For #10958, #24543, but makes sense on its own.
Change-Id: I2a87dab66b82a1863e4b6512b1f8def51463ce2a
Reviewed-on: https://go-review.googlesource.com/c/go/+/203284
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
To permit ssa-level optimization, this change introduces an amd64 intrinsic
that generates the VFMADD231SD instruction for the fused-multiply-add
operation on systems that support it. System support is detected via
cpu.X86.HasFMA. A rewrite rule can then translate the generic ssa intrinsic
("Fma") to VFMADD231SD.
The benchmark compares the software implementation (old) with the intrinsic
(new).
name old time/op new time/op delta
Fma-4 27.2ns ± 1% 1.0ns ± 9% -96.48% (p=0.008 n=5+5)
Updates #25819.
Change-Id: I966655e5f96817a5d06dff5942418a3915b09584
Reviewed-on: https://go-review.googlesource.com/c/go/+/137156
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
This opcode was only used to mark unreachable code for plive to use.
plive now uses the SSA representation, so it knows locations are
unreachable because they are ends of Exit blocks. It doesn't need
these opcodes any more.
These opcodes actually used space in the binary, 2 bytes per undef
on x86 and more for other archs.
Makes the amd64 go binary 0.2% smaller.
Change-Id: I64c84c35db7c7949617a3a5830f09c8e5fcd2620
Reviewed-on: https://go-review.googlesource.com/c/go/+/171058
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
'SUBQ $-0x80, r' is shorter to encode than 'ADDQ $0x80, r',
and functionally equivalent. Use it instead.
Shaves off a few bytes here and there:
file before after Δ %
compile 25935856 25927664 -8192 -0.032%
nm 4251840 4247744 -4096 -0.096%
Change-Id: Ia9e02ea38cbded6a52a613b92e3a914f878d931e
Reviewed-on: https://go-review.googlesource.com/c/go/+/168344
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
A few examples (for accessing a slice of length 3):
s[-1] runtime error: index out of range [-1]
s[3] runtime error: index out of range [3] with length 3
s[-1:0] runtime error: slice bounds out of range [-1:]
s[3:0] runtime error: slice bounds out of range [3:0]
s[3:-1] runtime error: slice bounds out of range [:-1]
s[3:4] runtime error: slice bounds out of range [:4] with capacity 3
s[0:3:4] runtime error: slice bounds out of range [::4] with capacity 3
Note that in cases where there are multiple things wrong with the
indexes (e.g. s[3:-1]), we report one of those errors kind of
arbitrarily, currently the rightmost one.
An exhaustive set of examples is in issue30116[u].out in the CL.
The message text has the same prefix as the old message text. That
leads to slightly awkward phrasing but hopefully minimizes the chance
that code depending on the error text will break.
Increases the size of the go binary by 0.5% (amd64). The panic functions
take arguments in registers in order to keep the size of the compiled code
as small as possible.
Fixes#30116
Change-Id: Idb99a827b7888822ca34c240eca87b7e44a04fdd
Reviewed-on: https://go-review.googlesource.com/c/go/+/161477
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: David Chase <drchase@google.com>
Refactoring only.
This makes it easier to add ops
that do indexed memory loads/stores.
Passes toolstash-check.
Change-Id: I82df0d4154718577ec42106fa1bc76571bf65096
Reviewed-on: https://go-review.googlesource.com/c/go/+/166425
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
prove is able to find 94 occurrences in std cmd where a divisor
can't have the value -1. The change removes
the extraneous fix-up code for these cases.
Fixes#25239
Change-Id: Ic184de971f47cc57c702eb72805b8e291c14035d
Reviewed-on: https://go-review.googlesource.com/c/130215
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Add generic, 386 and amd64 specific ops and SSA rules for multiplication
with overflow and branching based on overflow flags. Use these to intrinsify
runtime/internal/math.MulUinptr.
On amd64
mul, overflow := math.MulUintptr(a, b)
if overflow {
is lowered to two instructions:
MULQ SI
JO 0x10ee35c
No codegen tests as codegen can not currently test unexported internal runtime
functions.
amd64:
name old time/op new time/op delta
MulUintptr/small 1.16ns ± 5% 0.88ns ± 6% -24.36% (p=0.000 n=19+20)
MulUintptr/large 10.7ns ± 1% 1.1ns ± 1% -89.28% (p=0.000 n=17+19)
Change-Id: If60739a86f820e5044d677276c21df90d3c7a86a
Reviewed-on: https://go-review.googlesource.com/c/141820
Run-TryBot: Martin Möhrmann <moehrmann@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
BSFQ/BSRQ/BSFL/BSRL/SQRTSD have similar logic in amd64's assembly
generator. This CL combines them together while does not impact
generated amd64 code. The total size of
pkg/linux_amd64/cmd/compile/internal decreases about 1.8KB.
