LegalizeDAG.cpp uses the value of the comparison operands when checking
the legality of BR_CC, so DAGCombiner should do the same.
v2:
- Expand more BR_CC value types for NVPTX
v3:
- Expand correct BR_CC value types for Hexagon, Mips, and XCore.
llvm-svn: 176694
This is certainly not the last word on scheduling for this target, but
right now this allows a few apps to run / finish with radeonsi, most
notably UT2004 / Lightsmark. They fail to compile some shaders with the
default scheduler because it ends up trying to spill registers, which
we don't support yet (and which is probably a bad idea in general for
performance if it can be avoided).
NOTE: This is a candidate for the Mesa stable branch.
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176687
That can usually be lowered efficiently and is common in sandybridge code.
It would be nice to do this in DAGCombiner but we can't insert arbitrary
BUILD_VECTORs this late.
Fixes PR15462.
llvm-svn: 176634
v2: update CMakeLists.txt as well
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176626
v2: fix R600 regressions
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176624
Just encode the type as target specific attribute.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176622
- Phi nodes should be replaced/updated after lowering CMOV into branch
because 'mainMBB' updating operand in Phi node is changed.
- Add EFLAGS in livein before lowering the 2nd CMOV. It's necessary as
we will reuse the EFLAGS generated before the 1st lowered CMOV, which
won't clobber EFLAGS. However, we need explicitly specify that.
- '-attr=-cmov' test case are added.
llvm-svn: 176598
- Clear 'mayStore' flag when loading from the atomic variable before the
spin loop
- Clear kill flag from one use to multiple use in registers forming the
address to that atomic variable
- don't use a physical register as live-in register in BB (neither entry
nor landing pad.) by copying it into virtual register
(patch by Cameron Zwarich)
llvm-svn: 176538
This calling convention was added just to handle functions which return vector
of floats. The fix committed in r165585 solves the problem.
llvm-svn: 176530
This patch adds many more functions to the target library information.
All of the functions being added were discovered while doing the migration
of the simplify-libcalls attribute annotation functionality to the
functionattrs pass. As a part of that work the attribute annotation logic
will query TLI to determine if a function should be annotated or not.
Signed-off-by: Meador Inge <meadori@codesourcery.com>
llvm-svn: 176514
This is a skeleton for a pre-RA MachineInstr scheduler strategy. Currently
it only tries to expose more parallelism for ALU instructions (this also
makes the distribution of GPR channels more uniform and increases the
chances of ALU instructions to be packed together in a single VLIW group).
Also it tries to reduce clause switching by grouping instruction of the
same kind (ALU/FETCH/CF) together.
Vincent Lejeune:
- Support for VLIW4 Slot assignement
- Recomputation of ScheduleDAG to get more parallelism opportunities
Tom Stellard:
- Fix assertion failure when trying to determine an instruction's slot
based on its destination register's class
- Fix some compiler warnings
Vincent Lejeune: [v2]
- Remove recomputation of ScheduleDAG (will be provided in a later patch)
- Improve estimation of an ALU clause size so that heuristic does not emit cf
instructions at the wrong position.
- Make schedule heuristic smarter using SUnit Depth
- Take constant read limitations into account
Vincent Lejeune: [v3]
- Fix some uninitialized values in ConstPair
- Add asserts to ensure an ALU slot is always populated
llvm-svn: 176498
Maintaining CONST_COPY Instructions until Pre Emit may prevent some ifcvt case
and taking them in account for scheduling is difficult for no real benefit.
llvm-svn: 176488
Reviewed-by: Tom Stellard <thomas.stellard at amd.com>
mayLoad complexify scheduling and does not bring any usefull info
as the location is not writeable at all.
llvm-svn: 176486
one-byte NOPs. If the processor actually executes those NOPs, as it sometimes
does with aligned bundling, this can have a performance impact. From my
micro-benchmarks run on my one machine, a 15-byte NOP followed by twelve
one-byte NOPs is about 20% worse than a 15 followed by a 12. This patch
changes NOP emission to emit as many 15-byte (the maximum) as possible followed
by at most one shorter NOP.
llvm-svn: 176464
* Only apply divide bypass optimization when not optimizing for size.
* Fixed bug caused by constant for 0 value of type Int32,
used dividend type to generate the constant instead.
* For atom x86-64 apply the divide bypass to use 16-bit divides instead of
64-bit divides when operand values are small enough.
* Added lit tests for 64-bit divide bypass.
