[AMDGPU] Lowering VGPR to SGPR copies to v_readfirstlane_b32 if profitable.

Since the divergence-driven instruction selection has been enabled for AMDGPU,
all the uniform instructions are expected

[AMDGPU] Lowering VGPR to SGPR copies to v_readfirstlane_b32 if profitable.

Since the divergence-driven instruction selection has been enabled for AMDGPU,
all the uniform instructions are expected to be selected to SALU form, except those not having one.
VGPR to SGPR copies appear in MIR to connect values producers and consumers. This change implements an algorithm
that evolves a reasonable tradeoff between the profit achieved from keeping the uniform instructions in SALU form
and overhead introduced by the data transfer between the VGPRs and SGPRs.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D128252

show more ...

[AMDGPU] Do not generate ELF symbols for the local branch target labels

The compiler was generating symbols in the final code object for local
branch target labels. This bloats the code object, slow

[AMDGPU] Do not generate ELF symbols for the local branch target labels

The compiler was generating symbols in the final code object for local
branch target labels. This bloats the code object, slows down the loader,
and is only used to simplify disassembly.

Use '--symbolize-operands' with llvm-objdump to improve readability of the
branch target operands in disassembly.

Fixes: SWDEV-312223

Reviewed By: scott.linder

Differential Revision: https://reviews.llvm.org/D114273

show more ...

[LSR] Fix for pre-indexed generated constant offset

This patch changed the isLegalUse check to ensure that
LSRInstance::GenerateConstantOffsetsImpl generates an
offset that results in a legal addres

[LSR] Fix for pre-indexed generated constant offset

This patch changed the isLegalUse check to ensure that
LSRInstance::GenerateConstantOffsetsImpl generates an
offset that results in a legal addressing mode and
formula. The check is changed to look similar to the
assert check used for illegal formulas.

Differential Revision: https://reviews.llvm.org/D100383

Change-Id: Iffb9e32d59df96b8f072c00f6c339108159a009a

show more ...

[AMDGPU] Fix typo in regular expression checks. NFC.

[AMDGPU] Disable 'Skip Uniform Regions' optimization by default for AMDGPU.

Reviewers: sameerds, dstuttard

Differential Revision: https://reviews.llvm.org/D77228

Revert e1730cfeb3588f20dcf4a96b181ad52761666e52

[AMDGPU] Disable 'Skip Uniform Regions' optimization by default for AMDGPU.

Reviewers: sameerds, dstuttard

Differential Revision: https://reviews.llvm.org/D77228

AMDGPU: Try a lot harder to emit scalar loads

This has two main components. First, widen
widen short constant loads in DAG when they have
the correct alignment. This is already done a bit in
AMDGPUC

AMDGPU: Try a lot harder to emit scalar loads

This has two main components. First, widen
widen short constant loads in DAG when they have
the correct alignment. This is already done a bit in
AMDGPUCodeGenPrepare, since that has access to
DivergenceAnalysis. This can't help kernarg loads
created in the DAG. Start to use DAG divergence analysis
to help this case.

The second part is to avoid kernel argument lowering
breaking the alignment of short vector elements because
calling convention lowering wants to split everything
into legal register types.

When loading a split type, load the nearest 4-byte aligned
segment and shift to get the desired bits. This extra
load of the earlier argument piece ends up merging,
and the bit extract hopefully folds out.

There are a number of improvements and regressions with
this, but I think as-is this is a better compromise between
several of the worst parts of SelectionDAG.

Particularly when i16 is legal, this produces worse code
for i8 and i16 element vector kernel arguments. This is
partially due to the very weak load merging the DAG does.
It only looks for fairly specific combines between pairs
of loads which no longer appear. In particular this
causes v4i16 loads to be split into 2 components when
previously the two halves were merged.

Worse, because of the newly introduced shifts, there
is a lot more unnecessary vector packing and unpacking code
emitted. At least some of this is due to reporting
false for isTypeDesirableForOp for i16 as a workaround for
the lack of divergence information in the DAG. The cases
where this happens it doesn't actually matter, but the
relevant code in SimplifyDemandedBits doens't have the context
to know to ignore this.

The use of the scalar cache is probably more important
than the mess of mostly scalar instructions doing this packing
and unpacking. Future work can fix this, possibly by making better
use of the new DAG divergence information for controlling promotion
decisions, or adding another version of shift + trunc + shift
combines that doesn't only know about the used types.

llvm-svn: 334180

show more ...

AMDGPU/SI: Handle infinite loop for the structurizer to work with CFG with infinite loops.

Summary:
The current StructurizeCFG pass only works for CFG with one exit. AMDGPUUnifyDivergentExitNodes

AMDGPU/SI: Handle infinite loop for the structurizer to work with CFG with infinite loops.

