forked from OSchip/llvm-project
Dorit Nuzman
parent
3dabfc6b0d
commit
bf2c15b5dc
|
|
@ -5734,7 +5734,15 @@ void InterleavedAccessInfo::collectConstStrideAccesses(
|
|||
continue;
|
||||
|
||||
Value *Ptr = getPointerOperand(&I);
|
||||
int64_t Stride = getPtrStride(PSE, Ptr, TheLoop, Strides);
|
||||
// We don't check wrapping here because we don't know yet if Ptr will be
|
||||
// part of a full group or a group with gaps. Checking wrapping for all
|
||||
// pointers (even those that end up in groups with no gaps) will be overly
|
||||
// conservative. For full groups, wrapping should be ok since if we would
|
||||
// wrap around the address space we would do a memory access at nullptr
|
||||
// even without the transformation. The wrapping checks are therefore
|
||||
// deferred until after we've formed the interleaved groups.
|
||||
int64_t Stride = getPtrStride(PSE, Ptr, TheLoop, Strides,
|
||||
/*Assume=*/true, /*ShouldCheckWrap=*/false);
|
||||
|
||||
const SCEV *Scev = replaceSymbolicStrideSCEV(PSE, Strides, Ptr);
|
||||
PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
|
||||
|
|
@ -5938,20 +5946,66 @@ void InterleavedAccessInfo::analyzeInterleaving(
|
|||
if (Group->getNumMembers() != Group->getFactor())
|
||||
releaseGroup(Group);
|
||||
|
||||
// If there is a non-reversed interleaved load group with gaps, we will need
|
||||
// to execute at least one scalar epilogue iteration. This will ensure that
|
||||
// we don't speculatively access memory out-of-bounds. Note that we only need
|
||||
// to look for a member at index factor - 1, since every group must have a
|
||||
// member at index zero.
|
||||
for (InterleaveGroup *Group : LoadGroups)
|
||||
if (!Group->getMember(Group->getFactor() - 1)) {
|
||||
if (Group->isReverse()) {
|
||||
// Remove interleaved groups with gaps (currently only loads) whose memory
|
||||
// accesses may wrap around. We have to revisit the getPtrStride analysis,
|
||||
// this time with ShouldCheckWrap=true, since collectConstStrideAccesses does
|
||||
// not check wrapping (see documentation there).
|
||||
// FORNOW we use Assume=false;
|
||||
// TODO: Change to Assume=true but making sure we don't exceed the threshold
|
||||
// of runtime SCEV assumptions checks (thereby potentially failing to
|
||||
// vectorize altogether).
|
||||
// Additional optional optimizations:
|
||||
// TODO: If we are peeling the loop and we know that the first pointer doesn't
|
||||
// wrap then we can deduce that all pointers in the group don't wrap.
|
||||
// This means that we can forcefully peel the loop in order to only have to
|
||||
// check the first pointer for no-wrap. When we'll change to use Assume=true
|
||||
// we'll only need at most one runtime check per interleaved group.
|
||||
//
|
||||
for (InterleaveGroup *Group : LoadGroups) {
|
||||
|
||||
// Case 1: A full group. Can Skip the checks; For full groups, if the wide
|
||||
// load would wrap around the address space we would do a memory access at
|
||||
// nullptr even without the transformation.
|
||||
if (Group->getNumMembers() == Group->getFactor())
|
||||
continue;
|
||||
|
||||
// Case 2: If first and last members of the group don't wrap this implies
|
||||
// that all the pointers in the group don't wrap.
|
||||
// So we check only group member 0 (which is always guaranteed to exist),
|
||||
// and group member Factor - 1; If the latter doesn't exist we rely on
|
||||
// peeling (if it is a non-reveresed accsess -- see Case 3).
