We were still using the rounded down offset and alignment even though
they aren't handled because you can't trivially bitcast the loaded
value.
llvm-svn: 348658
This change attempts to shrink scalar AND, OR and XOR instructions which take an immediate that isn't inlineable.
It performs:
AND s0, s0, ~(1 << n) -> BITSET0 s0, n
OR s0, s0, (1 << n) -> BITSET1 s0, n
AND s0, s1, x -> ANDN2 s0, s1, ~x
OR s0, s1, x -> ORN2 s0, s1, ~x
XOR s0, s1, x -> XNOR s0, s1, ~x
In particular, this catches setting and clearing the sign bit for fabs (and x, 0x7ffffffff -> bitset0 x, 31 and or x, 0x80000000 -> bitset1 x, 31).
llvm-svn: 348601
Adds fatal errors for any target that does not support the Tiny or Kernel
codemodels by rejigging the getEffectiveCodeModel calls.
Differential Revision: https://reviews.llvm.org/D50141
llvm-svn: 348585
The introduction of S_{ADD|SUB}_U64_PSEUDO instructions which are decomposed
into VOP3 instruction pairs for S_ADD_U64_PSEUDO:
V_ADD_I32_e64
V_ADDC_U32_e64
and for S_SUB_U64_PSEUDO
V_SUB_I32_e64
V_SUBB_U32_e64
preclude the use of SDWA to encode a constant.
SDWA: Sub-Dword addressing is supported on VOP1 and VOP2 instructions,
but not on VOP3 instructions.
We desire to fold the bit-and operand into the instruction encoding
for the V_ADD_I32 instruction. This requires that we transform the
VOP3 into a VOP2 form of the instruction (_e32).
%19:vgpr_32 = V_AND_B32_e32 255,
killed %16:vgpr_32, implicit $exec
%47:vgpr_32, %49:sreg_64_xexec = V_ADD_I32_e64
%26.sub0:vreg_64, %19:vgpr_32, implicit $exec
%48:vgpr_32, dead %50:sreg_64_xexec = V_ADDC_U32_e64
%26.sub1:vreg_64, %54:vgpr_32, killed %49:sreg_64_xexec, implicit $exec
which then allows the SDWA encoding and becomes
%47:vgpr_32 = V_ADD_I32_sdwa
0, %26.sub0:vreg_64, 0, killed %16:vgpr_32, 0, 6, 0, 6, 0,
implicit-def $vcc, implicit $exec
%48:vgpr_32 = V_ADDC_U32_e32
0, %26.sub1:vreg_64, implicit-def $vcc, implicit $vcc, implicit $exec
Differential Revision: https://reviews.llvm.org/D54882
llvm-svn: 348132
The identity ~(x ^ y) == (~x ^ y) == (x ^ ~y) allows XNOR (XOR/NOT) to turn into NOT/XOR. Handling this case with its own split means we can make the NOT remain in the scalar unit. Previously, we split 64-bit XNOR into two 32-bit XNOR, then lowered. Now, we get three instructions (s_not, v_xor, v_xor) rather than four in the case where either of the sources is a scalar 64-bit.
Add test cases to xnor.ll to attempt XNOR Vx, Sy and XNOR Sx, Vy. Also adding test that uses the opposite identity such that (~x ^ y) on the scalar unit (or vector for gfx906) can generate XNOR. This already worked, but I didn't see a test for it.
Differential: https://reviews.llvm.org/D55071
llvm-svn: 348075
Summary:
Moving SMRD to VMEM in SIFixSGPRCopies is rather bad for performance if
the load is really uniform. So select the scalar load intrinsics directly
to either VMEM or SMRD buffer loads based on divergence analysis.
If an offset happens to end up in a VGPR -- either because a floating
point calculation was involved, or due to other remaining deficiencies
in SIFixSGPRCopies -- we use v_readfirstlane.
There is some unrelated churn in tests since we now select MUBUF offsets
in a unified way with non-scalar buffer loads.
Change-Id: I170e6816323beb1348677b358c9d380865cd1a19
Reviewers: arsenm, alex-t, rampitec, tpr
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D53283
llvm-svn: 348050
Summary:
The VirtReg2Value mapping is crucial for getting consistently
reliable divergence information into the SelectionDAG. This
patch fixes a bunch of issues that lead to incorrect divergence
info and introduces tight assertions to ensure we don't regress:
1. VirtReg2Value is generated lazily; there were some cases where
a lookup was performed before all relevant virtual registers were
created, leading to an out-of-sync mapping. Those cases were:
- Complex code to lower formal arguments that generated CopyFromReg
nodes from live-in registers (fixed by never querying the mapping
for live-in registers).
- Code that generates CopyToReg for formal arguments that are used
outside the entry basic block (fixed by never querying the
mapping for Register nodes, which don't need the divergence info
anyway).
2. For complex values that are lowered to a sequence of registers,
all registers must be reflected in the VirtReg2Value mapping.
I am not adding any new tests, since I'm not actually aware of any
bugs that these problems are causing with trunk as-is. However,
I recently added a test case (in r346423) which fails when D53283 is
applied without this change. Also, the new assertions should provide
most of the effective test coverage.
There is one test change in sdwa-peephole.ll. The underlying issue
is that since the divergence info is now correct, the DAGISel will
select V_OR_B32 directly instead of S_OR_B32. This leads to an extra
COPY which affects the behavior of MachineLICM in a way that ends up
with the S_MOV_B32 with the constant in a different basic block than
the V_OR_B32, which is presumably what defeats the peephole.
Reviewers: alex-t, arsenm, rampitec
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D54340
llvm-svn: 348049
Introduces DPP pseudo instructions and the pass that combines DPP mov with subsequent uses.
Differential revision: https://reviews.llvm.org/D53762
llvm-svn: 347993
Also revert fix r347876
One of the buildbots was reporting a failure in some relevant tests that I can't
repro or explain at present, so reverting until I can isolate.
llvm-svn: 347911
This patch adds support for S_ANDN2, S_ORN2 32-bit and 64-bit instructions and adds splits to move them to the vector unit (for which there is no equivalent instruction). It modifies the way that the more complex scalar instructions are lowered to vector instructions by first breaking them down to sequences of simpler scalar instructions which are then lowered through the existing code paths. The pattern for S_XNOR has also been updated to apply inversion to one input rather than the output of the XOR as the result is equivalent and may allow leaving the NOT instruction on the scalar unit.
A new tests for NAND, NOR, ANDN2 and ORN2 have been added, and existing tests now hit the new instructions (and have been modified accordingly).
Differential: https://reviews.llvm.org/D54714
llvm-svn: 347877
My change svn-id: 347871 caused a buildbot failure due to an unused
variable def (used in an assert).
Change-Id: Ia882d18bb6fa79b4d7bbfda422b9ea5d23eab336
llvm-svn: 347876
TFE and LWE support requires extra result registers that are written in the
event of a failure in order to detect that failure case.
The specific use-case that initiated these changes is sparse texture support.
This means that if image intrinsics are used with either option turned on, the
programmer must ensure that the return type can contain all of the expected
results. This can result in redundant registers since the vector size must be a
power-of-2.
This change takes roughly 6 parts:
1. Modify the instruction defs in tablegen to add new instruction variants that
can accomodate the extra return values.
2. Updates to lowerImage in SIISelLowering.cpp to accomodate setting TFE or LWE
(where the bulk of the work for these instruction types is now done)
3. Extra verification code to catch cases where intrinsics have been used but
insufficient return registers are used.
4. Modification to the adjustWritemask optimisation to account for TFE/LWE being
enabled (requires extra registers to be maintained for error return value).
5. An extra pass to zero initialize the error value return - this is because if
the error does not occur, the register is not written and thus must be zeroed
before use. Also added a new (on by default) option to ensure ALL return values
are zero-initialized that is required for sparse texture support.
6. Disable the inst_combine optimization in the presence of tfe/lwe (later TODO
for this to re-enable and handle correctly).
There's an additional fix now to avoid a dmask=0
For an image intrinsic with tfe where all result channels except tfe
were unused, I was getting an image instruction with dmask=0 and only a
single vgpr result for tfe. That is incorrect because the hardware
assumes there is at least one vgpr result, plus the one for tfe.
Fixed by forcing dmask to 1, which gives the desired two vgpr result
with tfe in the second one.