Summary:
The current StructurizeCFG pass only works for CFG with one exit. AMDGPUUnifyDivergentExitNodes combines multiple "return" blocks and/or "unreachable" blocks
to one exit block for the Structurizer to work. However, infinite loop is another kind of special "exit", and if we don't handle it, the case of multiple exits will prevent the structurizer from working.

In this work, for each infinite loop, we add a dummy edge to the "return" block, and thus the AMDGPUUnifyDivergentExitNodes pass will work with infinite loops.
This will make CFG with infinite loops be structurized.

Reviewer:
nhaehnle

Differential Revision:
https://reviews.llvm.org/D46340

llvm-svn: 332625

show more ...

[AMDGPU] Fixed incorrect uniform branch condition

Summary:
I had a case where multiple nested uniform ifs resulted in code that did
v_cmp comparisons, combining the results with s_and_b64, s_or_b64

[AMDGPU] Fixed incorrect uniform branch condition

Summary:
I had a case where multiple nested uniform ifs resulted in code that did
v_cmp comparisons, combining the results with s_and_b64, s_or_b64 and
s_xor_b64 and using the resulting mask in s_cbranch_vccnz, without first
ensuring that bits for inactive lanes were clear.

There was already code for inserting an "s_and_b64 vcc, exec, vcc" to
clear bits for inactive lanes in the case that the branch is instruction
selected as s_cbranch_scc1 and is then changed to s_cbranch_vccnz in
SIFixSGPRCopies. I have added the same code into SILowerControlFlow for
the case that the branch is instruction selected as s_cbranch_vccnz.

This de-optimizes the code in some cases where the s_and is not needed,
because vcc is the result of a v_cmp, or multiple v_cmp instructions
combined by s_and/s_or. We should add a pass to re-optimize those cases.

Reviewers: arsenm, kzhuravl

Subscribers: wdng, yaxunl, t-tye, llvm-commits, dstuttard, timcorringham, nhaehnle

Differential Revision: https://reviews.llvm.org/D41292

llvm-svn: 322119

show more ...

[CodeGen] Unify MBB reference format in both MIR and debug output

As part of the unification of the debug format and the MIR format, print
MBB references as '%bb.5'.

The MIR printer prints the IR n

[CodeGen] Unify MBB reference format in both MIR and debug output

As part of the unification of the debug format and the MIR format, print
MBB references as '%bb.5'.

The MIR printer prints the IR name of a MBB only for block definitions.

* find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g'
* find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g'
* find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g'
* grep -nr 'BB#' and fix

Differential Revision: https://reviews.llvm.org/D40422

llvm-svn: 319665

show more ...

AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel

Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
ca

AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel

Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.

Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).

llvm-svn: 298444

show more ...

Codegen: Make chains from trellis-shaped CFGs

Lay out trellis-shaped CFGs optimally.
A trellis of the shape below:

A B
|\ /|
| \ / |
| X |
| / \ |
|/ \|
C D

would be la

Codegen: Make chains from trellis-shaped CFGs

Lay out trellis-shaped CFGs optimally.
A trellis of the shape below:

A B
|\ /|
| \ / |
| X |
| / \ |
|/ \|
C D

would be laid out A; B->C ; D by the current layout algorithm. Now we identify
trellises and lay them out either A->C; B->D or A->D; B->C. This scales with an
increasing number of predecessors. A trellis is a a group of 2 or more
predecessor blocks that all have the same successors.

because of this we can tail duplicate to extend existing trellises.

As an example consider the following CFG:

B D F H
/ \ / \ / \ / \
A---C---E---G---Ret

Where A,C,E,G are all small (Currently 2 instructions).

The CFG preserving layout is then A,B,C,D,E,F,G,H,Ret.

The current code will copy C into B, E into D and G into F and yield the layout
A,C,B(C),E,D(E),F(G),G,H,ret

define void @straight_test(i32 %tag) {
entry:
br label %test1
test1: ; A
%tagbit1 = and i32 %tag, 1
%tagbit1eq0 = icmp eq i32 %tagbit1, 0
br i1 %tagbit1eq0, label %test2, label %optional1
optional1: ; B
call void @a()
br label %test2
test2: ; C
%tagbit2 = and i32 %tag, 2
%tagbit2eq0 = icmp eq i32 %tagbit2, 0
br i1 %tagbit2eq0, label %test3, label %optional2
optional2: ; D
call void @b()
br label %test3
test3: ; E
%tagbit3 = and i32 %tag, 4
%tagbit3eq0 = icmp eq i32 %tagbit3, 0
br i1 %tagbit3eq0, label %test4, label %optional3
optional3: ; F
call void @c()
br label %test4
test4: ; G
%tagbit4 = and i32 %tag, 8
%tagbit4eq0 = icmp eq i32 %tagbit4, 0
br i1 %tagbit4eq0, label %exit, label %optional4
optional4: ; H
call void @d()
br label %exit
exit:
ret void
}