|
||||
Value *FirstMemberPtr = getPointerOperand(Group->getMember(0));
|
||||
if (!getPtrStride(PSE, FirstMemberPtr, TheLoop, Strides, /*Assume=*/false,
|
||||
/*ShouldCheckWrap=*/true)) {
|
||||
DEBUG(dbgs() << "LV: Invalidate candidate interleaved group due to "
|
||||
"first group member potentially pointer-wrapping.\n");
|
||||
releaseGroup(Group);
|
||||
continue;
|
||||
}
|
||||
Instruction *LastMember = Group->getMember(Group->getFactor() - 1);
|
||||
if (LastMember) {
|
||||
Value *LastMemberPtr = getPointerOperand(LastMember);
|
||||
if (!getPtrStride(PSE, LastMemberPtr, TheLoop, Strides, /*Assume=*/false,
|
||||
/*ShouldCheckWrap=*/true)) {
|
||||
DEBUG(dbgs() << "LV: Invalidate candidate interleaved group due to "
|
||||
"last group member potentially pointer-wrapping.\n");
|
||||
releaseGroup(Group);
|
||||
} else {
|
||||
DEBUG(dbgs() << "LV: Interleaved group requires epilogue iteration.\n");
|
||||
RequiresScalarEpilogue = true;
|
||||
}
|
||||
}
|
||||
else {
|
||||
// Case 3: A non-reversed interleaved load group with gaps: We need
|
||||
// to execute at least one scalar epilogue iteration. This will ensure
|
||||
// we don't speculatively access memory out-of-bounds. We only need
|
||||
// to look for a member at index factor - 1, since every group must have
|
||||
// a member at index zero.
|
||||
if (Group->isReverse()) {
|
||||
releaseGroup(Group);
|
||||
continue;
|
||||
}
|
||||
DEBUG(dbgs() << "LV: Interleaved group requires epilogue iteration.\n");
|
||||
RequiresScalarEpilogue = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
LoopVectorizationCostModel::VectorizationFactor
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
; RUN: opt -loop-vectorize -mtriple=arm64-apple-ios -S -mcpu=cyclone < %s | FileCheck %s
|
||||
; RUN: opt -loop-vectorize -mtriple=arm64-apple-ios -S -mcpu=cyclone -enable-interleaved-mem-accesses=false < %s | FileCheck %s
|
||||
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n32:64-S128"
|
||||
|
||||
@kernel = global [512 x float] zeroinitializer, align 16
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
; RUN: opt -loop-vectorize -mtriple=thumbv7s-apple-ios6.0.0 -S < %s | FileCheck %s
|
||||
; RUN: opt -loop-vectorize -mtriple=thumbv7s-apple-ios6.0.0 -S -enable-interleaved-mem-accesses=false < %s | FileCheck %s
|
||||
|
||||
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
|
||||
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
; RUN: opt -loop-vectorize -mtriple=x86_64-apple-macosx -S -mcpu=corei7-avx < %s | FileCheck %s
|
||||
; RUN: opt -loop-vectorize -mtriple=x86_64-apple-macosx -S -mcpu=corei7-avx -enable-interleaved-mem-accesses=false < %s | FileCheck %s
|
||||
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
||||
|
||||
@kernel = global [512 x float] zeroinitializer, align 16
|
||||
|
|
|
|||
|
|
@ -0,0 +1,78 @@
|
|||
; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses=true < %s | FileCheck %s
|
||||
|
||||
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
||||
|
||||
; Check that the interleaved-mem-access analysis identifies the access
|
||||
; to array 'in' as interleaved, despite the possibly wrapping unsigned
|
||||
; 'out_ix' index.
|
||||
;
|
||||
; In this test the interleave-groups are full (have no gaps), so no wrapping
|
||||
; checks are necessary. We can call getPtrStride with Assume=false and
|
||||
; ShouldCheckWrap=false to safely figure out that the stride is 2.