The TFE or LWE result is returned from the intrinsics using an aggregate
type. Look in the test code provided to see how this works, but in essence IR
code to invoke the intrinsic looks as follows:
%v = call {<4 x float>,i32} @llvm.amdgcn.image.load.1d.v4f32i32.i32(i32 15,
i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
%v.vec = extractvalue {<4 x float>, i32} %v, 0
%v.err = extractvalue {<4 x float>, i32} %v, 1
Differential revision: https://reviews.llvm.org/D48826
Change-Id: If222bc03642e76cf98059a6bef5d5bffeda38dda
llvm-svn: 347871
Summary:
MachineLoopInfo cannot be relied on for correctness, because it cannot
properly recognize loops in irreducible control flow which can be
introduced by late machine basic block optimization passes. See the new
test case for the reduced form of an example that occurred in practice.
Use a simple fixpoint iteration instead.
In order to facilitate this change, refactor WaitcntBrackets so that it
only tracks pending events and registers, rather than also maintaining
state that is relevant for the high-level algorithm. Various accessor
methods can be removed or made private as a consequence.
Affects (in radv):
- dEQP-VK.glsl.loops.special.{for,while}_uniform_iterations.select_iteration_count_{fragment,vertex}
Fixes: r345719 ("AMDGPU: Rewrite SILowerI1Copies to always stay on SALU")
Reviewers: msearles, rampitec, scott.linder, kanarayan
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits, hakzsam
Differential Revision: https://reviews.llvm.org/D54231
llvm-svn: 347853
Summary:
There is one obsolete reference to using -1 as an indication of "unknown",
but this isn't actually used anywhere.
Using unsigned makes robust wrapping checks easier.
Reviewers: msearles, rampitec, scott.linder, kanarayan
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, llvm-commits, tpr, t-tye, hakzsam
Differential Revision: https://reviews.llvm.org/D54230
llvm-svn: 347852
Summary:
Instead of storing the "score" (last time point) of the various relevant
events, only store whether an event is pending or not.
This is sufficient, because whenever only one event of a count type is
pending, its last time point is naturally the upper bound of all time
points of this count type, and when multiple event types are pending,
the count type has gone out of order and an s_waitcnt to 0 is required
to clear any pending event type (and will then clear all pending event
types for that count type).
This also removes the special handling of GDS_GPR_LOCK and EXP_GPR_LOCK.
I do not understand what this special handling ever attempted to achieve.
It has existed ever since the original port from an internal code base,
so my best guess is that it solved a problem related to EXEC handling in
that internal code base.
Reviewers: msearles, rampitec, scott.linder, kanarayan
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits, hakzsam
Differential Revision: https://reviews.llvm.org/D54228
llvm-svn: 347850
Summary:
It hides the type casting ugliness, and I happened to have to add a new
such loop (in a later patch).
Reviewers: msearles, rampitec, scott.linder, kanarayan
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits, hakzsam
Differential Revision: https://reviews.llvm.org/D54227
llvm-svn: 347849
Summary:
Reduce the statefulness of the algorithm in two ways:
1. More clearly split generateWaitcntInstBefore into two phases: the
first one which determines the required wait, if any, without changing
the ScoreBrackets, and the second one which actually inserts the wait
and updates the brackets.
2. Communicate pre-existing s_waitcnt instructions using an argument to
generateWaitcntInstBefore instead of through the ScoreBrackets.
To simplify these changes, a Waitcnt structure is introduced which carries
the counts of an s_waitcnt instruction in decoded form.
There are some functional changes:
1. The FIXME for the VCCZ bug workaround was implemented: we only wait for
SMEM instructions as required instead of waiting on all counters.
2. We now properly track pre-existing waitcnt's in all cases, which leads
to less conservative waitcnts being emitted in some cases.
s_load_dword ...
s_waitcnt lgkmcnt(0) <-- pre-existing wait count
ds_read_b32 v0, ...
ds_read_b32 v1, ...