Patch by Tyler Nowicki!
llvm-svn: 176442
The VDUP instruction source register doesn't allow a non-constant lane
index, so make sure we don't construct a ARM::VDUPLANE node asking it to
do so.
rdar://13328063
http://llvm.org/bugs/show_bug.cgi?id=13963
llvm-svn: 176413
This matters for example in following matrix multiply:
int **mmult(int rows, int cols, int **m1, int **m2, int **m3) {
int i, j, k, val;
for (i=0; i<rows; i++) {
for (j=0; j<cols; j++) {
val = 0;
for (k=0; k<cols; k++) {
val += m1[i][k] * m2[k][j];
}
m3[i][j] = val;
}
}
return(m3);
}
Taken from the test-suite benchmark Shootout.
We estimate the cost of the multiply to be 2 while we generate 9 instructions
for it and end up being quite a bit slower than the scalar version (48% on my
machine).
Also, properly differentiate between avx1 and avx2. On avx-1 we still split the
vector into 2 128bits and handle the subvector muls like above with 9
instructions.
Only on avx-2 will we have a cost of 9 for v4i64.
I changed the test case in test/Transforms/LoopVectorize/X86/avx1.ll to use an
add instead of a mul because with a mul we now no longer vectorize. I did
verify that the mul would be indeed more expensive when vectorized with 3
kernels:
for (i ...)
r += a[i] * 3;
for (i ...)
m1[i] = m1[i] * 3; // This matches the test case in avx1.ll
and a matrix multiply.
In each case the vectorized version was considerably slower.
radar://13304919
llvm-svn: 176403
This patch eliminates the need to emit a constant move instruction when this
pattern is matched:
(select (setgt a, Constant), T, F)
The pattern above effectively turns into this:
(conditional-move (setlt a, Constant + 1), F, T)
llvm-svn: 176384
- ISD::SHL/SRL/SRA must have either both scalar or both vector operands
but TLI.getShiftAmountTy() so far only return scalar type. As a
result, backend logic assuming that breaks.
- Rename the original TLI.getShiftAmountTy() to
TLI.getScalarShiftAmountTy() and re-define TLI.getShiftAmountTy() to
return target-specificed scalar type or the same vector type as the
1st operand.
- Fix most TICG logic assuming TLI.getShiftAmountTy() a simple scalar
type.
llvm-svn: 176364
dispatch code. As far as I can tell the thumb2 code is behaving as expected.
I was able to compile and run the associated test case for both arm and thumb1.
rdar://13066352
llvm-svn: 176363
v2: based on Michels patch, but now allows copying of all registers sizes.
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
llvm-svn: 176346
This function will be used later when the capability to search delay slot
filling instructions in successor blocks is added. No intended functionality
changes.
llvm-svn: 176325
The work done by the post-encoder (setting architecturally unused bits to 0 as
required) can be done by the existing operand that covers the "#0.0". This
removes at least one use of the discouraged PostEncoderMethod uses.
llvm-svn: 176261
If an otherwise weak var is actually defined in this unit, it can't be
undefined at runtime so we can use normal global variable sequences (ADRP/ADD)
to access it.
llvm-svn: 176259
This fixes an issue where trying to assemlbe valid ADR instructions would cause
LLVM to hit a failed assertion.
Patch by Keith Walker.
llvm-svn: 176189
There's no need to generate a stack frame for PPC32 SVR4 when there are
no local variables assigned to the stack, i.e., when no red zone is needed.
(PPC64 supports a red zone, but PPC32 does not.)
llvm-svn: 176124
Make it possible to map between e32 and e64 encoding opcodes.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176104
Include immediate folding and SGPR limit handling for VOP3 instructions.
v2: remove leftover hasExtraSrcRegAllocReq
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176101
v2: document why we hardcode VCC for now.
This is a candidate for the mesa-stable branch.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176099
Prevent producing real strange tablegen code by using
proper register sizes, alignments and hierarchy.
Also cleanup the unused definitions and add some comments.
v2: add SGPR 512 bit registers, stop registers from wrapping around,
fix SGPR alignment
This is a candidate for the mesa-stable branch.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176098
This is a candidate for the mesa-stable branch.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 176097
fewer scalar integer (i32 or i64) arguments. It completely eliminates the need
for SDISel for trivial functions.
Also, add the new llc -fast-isel-abort-args option, which is similar to
-fast-isel-abort option, but for formal argument lowering.
llvm-svn: 176052
This removes a const_cast hack from PPCRegisterInfo::hasReservedSpillSlot().