|
||||
|
||||
; #include <stdlib.h>
|
||||
; class Complex {
|
||||
; private:
|
||||
; float real_;
|
||||
; float imaginary_;
|
||||
;
|
||||
;public:
|
||||
; Complex() : real_(0), imaginary_(0) { }
|
||||
; Complex(float real, float imaginary) : real_(real), imaginary_(imaginary) { }
|
||||
; Complex(const Complex &rhs) : real_(rhs.real()), imaginary_(rhs.imaginary()) { }
|
||||
;
|
||||
; inline float real() const { return real_; }
|
||||
; inline float imaginary() const { return imaginary_; }
|
||||
;};
|
||||
;
|
||||
;void test(Complex * __restrict__ out, Complex * __restrict__ in, size_t out_start, size_t size)
|
||||
;{
|
||||
; for (size_t out_offset = 0; out_offset < size; ++out_offset)
|
||||
; {
|
||||
; size_t out_ix = out_start + out_offset;
|
||||
; Complex t0 = in[out_ix];
|
||||
; out[out_ix] = t0;
|
||||
; }
|
||||
;}
|
||||
|
||||
; CHECK: vector.body:
|
||||
; CHECK: %wide.vec = load <8 x i32>, <8 x i32>* {{.*}}, align 4
|
||||
; CHECK: shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
||||
; CHECK: shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
||||
|
||||
%class.Complex = type { float, float }
|
||||
|
||||
define void @_Z4testP7ComplexS0_mm(%class.Complex* noalias nocapture %out, %class.Complex* noalias nocapture readonly %in, i64 %out_start, i64 %size) local_unnamed_addr {
|
||||
entry:
|
||||
%cmp9 = icmp eq i64 %size, 0
|
||||
br i1 %cmp9, label %for.cond.cleanup, label %for.body.preheader
|
||||
|
||||
for.body.preheader:
|
||||
br label %for.body
|
||||
|
||||
for.cond.cleanup.loopexit:
|
||||
br label %for.cond.cleanup
|
||||
|
||||
for.cond.cleanup:
|
||||
ret void
|
||||
|
||||
for.body:
|
||||
%out_offset.010 = phi i64 [ %inc, %for.body ], [ 0, %for.body.preheader ]
|
||||
%add = add i64 %out_offset.010, %out_start
|
||||
%arrayidx = getelementptr inbounds %class.Complex, %class.Complex* %in, i64 %add
|
||||
%0 = bitcast %class.Complex* %arrayidx to i32*
|
||||
%1 = load i32, i32* %0, align 4
|
||||
%imaginary_.i.i = getelementptr inbounds %class.Complex, %class.Complex* %in, i64 %add, i32 1
|
||||
%2 = bitcast float* %imaginary_.i.i to i32*
|
||||
%3 = load i32, i32* %2, align 4
|
||||
%arrayidx1 = getelementptr inbounds %class.Complex, %class.Complex* %out, i64 %add
|
||||
%4 = bitcast %class.Complex* %arrayidx1 to i64*
|
||||
%t0.sroa.4.0.insert.ext = zext i32 %3 to i64
|
||||
%t0.sroa.4.0.insert.shift = shl nuw i64 %t0.sroa.4.0.insert.ext, 32
|
||||
%t0.sroa.0.0.insert.ext = zext i32 %1 to i64
|
||||
%t0.sroa.0.0.insert.insert = or i64 %t0.sroa.4.0.insert.shift, %t0.sroa.0.0.insert.ext
|
||||
store i64 %t0.sroa.0.0.insert.insert, i64* %4, align 4
|
||||
%inc = add nuw i64 %out_offset.010, 1
|
||||
%exitcond = icmp eq i64 %inc, %size
|
||||
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
|
||||
}
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses=true < %s | FileCheck %s
|
||||
|
||||
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
||||
|
||||
; Check that the interleaved-mem-access analysis currently does not create an
|
||||
; interleave group for the access to array 'in' due to the possibly wrapping
|
||||
; unsigned 'out_ix' index.
|
||||
;
|
||||
; In this test the interleave-group of the loads is not full (has gaps), so
|
||||
; the wrapping checks are necessary. Here this cannot be done statically so
|
||||
; runtime checks are needed, but with Assume=false getPtrStride cannot add
|
||||
; runtime checks and as a result we can't create the interleave-group.
|
||||
;
|
||||
; FIXME: This is currently a missed optimization until we can use Assume=true
|
||||
; with proper threshold checks. Once we do that the candidate interleave-group
|
||||
; will not be invalidated by the wrapping checks.
