mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-12-12 22:17:47 +00:00
cc03ee5234
This was reverted because of a miscompilation. At closer inspection, the problem was actually visible in a changed llvm regression test too. This one-line follow up fix/recommit will splat the IV, which is what we are trying to avoid if unnecessary in general, if tail-folding is requested even if all users are scalar instructions after vectorisation. Because with tail-folding, the splat IV will be used by the predicate of the masked loads/stores instructions. The previous version omitted this, which caused the miscompilation. The original commit message was: If tail-folding of the scalar remainder loop is applied, the primary induction variable is splat to a vector and used by the masked load/store vector instructions, thus the IV does not remain scalar. Because we now mark that the IV does not remain scalar for these cases, we don't emit the vector IV if it is not used. Thus, the vectoriser produces less dead code. Thanks to Ayal Zaks for the direction how to fix this.
51 lines
2.1 KiB
LLVM
51 lines
2.1 KiB
LLVM
; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s 2>&1 | FileCheck %s
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
@a = common local_unnamed_addr global i32 0, align 4
|
|
@b = common local_unnamed_addr global i8 0, align 1
|
|
|
|
; Function Attrs: norecurse nounwind uwtable
|
|
define void @doit1() local_unnamed_addr{
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%main.iv = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
|
|
|
%i8.iv = phi i8 [ 0, %entry ], [ %i8.add, %for.body ]
|
|
%i32.iv = phi i32 [ 0, %entry ], [ %i32.add, %for.body ]
|
|
|
|
%trunc.to.be.converted.to.new.iv = trunc i32 %i32.iv to i8
|
|
%i8.add = add i8 %i8.iv, %trunc.to.be.converted.to.new.iv
|
|
|
|
%noop.conv.under.pse = and i32 %i32.iv, 255
|
|
%i32.add = add nuw nsw i32 %noop.conv.under.pse, 9
|
|
|
|
%inc = add i32 %main.iv, 1
|
|
%tobool = icmp eq i32 %inc, 16
|
|
br i1 %tobool, label %for.cond.for.end_crit_edge, label %for.body
|
|
|
|
; CHECK-LABEL: @doit1(
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[MAIN_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[MAIN_IV_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
|
|
; CHECK-NEXT: [[I8_IV:%.*]] = phi <4 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[I8_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
|
|
; CHECK-NEXT: [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0
|
|
|
|
; CHECK-NEXT: [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]
|
|
|
|
; CHECK-NEXT: [[MAIN_IV_NEXT]] = add i32 [[MAIN_IV]], 4
|
|
; CHECK-NEXT: [[I32_IV_NEXT]] = add <4 x i32> [[I32_IV]], <i32 36, i32 36, i32 36, i32 36>
|
|
; CHECK-NEXT: [[IV_FROM_TRUNC_NEXT]] = add <4 x i8> [[IV_FROM_TRUNC]], <i8 36, i8 36, i8 36, i8 36>
|
|
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[MAIN_IV_NEXT]], 16
|
|
; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
|
|
|
|
for.cond.for.end_crit_edge:
|
|
store i8 %i8.add, i8* @b, align 1
|
|
br label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|