunc_lshr_buildvector_fold,
bitcast_bitcast_fold, fptrunc_fpext_fold]>;
bitcast_bitcast_fold, fptrunc_fpext_fold,
right_identity_neg_zero_fp]>;

def const_combines : GICombineGroup<[constant_fold_fp_ops, const_ptradd_to_i2p,
overlapping_and, mulo_by_2, mulo_by_0,
Expand Down
80 changes: 80 additions & 0 deletions llvm/test/CodeGen/AArch64/GlobalISel/combine-add.mir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,3 +127,83 @@ body: |
%3:_(<4 x s16>) = G_ADD %1, %2
$x0 = COPY %3
...
---
name: fadd_by_zero
tracksRegLiveness: true
body: |
bb.0:
liveins: $d0
; CHECK-LABEL: name: fadd_by_zero
; CHECK: liveins: $d0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $d0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 0.000000e+00
; CHECK-NEXT: [[FADD:%[0-9]+]]:_(s64) = G_FADD [[COPY]], [[C]]
; CHECK-NEXT: $d0 = COPY [[FADD]](s64)
%0:_(s64) = COPY $d0
%1:_(s64) = G_FCONSTANT double 0.000000e+00
%2:_(s64) = G_FADD %0, %1(s64)
$d0 = COPY %2(s64)
...
---
name: fadd_vector_by_zero
alignment: 4
tracksRegLiveness: true
frameInfo:
maxAlignment: 1
machineFunctionInfo: {}
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: fadd_vector_by_zero
; CHECK: liveins: $q0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 0.000000e+00
; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C]](s32), [[C]](s32), [[C]](s32), [[C]](s32)
; CHECK-NEXT: [[FADD:%[0-9]+]]:_(<4 x s32>) = G_FADD [[COPY]], [[BUILD_VECTOR]]
; CHECK-NEXT: $q0 = COPY [[FADD]](<4 x s32>)
%0:_(<4 x s32>) = COPY $q0
%1:_(s32) = G_FCONSTANT float 0.0
%2:_(<4 x s32>) = G_BUILD_VECTOR %1(s32), %1(s32), %1(s32), %1(s32)
%3:_(<4 x s32>) = G_FADD %0, %2(<4 x s32>)
$q0 = COPY %3(<4 x s32>)
...

---
name: fadd_by_neg_zero
tracksRegLiveness: true
body: |
bb.0:
liveins: $d0
; CHECK-LABEL: name: fadd_by_neg_zero
; CHECK: liveins: $d0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s64) = COPY $d0
; CHECK-NEXT: $d0 = COPY [[COPY]](s64)
%0:_(s64) = COPY $d0
%1:_(s64) = G_FCONSTANT double -0.000000e+00
%2:_(s64) = G_FADD %0, %1(s64)
$d0 = COPY %2(s64)
...
---
name: fadd_vector_by_neg_zero
alignment: 4
tracksRegLiveness: true
frameInfo:
maxAlignment: 1
machineFunctionInfo: {}
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: fadd_vector_by_neg_zero
; CHECK: liveins: $q0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK-NEXT: $q0 = COPY [[COPY]](<4 x s32>)
%0:_(<4 x s32>) = COPY $q0
%1:_(s32) = G_FCONSTANT float -0.0
%2:_(<4 x s32>) = G_BUILD_VECTOR %1(s32), %1(s32), %1(s32), %1(s32)
%3:_(<4 x s32>) = G_FADD %0, %2(<4 x s32>)
$q0 = COPY %3(<4 x s32>)
...