8 Commits

Author SHA1 Message Date
Matt Arsenault
d706d030af AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.

Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
2017-03-21 21:39:51 +00:00
Mikael Holmen
828d0d9643 [LSR] Pointers with different address spaces are considered incompatible.
Summary:
Function isCompatibleIVType is already used as a guard before the call to

 SE.getMinusSCEV(OperExpr, PrevExpr);

in LSRInstance::ChainInstruction. getMinusSCEV requires the expressions
to be of the same type, so we now consider two pointers with different
address spaces to be incompatible, since it is possible that the pointers
in fact have different sizes.

Reviewers: qcolombet, eli.friedman

Reviewed By: qcolombet

Subscribers: nhaehnle, Ka-Ka, llvm-commits, mzolotukhin

Differential Revision: https://reviews.llvm.org/D29885

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295033 91177308-0d34-0410-b5e6-96231b3b80d8
2017-02-14 06:37:42 +00:00
Matt Arsenault
65d158cb3f LSR: Check atomic instruction pointer operands
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294410 91177308-0d34-0410-b5e6-96231b3b80d8
2017-02-08 06:44:58 +00:00
Matt Arsenault
fed7884d87 LSR: Don't drop address space when type doesn't match
For targets with different addressing modes in each address space,
if this is dropped querying isLegalAddressingMode later with this
will give a nonsense result, breaking the isLegalUse assertions.

This is a candidate for the 4.0 release branch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293542 91177308-0d34-0410-b5e6-96231b3b80d8
2017-01-30 19:50:17 +00:00
Matt Arsenault
6af03e5068 AMDGPU: Run pointer optimization passes
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@272736 91177308-0d34-0410-b5e6-96231b3b80d8
2016-06-15 00:11:01 +00:00
Matt Arsenault
c33f9cd287 AMDGPU: Fix a few slightly broken tests
Fix minor bugs and uses of undef which break when
pointer related optimization passes are run.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@269944 91177308-0d34-0410-b5e6-96231b3b80d8
2016-05-18 15:48:44 +00:00
Matt Arsenault
0638337d10 AMDGPU: Stop reporting an addressing mode for unknown addrspace
This was being treated the same as private, which has an immediate
offset. For unknown, it probably means it's for a computation not
actually being used for accessing memory, so it should not have a
nontrivial addressing mode.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@268002 91177308-0d34-0410-b5e6-96231b3b80d8
2016-04-29 06:25:10 +00:00
Matt Arsenault
4861e30522 LoopStrengthReduce: Try to pass address space to isLegalAddressingMode
This seems to only work some of the time. In some situations,
this seems to use a nonsensical type and isn't actually aware of the
memory being accessed. e.g. if branch condition is an icmp of a pointer,
it checks the addressing mode of i1.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245137 91177308-0d34-0410-b5e6-96231b3b80d8
2015-08-15 00:53:06 +00:00