|
||||
|
||||
; #include <stdlib.h>
|
||||
; void test(float * __restrict__ out, float * __restrict__ in, size_t size)
|
||||
; {
|
||||
; for (size_t out_offset = 0; out_offset < size; ++out_offset)
|
||||
; {
|
||||
; float t0 = in[2*out_offset];
|
||||
; out[out_offset] = t0;
|
||||
; }
|
||||
; }
|
||||
|
||||
; CHECK: vector.body:
|
||||
; CHECK-NOT: %wide.vec = load <8 x i32>, <8 x i32>* {{.*}}, align 4
|
||||
; CHECK-NOT: shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
||||
|
||||
define void @_Z4testPfS_m(float* noalias nocapture %out, float* noalias nocapture readonly %in, i64 %size) local_unnamed_addr {
|
||||
entry:
|
||||
%cmp7 = icmp eq i64 %size, 0
|
||||
br i1 %cmp7, label %for.cond.cleanup, label %for.body.preheader
|
||||
|
||||
for.body.preheader:
|
||||
br label %for.body
|
||||
|
||||
for.cond.cleanup.loopexit:
|
||||
br label %for.cond.cleanup
|
||||
|
||||
for.cond.cleanup:
|
||||
ret void
|
||||
|
||||
for.body:
|
||||
%out_offset.08 = phi i64 [ %inc, %for.body ], [ 0, %for.body.preheader ]
|
||||
%mul = shl i64 %out_offset.08, 1
|
||||
%arrayidx = getelementptr inbounds float, float* %in, i64 %mul
|
||||
%0 = bitcast float* %arrayidx to i32*
|
||||
%1 = load i32, i32* %0, align 4
|
||||
%arrayidx1 = getelementptr inbounds float, float* %out, i64 %out_offset.08
|
||||
%2 = bitcast float* %arrayidx1 to i32*
|
||||
store i32 %1, i32* %2, align 4
|
||||
%inc = add nuw i64 %out_offset.08, 1
|
||||
%exitcond = icmp eq i64 %inc, %size
|
||||
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
|
||||
}
|
||||
|
|
@ -0,0 +1,57 @@
|
|||
; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses=true < %s | FileCheck %s
|
||||
|
||||
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
||||
|
||||
; Check that the interleaved-mem-access analysis currently does not create an
|
||||
; interleave group for access 'a' due to the possible pointer wrap-around.
|
||||
;
|
||||
; To begin with, in this test the candidate interleave group can be created
|
||||
; only when getPtrStride is called with Assume=true. Next, because
|
||||
; the interleave-group of the loads is not full (has gaps), we also need to check
|
||||
; for possible pointer wrapping. Here we currently use Assume=false and as a
|
||||
; result cannot prove the transformation is safe and therefore invalidate the
|
||||
; candidate interleave group.
|
||||
;
|
||||
; FIXME: This is a missed optimization. Once we use Assume=true here, we will
|
||||
; not have to invalidate the group.
|
||||
|
||||
; void func(unsigned * __restrict a, unsigned * __restrict b, unsigned char x, unsigned char y) {
|
||||
; int i = 0;
|
||||
; for (unsigned char index = x; i < y; index +=2, ++i)
|
||||
; b[i] = a[index] * 2;
|
||||
;
|
||||
; }
|
||||
|
||||
; CHECK: vector.body:
|
||||
; CHECK-NOT: %wide.vec = load <8 x i32>, <8 x i32>* {{.*}}, align 4
|
||||
; CHECK-NOT: shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
||||
|
||||
define void @_Z4funcPjS_hh(i32* noalias nocapture readonly %a, i32* noalias nocapture %b, i8 zeroext %x, i8 zeroext %y) local_unnamed_addr {
|
||||
entry:
|
||||
%cmp9 = icmp eq i8 %y, 0
|
||||
br i1 %cmp9, label %for.cond.cleanup, label %for.body.preheader
|
||||
|
||||
for.body.preheader:
|
||||
%wide.trip.count = zext i8 %y to i64
|
||||
br label %for.body
|
||||
|
||||
for.cond.cleanup.loopexit:
|
||||
br label %for.cond.cleanup
|
||||
|
||||
for.cond.cleanup:
|
||||
ret void
|
||||
|
||||
for.body:
|
||||
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
|
||||
%index.011 = phi i8 [ %add, %for.body ], [ %x, %for.body.preheader ]
|
||||
%idxprom = zext i8 %index.011 to i64
|
||||
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
|
||||
%0 = load i32, i32* %arrayidx, align 4
|
||||
%mul = shl i32 %0, 1
|
||||
%arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
|
||||
store i32 %mul, i32* %arrayidx2, align 4
|
||||
%add = add i8 %index.011, 2
|
||||
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
||||
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
|
||||
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
|
||||
}
|
||||
Loading…
Reference in New Issue