caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
c6c7bfc4d2bc37f55f57504c19d47deb7645dd76
clang-p2996/llvm/test/CodeGen/Hexagon/autohvx
History
Krzysztof Parzyszek a6d4fc0e29 [Hexagon] Use shuffles when lowering "gather" shufflevectors 
Shufflevector instructions in LLVM IR that extract a subset of elements
of a longer input into a shorter vector can be done using VECTOR_SHUFFLEs.
This will avoid expanding them into constly extracts and inserts.

llvm-svn: 342091
2018-09-12 22:14:52 +00:00
..
align2-64b.ll
[Hexagon] Use vector align-left when shift amount fits in 3 bits
2018-05-30 13:45:34 +00:00
align2-128b.ll
[Hexagon] Use vector align-left when shift amount fits in 3 bits
2018-05-30 13:45:34 +00:00
align-64b.ll
[Hexagon] Use vector align-left when shift amount fits in 3 bits
2018-05-30 13:45:34 +00:00
align-128b.ll
[Hexagon] Use vector align-left when shift amount fits in 3 bits
2018-05-30 13:45:34 +00:00
arith.ll
[Hexagon] Use V6_vmpyih for halfword multiplication
2018-02-05 15:40:06 +00:00
bitcount-64b.ll
[Hexagon] Select HVX code for vector CTPOP, CTLZ, and CTTZ
2018-06-01 14:52:58 +00:00
bitcount-128b.ll
[Hexagon] Select HVX code for vector CTPOP, CTLZ, and CTTZ
2018-06-01 14:52:58 +00:00
bitwise-pred-64b.ll
[Hexagon] Add patterns for accumulating HVX compares
2018-05-22 18:27:02 +00:00
bitwise-pred-128b.ll
[Hexagon] Add patterns for accumulating HVX compares
2018-05-22 18:27:02 +00:00
bswap.ll
[Hexagon] Generate code for vector bswap intrinsics
2018-04-19 14:46:44 +00:00
build-vector-i32-type.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
concat-vectors-64b.ll
[Hexagon] Handle concat_vectors of all allowed HVX types
2017-12-15 21:23:12 +00:00
concat-vectors-128b.ll
[Hexagon] Handle concat_vectors of all allowed HVX types
2017-12-15 21:23:12 +00:00
contract-64b.ll
…
contract-128b.ll
…
ctpop-split.ll
[Hexagon] Split CTPOP of vector pairs
2018-06-06 18:03:29 +00:00
deal-64b.ll
…
deal-128b.ll
…
delta2-64b.ll
…
delta-64b.ll
…
delta-128b.ll
…
extract-element.ll
[Hexagon] Generate HVX code for vector construction and access
2017-12-06 16:40:37 +00:00
float-cost.ll
[Hexagon] Make floating point operations expensive for vectorization
2018-06-12 15:12:50 +00:00
interleave.ll
[Hexagon] Enable interleaving in loop vectorizer
2018-08-22 20:15:04 +00:00
isel-anyext-inreg.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-anyext-pair.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-bitcast-vsplat2.ll
[Hexagon] Improve HVX instruction selection (bitcast, vsplat)
2018-04-20 19:38:37 +00:00
isel-bitcast-vsplat.ll
[Hexagon] Improve HVX instruction selection (bitcast, vsplat)
2018-04-20 19:38:37 +00:00
isel-bool-vector.ll
[Hexagon] Run late copy propagation and dead code elimination passes
2018-01-24 17:48:11 +00:00
isel-build-undef.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-concat-multiple.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-concat-vectors-bool.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-concat-vectors.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-const-splat-bitcast.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-const-splat.ll
[Hexagon] Generate constant splats instead of loads from constant pool
2018-01-26 21:54:56 +00:00
isel-const-vector.ll
[Hexagon] Cast elements to correct type when creating constant vector
2018-01-11 18:03:23 +00:00
isel-expand-unaligned-loads-noindexed.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-expand-unaligned-loads.ll
[Hexagon] Add heuristic to exclude critical path cost for scheduling
2018-03-20 19:26:27 +00:00
isel-extractelt-illegal-type.ll
[Hexagon] Use legal types when lowering CONCAT_VECTORS via BUILD_VECTOR
2018-04-19 17:11:58 +00:00
isel-qfalse.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-select-const.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-setcc-pair.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-sext-inreg.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-shift-byte.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-shuffle-gather.ll
[Hexagon] Use shuffles when lowering "gather" shufflevectors
2018-09-12 22:14:52 +00:00
isel-shuffle-pack.ll
[Hexagon] Fix packing source vectors in shufflevector selection
2018-05-25 14:53:14 +00:00
isel-truncate.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-vec-ext.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
isel-vsplat-pair.ll
[Hexagon] Simplify CFG after atomic expansion
2018-08-02 22:17:53 +00:00
lower-insert-elt.ll
[Hexagon] Crash in instruction selection for insert_vector_elt for HVX
2017-12-11 14:46:06 +00:00
maximize-bandwidth.ll
[Hexagon] Implement TTI::shouldMaximizeVectorBandwidth
2018-03-27 18:10:47 +00:00
perfect-single.ll
…
reg-sequence.ll
[Hexagon] Return true in enableMultipleCopyHints().
2018-02-21 16:37:45 +00:00
shift-64b.ll
[Hexagon] Add patterns for vector shift-and-accumulate
2018-05-09 21:10:41 +00:00
shift-128b.ll
[Hexagon] Add patterns for vector shift-and-accumulate
2018-05-09 21:10:41 +00:00
shuff-64b.ll
…
shuff-128b.ll
…
shuff-combos-64b.ll
[Hexagon] Relax some checks in testcases, NFC
2017-12-12 21:44:04 +00:00
shuff-combos-128b.ll
[Hexagon] Relax some checks in testcases, NFC
2017-12-12 21:44:04 +00:00
shuff-single.ll
[Hexagon] Recognize vdealb, vdealh, vshuffb and vshuffh specifically
2017-12-06 22:41:49 +00:00
vdd0.ll
[Hexagon] Implement vector-pair zero as V6_vsubw_dv
2018-06-06 19:34:40 +00:00
vector-compare-64b.ll
[Hexagon] Add patterns for accumulating HVX compares
2018-05-22 18:27:02 +00:00
vector-compare-128b.ll
[Hexagon] Add patterns for accumulating HVX compares
2018-05-22 18:27:02 +00:00
vext-64b.ll
[Hexagon] Even simpler patterns for sign- and zero-extending HVX vectors
2018-01-05 22:31:11 +00:00
vext-128b.ll
[Hexagon] Even simpler patterns for sign- and zero-extending HVX vectors
2018-01-05 22:31:11 +00:00
vmux-order.ll
[Hexagon] Better detection of identity and undef masks in shuffles
2017-12-12 20:23:12 +00:00