| commit | 437310b30fd57aa0afdc3188ce256eb5cb445b21 | |
| author | David Green <david.green@arm.com> | |
| Mon, 16 Sep 2019 13:02:41 +0000 (16 13:02 +0000) | ||
| committer | David Green <david.green@arm.com> | |
| Mon, 16 Sep 2019 13:02:41 +0000 (16 13:02 +0000) | ||
| tree | 6b7cdeb44c0e76eda52693578bff4f4d295f291f | treesnapshot (tar.gz zip) |
| parent | cba3b2c1c37a84400b7d96b00fd5dcaad611acd4 | commitdiff |
[ARM] Fold VCMP into VPT
MVE has VPT instructions, which perform the duties of both a VCMP and a VPST in
a single instruction, performing the compare and starting the VPT block in one.
This teaches the MVEVPTBlockPass to fold them, searching back through the
basicblock for a valid VCMP and creating the VPT from its operands.
There are some changes to the VPT instructions to accommodate this, altering
the order of the operands to match the VCMP better, and changing P0 register
defs to be VPR defs, as is used in other places.
Differential Revision: https://reviews.llvm.org/D66577
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@371982 91177308-0d34-0410-b5e6-96231b3b80d8
MVE has VPT instructions, which perform the duties of both a VCMP and a VPST in
a single instruction, performing the compare and starting the VPT block in one.
This teaches the MVEVPTBlockPass to fold them, searching back through the
basicblock for a valid VCMP and creating the VPT from its operands.
There are some changes to the VPT instructions to accommodate this, altering
the order of the operands to match the VCMP better, and changing P0 register
defs to be VPR defs, as is used in other places.
Differential Revision: https://reviews.llvm.org/D66577
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@371982 91177308-0d34-0410-b5e6-96231b3b80d8
20 files changed: