------------------------------------------------------------------------
r232957 | thomas.stellard | 2015-03-23 12:06:01 -0400 (Mon, 23 Mar 2015) | 5 lines
R600/SI: Fix crash in SIInstrInfo::areLoadsFromSameBasePtr()
This function assumed that SMRD instructions always have immediate
offsets, which is not always the case.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@236069 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r229226 | Matthew.Arsenault | 2015-02-13 21:55:56 -0500 (Fri, 13 Feb 2015) | 5 lines
R600/SI: Fix copies from SGPR to VCC
This shows up without optimizations when vcc is required
to be used.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@235623 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r229225 | Matthew.Arsenault | 2015-02-13 21:55:54 -0500 (Fri, 13 Feb 2015) | 4 lines
R600/SI: Add hack to copy from a VGPR to VCC
This hopefully should be fixed when VReg_1 is removed.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@235622 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r228037 | marek.olsak | 2015-02-03 16:53:01 -0500 (Tue, 03 Feb 2015) | 6 lines
R600/SI: Fix B64 VALU shifts on VI
SI only has standard versions. VI only has REV versions.
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@235318 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r227990 | marek.olsak | 2015-02-03 12:38:12 -0500 (Tue, 03 Feb 2015) | 14 lines
R600/SI: Don't generate non-existent LSHL, LSHR, ASHR B32 variants on VI
This can happen when a REV instruction is commuted.
The trick is not to define the _vi versions of instructions, which has these
consequences:
- code generation will always fail if a pseudo cannot be lowered
(very useful to catch bugs where an unsupported instruction somehow makes
it to the printer)
- ability to query if a pseudo can be lowered, which is done in commuteOpcode
to prevent REV from commuting to non-REV on VI
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@235317 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r226597 | thomas.stellard | 2015-01-20 14:33:04 -0500 (Tue, 20 Jan 2015) | 5 lines
R600/SI: Add subtarget feature to enable VGPR spilling for all shader types
This is disabled by default, but can be enabled with the subtarget
feature: 'vgpr-spilling'
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@226728 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r226586 | thomas.stellard | 2015-01-20 12:49:47 -0500 (Tue, 20 Jan 2015) | 6 lines
R600/SI: Use external symbols for scratch buffer
We were passing the scratch buffer address to the shaders via user sgprs,
but now we use external symbols and have the driver patch the shader
using reloc information.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@226725 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r226583 | thomas.stellard | 2015-01-20 12:49:41 -0500 (Tue, 20 Jan 2015) | 5 lines
R600/SI: Update SIInstrInfo:verifyInstruction() after r225662
Now that we have our own custom register operand types, we need
to handle them in the verifiier.
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@226722 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r226190 | marek.olsak | 2015-01-15 13:43:01 -0500 (Thu, 15 Jan 2015) | 2 lines
R600/SI: Use 64-bit encoding by default for opcodes that are VOP3-only on VI
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@226719 91177308-0d34-0410-b5e6-96231b3b80d8
------------------------------------------------------------------------
r226188 | marek.olsak | 2015-01-15 13:42:51 -0500 (Thu, 15 Jan 2015) | 7 lines
R600/SI: Don't shrink instructions whose e32 encoding doesn't exist
v2: modify hasVALU32BitEncoding instead
v3: - add pseudoToMCOpcode helper to AMDGPUInstInfo, which is used by both
hasVALU32BitEncoding and AMDGPUMCInstLower::lower
- report an error if a pseudo can't be lowered
------------------------------------------------------------------------
git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_36@226717 91177308-0d34-0410-b5e6-96231b3b80d8
The backend now assumes that all immediates are integers. This allows
us to simplify immediate handling code, becasue we no longer need to
handle fp and integer immediates differently.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225844 91177308-0d34-0410-b5e6-96231b3b80d8
There are some operands which can take either immediates or registers
and we were previously using different register class to distinguish
between operands that could take immediates and those that could not.
