6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-28 19:31:58 +00:00
Code Issues Projects Releases Wiki Activity
65457b679a
llvm-6502/test
History
Arnold Schwaighofer 65457b679a Costmodel: Add support for horizontal vector reductions 
Upcoming SLP vectorization improvements will want to be able to estimate costs
of horizontal reductions. Add infrastructure to support this.

We model reductions as a series of (shufflevector,add) tuples ultimately
followed by an extractelement. For example, for an add-reduction of <4 x float>
we could generate the following sequence:

 (v0, v1, v2, v3)
   \   \  /  /
     \  \  /
       +  +

 (v0+v2, v1+v3, undef, undef)
    \      /
 ((v0+v2) + (v1+v3), undef, undef)

 %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef,
                           <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
 %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf
 %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef,
                          <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
 %r = extractelement <4 x float> %bin.rdx8, i32 0

This commit adds a cost model interface "getReductionCost(Opcode, Ty, Pairwise)"
that will allow clients to ask for the cost of such a reduction (as backends
might generate more efficient code than the cost of the individual instructions
summed up). This interface is excercised by the CostModel analysis pass which
looks for reduction patterns like the one above - starting at extractelements -
and if it sees a matching sequence will call the cost model interface.

We will also support a second form of pairwise reduction that is well supported
on common architectures (haddps, vpadd, faddp).

 (v0, v1, v2, v3)
  \   /    \  /
 (v0+v1, v2+v3, undef, undef)
    \     /
 ((v0+v1)+(v2+v3), undef, undef, undef)

  %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef,
        <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef>
  %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef,
        <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
  %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
  %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef,
        <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
  %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef,
        <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
  %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
  %r = extractelement <4 x float> %bin.rdx.1, i32 0

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190876 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-17 18:06:50 +00:00
..
Analysis Costmodel: Add support for horizontal vector reductions 2013-09-17 18:06:50 +00:00
Assembler Remove verifier check that attribute 'builtin' is only applied to calls to 2013-09-07 00:25:48 +00:00
Bindings/Ocaml [PR11606] ocaml bindings tests produce binaries in source dir 2013-08-23 00:55:32 +00:00
Bitcode Patch provide by Tom Roeder! 2013-09-12 22:02:31 +00:00
BugPoint
CodeGen Implement 3 AArch64 neon instructions : umov smov ins. 2013-09-17 02:21:02 +00:00
DebugInfo mention command line parameters 2013-09-17 00:15:36 +00:00
ExecutionEngine Add "native" to config.available_features, to make it easier to disable non-x-compile-safe tests 2013-09-13 10:59:01 +00:00
Feature Implement function prefix data as an IR feature. 2013-09-16 01:08:15 +00:00
FileCheck
Instrumentation [msan] Check return value of main(). 2013-09-16 13:24:32 +00:00
Integer
JitListener Debug Info Testing: updated to use NULL instead of "i32 0" in a few fields. 2013-09-06 21:03:58 +00:00
Linker Implement function prefix data as an IR feature. 2013-09-16 01:08:15 +00:00
MC [ARM] Fix the deprecation of MCR encodings that map to CP15{ISB,DSB,DMB}. 2013-09-17 09:54:57 +00:00
Object Add a minimal implementation of ranlib. 2013-08-28 16:22:16 +00:00
Other Update to remove the no-frame-pointer-elim-non-leaf flag if it was set to 'false'. 2013-08-22 21:28:54 +00:00
TableGen FileCheckize some tests. 2013-08-22 20:46:05 +00:00
tools Generate IMAGE_REL_AMD64_ADDR32NB relocations for SEH 2013-09-15 17:46:46 +00:00
Transforms SLPVectorizer: Don't vectorize phi nodes that use invoke values 2013-09-17 17:03:29 +00:00
Unit
Verifier
YAMLParser Convert the uses of '|&' to use '2>&1 |' instead, which works on old 2012-07-02 18:37:59 +00:00
CMakeLists.txt
lit.cfg Add "native" to config.available_features, to make it easier to disable non-x-compile-safe tests 2013-09-13 10:59:01 +00:00
lit.site.cfg.in
Makefile
Makefile.tests
TestRunner.sh