Roman Divacky
14551f041b
Lower FNEG just like FABS to fneg[ds] and fmov[ds], thus avoiding
...
expensive libcall. Also, Qp_neg is not implemented on at least
FreeBSD. This is also what gcc is doing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@202422 91177308-0d34-0410-b5e6-96231b3b80d8
2014-02-27 19:26:29 +00:00
Venkatraman Govindaraju
d0a796e5dd
[Sparc] Emit retl/ret instead of jmp instruction. It improves the readability of the assembly generated.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198910 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-10 02:55:27 +00:00
Venkatraman Govindaraju
fcd5e86396
[SparcV9] Handle i64 <-> float conversions in sparcv9 mode.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193957 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-03 12:28:40 +00:00
Venkatraman Govindaraju
5e45051e0e
[Sparc] Expand FP_TO_UINT, UINT_TO_FP for fp128.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193947 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-03 08:00:19 +00:00
Venkatraman Govindaraju
79c5e0c5ca
[Sparc] Do not emit nop after fcmp* instruction with V9.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192056 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-06 07:06:44 +00:00
Venkatraman Govindaraju
a8147756d6
[Sparc] Use correct alignment while loading/storing fp128 values.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192023 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-05 02:29:47 +00:00
Venkatraman Govindaraju
b648122c5f
[Sparc] Respect hasHardQuad parameter correctly when lowering SINT_TO_FP with fp128 operand.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192015 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-05 00:31:41 +00:00
Venkatraman Govindaraju
20b5879e0e
[Sparc] Fix lowering FABS on fp128 (long double) on pre-v9 targets.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191154 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-21 23:51:08 +00:00
Venkatraman Govindaraju
bf34f34642
[Sparc] Fix an assertion failure while lowering fcmp on long double.
...
This assertion is triggered because an integer constant is created with wrong
type.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189948 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-04 15:15:20 +00:00
Venkatraman Govindaraju
75ddb2bb34
[Sparc] Add support for soft long double (fp128).
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189780 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-03 04:11:59 +00:00
Venkatraman Govindaraju
6ee0857bd7
[Sparc] Implement spill and load for long double(f128) registers.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189768 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-02 18:32:45 +00:00
Venkatraman Govindaraju
2f17d0facf
[Sparc] Add long double (f128) instructions to sparc backend.
...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189198 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-25 18:30:06 +00:00