This patch switches to using RegisterOperands which should simplify the
backend by reducing the number of register classes and also make it
easier to implement the assembler.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225662 91177308-0d34-0410-b5e6-96231b3b80d8
Use VGPR_32 register class instead. These two register classes were
identical and having separate classes was causing
SIInstrInfo::isLegalOperands() to be overly conservative in some cases.
This change is necessary to prevent future paches from missing a folding
opportunity in fneg-fabs.ll.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225382 91177308-0d34-0410-b5e6-96231b3b80d8
The constant bus restrictions only apply to VALU instructions. This
enables SIFoldOperands to fold immediates into SALU instructions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224623 91177308-0d34-0410-b5e6-96231b3b80d8
This was checking if pseudo-operands like the source
modifiers were using the constant bus, which happens to work
because the values these all can be happen to be valid inline
immediates.
This fixes a later commit which starts checking the register class
of the operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224078 91177308-0d34-0410-b5e6-96231b3b80d8
There are 3 changes:
- Convert 32-bit S_LSHL/LSHR/ASHR to their V_*REV variants for VI
- Lower RSQ_CLAMP for VI
- Don't generate MIN/MAX_LEGACY on VI
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223604 91177308-0d34-0410-b5e6-96231b3b80d8
- Fix missing SALU format bits
- Remove unused isSALUInstr
- Add isVALU
- Switch isDS to use a bit like the others
- Move SIInstrInfo::is* functions to header
- Reorder so they are approximately sorted by type (SALU, VALU, memory)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@223038 91177308-0d34-0410-b5e6-96231b3b80d8
We need to use a s_mov_b32 rather than a copy, so that CSE will
eliminate redundant moves to the m0 register.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222584 91177308-0d34-0410-b5e6-96231b3b80d8
A register operand that has a common sub-class with its instruction's
defined register class is not always legal. For example,
SReg_32 and M0Reg both have a common sub-class, but we can't
use an SReg_32 in instructions that expect a M0Reg.
This prevents the llvm.SI.sendmsg.ll test from failing when the fold
operand pass is added.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222368 91177308-0d34-0410-b5e6-96231b3b80d8
This partially makes up for not having address spaces
used for alias analysis in some simple cases.
This is not yet enabled by default so shouldn't change anything yet.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222286 91177308-0d34-0410-b5e6-96231b3b80d8
This was resulting in use of a register after a kill.
For some reason this showed up as a problem in many tests
when moving the SIFixSGPRCopies pass closer to instruction
selection.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222175 91177308-0d34-0410-b5e6-96231b3b80d8
The generic code trying to use findCommutedOpIndices won't
understand that it needs to swap the modifier operands also,
so it should fail if they are set.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220064 91177308-0d34-0410-b5e6-96231b3b80d8
Added a FIXME coment instead, we need to handle the case where the
two DS instructions being compared have different numbers of operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219236 91177308-0d34-0410-b5e6-96231b3b80d8
Instead of moving the first SGPR that is different than the first,
legalize the operand that requires the fewest moves if one
SGPR is used for multiple operands.
This saves extra moves and is also required for some instructions
which require that the same operand be used for multiple operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218532 91177308-0d34-0410-b5e6-96231b3b80d8
Disable the SGPR usage restriction parts of the DAG legalizeOperands.
It now should only be doing immediate folding until it can be replaced
later. The real legalization work is now done by the other
SIInstrInfo::legalizeOperands
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218531 91177308-0d34-0410-b5e6-96231b3b80d8
The base implementation of commuteInstruction is used
in some cases, but it turns out this has been broken for a
long time since modifiers were inserted between the real operands.
The base implementation of commuteInstruction also fails on immediates,
which also needs to be fixed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218530 91177308-0d34-0410-b5e6-96231b3b80d8
e.g. v_cndmask_b32 requires the condition operand be an SGPR.
If one of the source operands were an SGPR, that would be considered
the one SGPR use and the condition operand would be illegally moved.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218529 91177308-0d34-0410-b5e6-96231b3b80d8
Tom Stellard
Matt Arsenault
Marek Olsak