The proper place to save the frame index for the CR spill slot is in the
PPCFunctionInfo object, not the PPCRegisterInfo object.
No new test cases, as this just reimplements existing function. Existing
tests such as test/CodeGen/PowerPC/crsave.ll are sufficient.
llvm-svn: 175998
16 more little piglits with radeonsi.
NOTE: This is a candidate for the Mesa stable branch.
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 175887
24 more little piglits with radeonsi.
NOTE: This is a candidate for the Mesa stable branch.
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 175886
9 more little piglits with radeonsi.
NOTE: This is a candidate for the Mesa stable branch.
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 175885
There's no apparent reason this code was copied from generated source
into a .cpp. It sets a bad example for those working on other targets
and trying to understand the register info API.
llvm-svn: 175849
to TargetFrameLowering, where it belongs. Incidentally, this allows us
to delete some duplicated (and slightly different!) code in TRI.
There are potentially other layering problems that can be cleaned up
as a result, or in a similar manner.
The refactoring was OK'd by Anton Korobeynikov on llvmdev.
Note: this touches the target interfaces, so out-of-tree targets may
be affected.
llvm-svn: 175788
Large code model is identical to medium code model except that the
addis/addi sequence for "local" accesses is never used. All accesses
use the addis/ld sequence.
The coding changes are straightforward; most of the patch is taken up
with creating variants of the medium model tests for large model.
llvm-svn: 175767
exists solely to enable it to call itself for i8 with some registers.
The proposed patch simplifies the function somewhat to make the High
bit only meaningful for the i8 mode, which makes sense. No functional
difference (getX86SubSuperRegister is not getting called from anywhere
outside with i64 and High=true).
llvm-svn: 175762
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175758
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175757
It actually fixes quite a bunch of piglit tests.
This is a candidate for the mesa-stable branch.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175756
Instead of using custom inserters, it's simpler and
should make DAG folding easier.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175755
v2: put implicit parameters in []
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175754
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175753
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175752
Order the classes and add asm operands.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175751
Fixing asm operation names.
v2: fix name of the e64 encoding, also add asm operands
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175750
Fixing asm operation names.
v2: use ZERO constant, also add asm operands
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175749
Fixing asm operation names.
v2: use ZERO constant, also add asm operands
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175748
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175747
Those two files got mixed up.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
llvm-svn: 175746
Fixes for-loop.cl piglit test
Patch By: Vincent Lejeune
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
NOTE: This is a candidate for the Mesa stable branch.
llvm-svn: 175742
The constructs %hi() and %lo() represent the high and low 16
bits of the address.
Because the 16 bit offset field of an LW instruction is
interpreted as signed, if bit 15 of the low part is 1 then the
low part will act as a negative and 1 needs to be added to the
high part.
Contributer: Vladimir Medic
llvm-svn: 175707
This patch implements the PPCDAGToDAGISel::PostprocessISelDAG virtual
method to perform post-selection peephole optimizations on the DAG
representation.
One optimization is implemented here: folds to clean up complex
addressing expressions for thread-local storage and medium code
model. It will also be useful for large code model sequences when
those are added later. I originally thought about doing this on the
MI representation prior to register assignment, but it's difficult to
do effective global dead code elimination at that point. DCE is
trivial on the DAG representation.
A typical example of a candidate code sequence in assembly:
addis 3, 2, globalvar@toc@ha
addi 3, 3, globalvar@toc@l
lwz 5, 0(3)
When the final instruction is a load or store with an immediate offset
of zero, the offset from the add-immediate can replace the zero,
provided the relocation information is carried along:
addis 3, 2, globalvar@toc@ha
lwz 5, globalvar@toc@l(3)
Since the addi can in general have multiple uses, we need to only
delete the instruction when the last use is removed.
llvm-svn: 175697
excluding visibility bits.
Mips specific standalone assembler directive "set at".
This directive changes the general purpose register
that the assembler will use when given the symbolic
register name $at.
This does not include negative testing. That will come
in a future patch.
A side affect of this patch recognizes the different
GPR register names for temporaries between old abi
and new abi so a test case for that is included.
Contributer: Vladimir Medic
llvm-svn: 175686
This handles the cases where the 6-bit splat element is odd, converting
to a three-instruction sequence to add or subtract two splats. With this
fix, the XFAIL in test/CodeGen/PowerPC/vec_constants.ll is removed.
llvm-svn: 175663
Tom Stellard