The two nested loops were confusing and also conservative in identifying
reduction variables. This patch replaces them by a worklist based approach.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181369 91177308-0d34-0410-b5e6-96231b3b80d8
We were passing an i32 to ConstantInt::get where an i64 was needed and we must
also pass the sign if we pass negatives numbers. The start index passed to
getConsecutiveVector must also be signed.
Should fix PR15882.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181286 91177308-0d34-0410-b5e6-96231b3b80d8
Add support for min/max reductions when "no-nans-float-math" is enabled. This
allows us to assume we have ordered floating point math and treat ordered and
unordered predicates equally.
radar://13723044
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181144 91177308-0d34-0410-b5e6-96231b3b80d8
We can just use the initial element that feeds the reduction.
max(max(x, y), z) == max(max(x,y), max(x,z))
radar://13723044
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181141 91177308-0d34-0410-b5e6-96231b3b80d8
By supporting the vectorization of PHINodes with more than two incoming values we can increase the complexity of nested if statements.
We can now vectorize this loop:
int foo(int *A, int *B, int n) {
for (int i=0; i < n; i++) {
int x = 9;
if (A[i] > B[i]) {
if (A[i] > 19) {
x = 3;
} else if (B[i] < 4 ) {
x = 4;
} else {
x = 5;
}
}
A[i] = x;
}
}
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181037 91177308-0d34-0410-b5e6-96231b3b80d8
This patch disables memory-instruction vectorization for types that need padding
bytes, e.g., x86_fp80 has 10 bytes store size with 6 bytes padding in darwin on
x86_64. Because the load/store vectorization is performed by the bit casting to
a packed vector, which has incompatible memory layout due to the lack of padding
bytes, the present vectorizer produces inconsistent result for memory
instructions of those types.
This patch checks an equality of the AllocSize of a scalar type and allocated
size for each vector element, to ensure that there is no padding bytes and the
array can be read/written using vector operations.
Patch by Daisuke Takahashi!
Fixes PR15758.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180196 91177308-0d34-0410-b5e6-96231b3b80d8
even if erroneously annotated with the parallel loop metadata.
Fixes Bug 15794:
"Loop Vectorizer: Crashes with the use of llvm.loop.parallel metadata"
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180081 91177308-0d34-0410-b5e6-96231b3b80d8
A min/max operation is represented by a select(cmp(lt/le/gt/ge, X, Y), X, Y)
sequence in LLVM. If we see such a sequence we can treat it just as any other
commutative binary instruction and reduce it.
This appears to help bzip2 by about 1.5% on an imac12,2.
radar://12960601
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179773 91177308-0d34-0410-b5e6-96231b3b80d8
Pass down the fact that an operand is going to be a vector of constants.
This should bring the performance of MultiSource/Benchmarks/PAQ8p/paq8p on x86
back. It had degraded to scalar performance due to my pervious shift cost change
that made all shifts expensive on x86.
radar://13576547
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178809 91177308-0d34-0410-b5e6-96231b3b80d8
We generate a select with a vectorized condition argument when the condition is
NOT loop invariant. Not the other way around.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177098 91177308-0d34-0410-b5e6-96231b3b80d8
We want vectorization to happen at -g. Ignore calls to the dbg.value intrinsic
and don't transfer them to the vectorized code.
radar://13378964
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176768 91177308-0d34-0410-b5e6-96231b3b80d8
This matters for example in following matrix multiply:
int **mmult(int rows, int cols, int **m1, int **m2, int **m3) {
int i, j, k, val;
for (i=0; i<rows; i++) {
for (j=0; j<cols; j++) {
val = 0;
for (k=0; k<cols; k++) {
val += m1[i][k] * m2[k][j];
}
m3[i][j] = val;
}
}
return(m3);
}
Taken from the test-suite benchmark Shootout.
We estimate the cost of the multiply to be 2 while we generate 9 instructions
for it and end up being quite a bit slower than the scalar version (48% on my
machine).
Also, properly differentiate between avx1 and avx2. On avx-1 we still split the
vector into 2 128bits and handle the subvector muls like above with 9
instructions.
Only on avx-2 will we have a cost of 9 for v4i64.