s_waitcnt lgkmcnt(0) <-- this is too conservative
use(v0)
more code
use(v1)
This increases code size a bit, but the reduced latency should still be a
win in basically all cases. The worst code size regressions in my shader-db
are:
WORST REGRESSIONS - Code Size
Before After Delta Percentage
1724 1736 12 0.70 % shaders/private/f1-2015/1334.shader_test [0]
2276 2284 8 0.35 % shaders/private/f1-2015/1306.shader_test [0]
4632 4640 8 0.17 % shaders/private/ue4_elemental/62.shader_test [0]
2376 2384 8 0.34 % shaders/private/f1-2015/1308.shader_test [0]
3284 3292 8 0.24 % shaders/private/talos_principle/1955.shader_test [0]
Reviewers: msearles, rampitec, scott.linder, kanarayan
Subscribers: arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits, hakzsam
Differential Revision: https://reviews.llvm.org/D54226
llvm-svn: 347848
Currently, instructions doing memory accesses through a base operand that is
not a register can not be analyzed using `TII::getMemOpBaseRegImmOfs`.
This means that functions such as `TII::shouldClusterMemOps` will bail
out on instructions using an FI as a base instead of a register.
The goal of this patch is to refactor all this to return a base
operand instead of a base register.
Then in a separate patch, I will add FI support to the mem op clustering
in the MachineScheduler.
Differential Revision: https://reviews.llvm.org/D54846
llvm-svn: 347746
It's possible in some cases to have a restore present
without a corresponding spill. Due to an apparent bug
in D54366 <https://reviews.llvm.org/D54366>, only the
restore for a register was emitted. It's probably
always a bug for this to happen, but due to how SGPR
spilling is implemented, this makes the issues appear
worse than it is.
llvm-svn: 347595
This works if DAG combiner is enabled, but without combining
we cannot select scalar_to_vector of <2 x half> and <2 x i16>.
Differential Revision: https://reviews.llvm.org/D54718
llvm-svn: 347259
This allows to avoid scratch use or indirect VGPR addressing for
small vectors.
Differential Revision: https://reviews.llvm.org/D54606
llvm-svn: 347231
Summary:
AMDGPUAsmPrinter has a getSTI function that derives a GCNSubtarget from the
TM. However, this means that overridden target features are not detected and can
result in incorrect behaviour.
Switch to using STM which is a GCNSubtarget derived from the MF (used elsewhere
in the same function).
Change-Id: Ib6328ad667b7fcdc87e9c06344e59859207db9b0
Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D54301
llvm-svn: 347221
If a block had one of the _term instructions used for gluing
exec modifying instructions to the end of the block,
analyzeBranch would fail, preventing the verifier from catching
a broken successor list.
llvm-svn: 347027
Add a pass to fixup various vector ISel issues.
Currently we handle converting GLOBAL_{LOAD|STORE}_*
and GLOBAL_Atomic_* instructions into their _SADDR variants.
This involves feeding the sreg into the saddr field of the new instruction.
llvm-svn: 347008
An extractelement with non-constant index will be lowered either to
scratch or movrel loop in most cases. This patch converts such
instruction into a set of selects if vector size is not too big.
Differential Revision: https://reviews.llvm.org/D54351
llvm-svn: 346800
Sometimes after basic block placement we end up with a code like:
sreg = s_mov_b64 -1
vcc = s_and_b64 exec, sreg
s_cbranch_vccz
This happens as a join of a block assigning -1 to a saved mask and
another block which consumes that saved mask with s_and_b64 and a
branch.
This is essentially a single s_cbranch_execz instruction when moved
into a single new basic block.
Differential Revision: https://reviews.llvm.org/D54164
llvm-svn: 346690
This is a long-awaited follow-up suggested in D33578. Since then, we've picked up even more
opportunities for vector narrowing from changes like D53784, so there are a lot of test diffs.
Apart from 2-3 strange cases, these are all wins.
I've structured this to be no-functional-change-intended for any target except for x86
because I couldn't tell if AArch64, ARM, and AMDGPU would improve or not. All of those
targets have existing regression tests (4, 4, 10 files respectively) that would be
affected. Also, Hexagon overrides the shouldReduceLoadWidth() hook, but doesn't show
any regression test diffs. The trade-off is deciding if an extra vector load is better
than a single wide load + extract_subvector.
For x86, this is almost always better (on paper at least) because we often can fold
loads into subsequent ops and not increase the official instruction count. There's also
some unknown -- but potentially large -- benefit from using narrower vector ops if wide
ops are implemented with multiple uops and/or frequency throttling is avoided.
Differential Revision: https://reviews.llvm.org/D54073
llvm-svn: 346595
Matt Arsenault