Kalle Raiskila 940e7965f1 Improve lowering of sext to i128 on SPU. ... The old algorithm inserted a 'rotqmbyi' instruction which was both redundant and wrong - it made shufb select bytes from the wrong end of the input quad. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@116701 91177308-0d34-0410-b5e6-96231b3b80d8		2010-10-18 09:34:19 +00:00
..
useful-harnesses
2009-01-01-BrCond.ll
2010-04-07-DbgValueOtherTargets.ll
and_ops.ll
arg_ret.ll	Zap some redundant 'ori $?, $?, 0' from SPU.	2010-10-01 09:20:01 +00:00
bigstack.ll	Have SPU handle halfvec stores aligned by 8 bytes.	2010-08-09 16:33:00 +00:00
bss.ll
call_indirect.ll
call.ll	Fix SPU BE to use all the available return registers.	2010-08-24 11:50:48 +00:00
crash.ll
ctpop.ll
dg.exp
dp_farith.ll
eqv.ll
extract_elt.ll
fcmp32.ll
fcmp64.ll
fdiv.ll
fneg-fabs.ll
i8ops.ll
i64ops.ll
icmp8.ll
icmp16.ll
icmp32.ll
icmp64.ll
immed16.ll
immed32.ll
immed64.ll
int2fp.ll
intrinsics_branch.ll
intrinsics_float.ll
intrinsics_logical.ll
jumptable.ll
loads.ll
mul_ops.ll
mul-with-overflow.ll
nand.ll
or_ops.ll
private.ll
rotate_ops.ll
select_bits.ll
sext128.ll	Improve lowering of sext to i128 on SPU.	2010-10-18 09:34:19 +00:00
shift_ops.ll
shuffles.ll	Fix CellSPU vector shuffles, again.	2010-09-08 11:53:38 +00:00
sp_farith.ll
stores.ll
storestruct.ll
struct_1.ll
sub_ops.ll
trunc.ll
v2f32.ll	Remove all traces of v2[i,f]32 on SPU.	2010-08-18 10:04:39 +00:00
v2i32.ll	Change SPU register re-interpretations from OR to COPY_TO_REGCLASS instruction.	2010-09-16 12:29:33 +00:00
vec_const.ll
vecinsert.ll