I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an
add instead of a mul because with a mul we now no longer vectorize. I did
verify that the mul would be indeed more expensive when vectorized with 3
kernels:
for (i ...)
r += a[i] * 3;
for (i ...)
m1[i] = m1[i] * 3; // This matches the test case in avx1.ll
and a matrix multiply.
In each case the vectorized version was considerably slower.
radar://13304919
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176403 91177308-0d34-0410-b5e6-96231b3b80d8
The LoopVectorizer often runs multiple times on the same function due to inlining.
When this happens the loop vectorizer often vectorizes the same loops multiple times, increasing code size and adding unneeded branches.
With this patch, the vectorizer during vectorization puts metadata on scalar loops and marks them as 'already vectorized' so that it knows to ignore them when it sees them a second time.
PR14448.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176399 91177308-0d34-0410-b5e6-96231b3b80d8
This properly asks TargetLibraryInfo if a call is available and if it is, it
can be translated into the corresponding LLVM builtin. We don't vectorize sqrt()
yet because I'm not sure about the semantics for negative numbers. The other
intrinsic should be exact equivalents to the libm functions.
Differential Revision: http://llvm-reviews.chandlerc.com/D465
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176188 91177308-0d34-0410-b5e6-96231b3b80d8
Storing the load/store instructions with the values
and inspect them using Alias Analysis to make sure
they don't alias, since the GEP pointer operand doesn't
take the offset into account.
Trying hard to not add any extra cost to loads and stores
that don't overlap on global values, AA is *only* calculated
if all of the previous attempts failed.
Using biggest vector register size as the stride for the
vectorization access, as we're being conservative and
the cost model (which calculates the real vectorization
factor) is only run after the legalization phase.
We might re-think this relationship in the future, but
for now, I'd rather be safe than sorry.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@175818 91177308-0d34-0410-b5e6-96231b3b80d8
In the loop vectorizer cost model, we used to ignore stores/loads of a pointer
type when computing the widest type within a loop. This meant that if we had
only stores/loads of pointers in a loop we would return a widest type of 8bits
(instead of 32 or 64 bit) and therefore a vector factor that was too big.
Now, if we see a consecutive store/load of pointers we use the size of a pointer
(from data layout).
This problem occured in SingleSource/Benchmarks/Shootout-C++/hash.cpp (reduced
test case is the first test in vector_ptr_load_store.ll).
radar://13139343
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174377 91177308-0d34-0410-b5e6-96231b3b80d8
Changing ARMBaseTargetMachine to return ARMTargetLowering intead of
the generic one (similar to x86 code).
Tests showing which instructions were added to cast when necessary
or cost zero when not. Downcast to 16 bits are not lowered in NEON,
so costs are not there yet.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@173849 91177308-0d34-0410-b5e6-96231b3b80d8
We ignore the cpu frontend and focus on pipeline utilization. We do this because we
don't have a good way to estimate the loop body size at the IR level.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172964 91177308-0d34-0410-b5e6-96231b3b80d8
This separates the check for "too few elements to run the vector loop" from the
"memory overlap" check, giving a lot nicer code and allowing to skip the memory
checks when we're not going to execute the vector code anyways. We still leave
the decision of whether to emit the memory checks as branches or setccs, but it
seems to be doing a good job. If ugly code pops up we may want to emit them as
separate blocks too. Small speedup on MultiSource/Benchmarks/MallocBench/espresso.
Most of this is legwork to allow multiple bypass blocks while updating PHIs,
dominators and loop info.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172902 91177308-0d34-0410-b5e6-96231b3b80d8
the target if it supports the different CAST types. We didn't do this
on X86 because of the different register sizes and types, but on ARM
this makes sense.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172245 91177308-0d34-0410-b5e6-96231b3b80d8
We don't have a detailed analysis on which values are vectorized and which stay scalars in the vectorized loop so we use
another method. We look at reduction variables, loads and stores, which are the only ways to get information in and out
of loop iterations. If the data types are extended and truncated then the cost model will catch the cost of the vector
zext/sext/trunc operations.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172178 91177308-0d34-0410-b5e6-96231b3b80d8
