[CostModel][X86] Update RUN -passes=* to double quotes to appease update scripts on windows

[test] Migrate '-analyze -cost-model' to '-passes=print<cost-model>'

[CostModel] Treat 'widen subvector' patterns as zero cost

As discussed on D107228, widening a subvector by inserting the whole subvector into the bottom a larger undef vector should always be cheap

[CostModel] Treat 'widen subvector' patterns as zero cost

As discussed on D107228, widening a subvector by inserting the whole subvector into the bottom a larger undef vector should always be cheap enough that we can treat it as zero cost.

NOTE: If this proves to cause issues we have the option of introducing a "SK_WidenSubvector" shuffle kind enum that targets could override the zero cost, but that doesn't seem necessary atm.

Differential Revision: https://reviews.llvm.org/D107228

show more ...

[TTI] Add basic SK_InsertSubvector shuffle mask recognition

This patch adds an initial ShuffleVectorInst::isInsertSubvectorMask helper to recognize 2-op shuffles where the lowest elements of one of

[TTI] Add basic SK_InsertSubvector shuffle mask recognition

This patch adds an initial ShuffleVectorInst::isInsertSubvectorMask helper to recognize 2-op shuffles where the lowest elements of one of the sources are being inserted into the "in-place" other operand, this includes "concat_vectors" patterns as can be seen in the Arm shuffle cost changes. This also helped fix a x86 issue with irregular/length-changing SK_InsertSubvector costs - I'm hoping this will help with D107188

This doesn't currently attempt to work with 1-op shuffles that could either be a "widening" shuffle or a self-insertion.

The self-insertion case is tricky, but we currently always match this with the existing SK_PermuteSingleSrc logic.

The widening case will be addressed in a follow up patch that treats the cost as 0.

Masks with a high number of undef elts will still struggle to match optimal subvector widths - its currently bounded by minimum-width possible insertion, whilst some cases would benefit from wider (pow2?) subvectors.

Differential Revision: https://reviews.llvm.org/D107228

show more ...

[InstructionCost] Don't conflate Invalid costs with Unknown costs.

We previously made a change to getUserCost to return a Invalid cost
when one of the TTI costs returned '-1' (meaning 'unknown' or
'

[InstructionCost] Don't conflate Invalid costs with Unknown costs.

We previously made a change to getUserCost to return a Invalid cost
when one of the TTI costs returned '-1' (meaning 'unknown' or
'infinitely expensive'). It makes no sense to say that:

shufflevector <2 x i8> %x, <2 x i8> %y, <4 x i32> <i32 0, i32 1, i32 2, i32 3>

has an invalid cost. Perhaps the cost is not known, but the IR is valid
and can be code-generated. Invalid should only be used for IR that
cannot possibly be code-generated and where a cost is nonsensical.

With more passes now asserting that the cost must be valid, it is possible
that those assertions will fail for perfectly valid IR. An incomplete
cost-model probably shouldn't be a reason for the compiler to break.

It's better to consider these costs as 'very expensive' and ignore them
for other reasons. At some point, we should consider replacing -1 with
some other mechanism.

Reviewed By: paulwalker-arm, dmgreen

Differential Revision: https://reviews.llvm.org/D99502

show more ...

[CostModel][X86] Remove unused check-prefixes

[CostModel][X86] add CostModel for SK_Select(v8f64, v8i64, v16f32, v16i32, v32i16, v64i8)

add CostModel for SK_Select(v8f64, v8i64, v16f32, v16i32, v32i16, v64i8)

Reviewed By: RKSimon

Differential

[CostModel][X86] add CostModel for SK_Select(v8f64, v8i64, v16f32, v16i32, v32i16, v64i8)

add CostModel for SK_Select(v8f64, v8i64, v16f32, v16i32, v32i16, v64i8)

Reviewed By: RKSimon

Differential Revision: https://reviews.llvm.org/D87884

show more ...

[X86][CostModel] Bump the cost of vpermw/vpermt2b/vperm2w

vpermw is 2 uops. vpermt2b/vpermt2w are two shuffle uops and a port 015 uop. Weirdly vpermb is a single uop.

This patch bumps the cost to 2

[X86][CostModel] Bump the cost of vpermw/vpermt2b/vperm2w

vpermw is 2 uops. vpermt2b/vpermt2w are two shuffle uops and a port 015 uop. Weirdly vpermb is a single uop.

This patch bumps the cost to 2 for these operations. Maybe should go to 3 for the vpermt2*, but I've started conservative.

I've also removed a few entries that were now the same as earlier subtargets or that I didn't think we really did. Like I don't think we extend v32i8 to v32i16, shuffle, and then truncate.

Differential Revision: https://reviews.llvm.org/D79148

show more ...

[CostModel][X86] Add shuffle costs for some common sub-128bit vectors

v2i8/v4i8/v8i8 + v2i16/v4i16 all show up in vectorizer code and by just using the legalized types (v16i8/v8i16) we're highly exa

[CostModel][X86] Add shuffle costs for some common sub-128bit vectors

v2i8/v4i8/v8i8 + v2i16/v4i16 all show up in vectorizer code and by just using the legalized types (v16i8/v8i16) we're highly exaggerating the actual cost of the shuffle.

show more ...

[CostModel][X86] Add some insert subvector cost tests for vXf32/vXi32/vXi16/vXi8 types

[CostModel][X86] Improve extract/insert element costs (PR43605)

This tries to improve the accuracy of extract/insert element costs by accounting for subvector extraction/insertion for >128-bit vecto

[CostModel][X86] Improve extract/insert element costs (PR43605)

This tries to improve the accuracy of extract/insert element costs by accounting for subvector extraction/insertion for >128-bit vectors and the shuffling of elements to/from the 0'th index.

It also adds INSERTPS for f32 types and PINSR/PEXTR costs for integer types (at the moment we assume the same cost as MOVD/MOVQ - which isn't always true).

Differential Revision: https://reviews.llvm.org/D74976

show more ...

[CostModel][X86] Try to check against common prefixes before using target-specific cpu checks

SLM/GLM is still a mess so not all of them have been updated yet.

[CostModel][X86] Add some initial extract/insert subvector shuffle cost tests

Just f64/i64 tests initially to demonstrate PR39368

llvm-svn: 344857