here is the layout after D27742:
straight_test: # @straight_test
; ... Prologue elided
; BB#0: # %entry ; A (merged with test1)
; ... More prologue elided
mr 30, 3
andi. 3, 30, 1
bc 12, 1, .LBB0_2
; BB#1: # %test2 ; C
rlwinm. 3, 30, 0, 30, 30
beq 0, .LBB0_3
b .LBB0_4
.LBB0_2: # %optional1 ; B (copy of C)
bl a
nop
rlwinm. 3, 30, 0, 30, 30
bne 0, .LBB0_4
.LBB0_3: # %test3 ; E
rlwinm. 3, 30, 0, 29, 29
beq 0, .LBB0_5
b .LBB0_6
.LBB0_4: # %optional2 ; D (copy of E)
bl b
nop
rlwinm. 3, 30, 0, 29, 29
bne 0, .LBB0_6
.LBB0_5: # %test4 ; G
rlwinm. 3, 30, 0, 28, 28
beq 0, .LBB0_8
b .LBB0_7
.LBB0_6: # %optional3 ; F (copy of G)
bl c
nop
rlwinm. 3, 30, 0, 28, 28
beq 0, .LBB0_8
.LBB0_7: # %optional4 ; H
bl d
nop
.LBB0_8: # %exit ; Ret
ld 30, 96(1) # 8-byte Folded Reload
addi 1, 1, 112
ld 0, 16(1)
mtlr 0
blr

The tail-duplication has produced some benefit, but it has also produced a
trellis which is not laid out optimally. With this patch, we improve the layouts
of such trellises, and decrease the cost calculation for tail-duplication
accordingly.

This patch produces the layout A,C,E,G,B,D,F,H,Ret. This layout does have
back edges, which is a negative, but it has a bigger compensating
positive, which is that it handles the case where there are long strings
of skipped blocks much better than the original layout. Both layouts
handle runs of executed blocks equally well. Branch prediction also
improves if there is any correlation between subsequent optional blocks.

Here is the resulting concrete layout:

straight_test: # @straight_test
; BB#0: # %entry ; A (merged with test1)
mr 30, 3
andi. 3, 30, 1
bc 12, 1, .LBB0_4
; BB#1: # %test2 ; C
rlwinm. 3, 30, 0, 30, 30
bne 0, .LBB0_5
.LBB0_2: # %test3 ; E
rlwinm. 3, 30, 0, 29, 29
bne 0, .LBB0_6
.LBB0_3: # %test4 ; G
rlwinm. 3, 30, 0, 28, 28
bne 0, .LBB0_7
b .LBB0_8
.LBB0_4: # %optional1 ; B (Copy of C)
bl a
nop
rlwinm. 3, 30, 0, 30, 30
beq 0, .LBB0_2
.LBB0_5: # %optional2 ; D (Copy of E)
bl b
nop
rlwinm. 3, 30, 0, 29, 29
beq 0, .LBB0_3
.LBB0_6: # %optional3 ; F (Copy of G)
bl c
nop
rlwinm. 3, 30, 0, 28, 28
beq 0, .LBB0_8
.LBB0_7: # %optional4 ; H
bl d
nop
.LBB0_8: # %exit

Differential Revision: https://reviews.llvm.org/D28522

llvm-svn: 295223

show more ...

AMDGPU/SI: Avoid moving PHIs to VALU when phi values are defined in scalar branches

Reviewers: arsenm

Subscribers: arsenm, llvm-commits, kzhuravl

Differential Revision: https://reviews.llvm.org/D2

AMDGPU/SI: Avoid moving PHIs to VALU when phi values are defined in scalar branches

Reviewers: arsenm

Subscribers: arsenm, llvm-commits, kzhuravl

Differential Revision: https://reviews.llvm.org/D23417

llvm-svn: 288095

show more ...

AMDGPU: Remove unnecessary and on conditional branch

The comment explaining why this was necessary is incorrect
in its description of v_cmp's behavior for inactive workitems.

llvm-svn: 286134

AMDGPU: Use unsigned compare for eq/ne

For some reason there are both of these available, except
for scalar 64-bit compares which only has u64. I'm not sure
why there are both (I'm guessing it's for

AMDGPU: Use unsigned compare for eq/ne

For some reason there are both of these available, except
for scalar 64-bit compares which only has u64. I'm not sure
why there are both (I'm guessing it's for the one bit inputs we
don't use), but for consistency always using the
unsigned one.

llvm-svn: 282832

show more ...

AMDGPU: Un-xfail and add tests

Un XFAIL a few tests plus a few more I had lying around
in my tree, which seem to all work now but I don't see tests
that quite test the same things.

llvm-svn: 273655