Change-Id: I5f3210c5178c20ac9108877c69f17234baf5b6b7
Reviewed-on: https://go-review.googlesource.com/c/140438
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
This CL combines similar code in amd64's assembly generator. The
total size of pkg/linux_amd64/cmd/compile/ decreases about 4.5KB,
while the generated amd64 code is not affected.
Change-Id: I4cdbdd22bde8857aafdc29b47fa100a906fa1598
Reviewed-on: https://go-review.googlesource.com/c/140298
Run-TryBot: Ben Shi <powerman1st@163.com>
Reviewed-by: Keith Randall <khr@golang.org>
AMD64's ADDQconstmodify/ADDLconstmodify have similar logic with
other constmodify like operators, but seperated case statements.
This CL simplify them with a fallthrough.
Change-Id: Ia73ffeaddc5080182f68c06c9d9b48fe32a14e38
Reviewed-on: https://go-review.googlesource.com/135855
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Merge two case-statements together, since they have similar logic.
1. That makes the assembly generator more clear.
2. The total size of cmd/compile decreases about 0.8KB.
Change-Id: I0144a07152202ee7b21e323bcd5dea80a351a6e3
Reviewed-on: https://go-review.googlesource.com/134215
Run-TryBot: Ben Shi <powerman1st@163.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Some *mem ops are loads, some are stores, some are modifications.
Replace mem->load for the loads.
Replace mem->store for the stores.
Replace mem->modify for the load-modify-stores.
The only semantic change in this CL is to mark
ADD(Q|L)constmodify (which used to be ADD(Q|L)constmem) as
both a read and a write, instead of just a write. This is arguably
a bug fix, but the bug isn't triggerable at the moment, see CL 112157.
Change-Id: Iccb45aea817b606adb2d712ff99b10ee28e4616a
Reviewed-on: https://go-review.googlesource.com/112159
Run-TryBot: Keith Randall <khr@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Currently, each architecture lowers OpConvert to an arch-specific
OpXXXconvert. This is silly because OpConvert means the same thing on
all architectures and is logically a no-op that exists only to keep
track of conversions to and from unsafe.Pointer. Furthermore, lowering
it makes it harder to recognize in other analyses, particularly
liveness analysis.
This CL eliminates the lowering of OpConvert, leaving it as the
generic op until code generation time.
The main complexity here is that we still need to register-allocate
OpConvert operations. Currently, each arch's lowered OpConvert
specifies all GP registers in its register mask. Ideally, OpConvert
wouldn't affect value homing at all, and we could just copy the home
of OpConvert's source, but this can potentially home an OpConvert in a
LocalSlot, which neither regalloc nor stackalloc expect. Rather than
try to disentangle this assumption from regalloc and stackalloc, we
continue to register-allocate OpConvert, but teach regalloc that
OpConvert can be allocated to any allocatable GP register.
For #24543.
Change-Id: I795a6aee5fd94d4444a7bafac3838a400c9f7bb6
Reviewed-on: https://go-review.googlesource.com/108496
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: David Chase <drchase@google.com>
When a neither of a conditional block's successors follows,
the block must end with a conditional branch followed by a
an unconditional branch. If the (conditional) branch is
"unlikely", invert it and swap successors to make it
likely instead.
This doesn't matter to most benchmarks on amd64, but in one
instance on amd64 it caused a 30% improvement, and it is
otherwise harmless. The problematic loop is
for i := 0; i < w; i++ {
if pw[i] != 0 {
return true
}
}
compiled under GOEXPERIMENT=preemptibleloops
This the very worst-case benchmark for that experiment.
Also in this CL is a commoning up of heavily-repeated
boilerplate, which made it much easier to see that the
changes were applied correctly. In the future this should
allow un-exporting of SSAGenState.Branches once the
boilerplate-replacement is done everywhere.
Change-Id: I0e5ded6eeb3ab1e3e0138e12d54c7e056bd99335
Reviewed-on: https://go-review.googlesource.com/104977
Run-TryBot: David Chase <drchase@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
This reverts commit 080187f4f72bd6594e3c2efc35cf51bf61378552.
It broke build of golang.org/x/exp/shiny/iconvg
See issue 24395 for details
Change-Id: Ifd6134f6214e6cee40bd3c63c32941d5fc96ae8b
Reviewed-on: https://go-review.googlesource.com/100755
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
This rule is meant for code optimization, but it makes other rules
potentially more complex, as they need to cope with the fact that
a 32-bit op (BTLconst) can appear everywhere a 64-bit rule maches.
Move the optimization to opcode expansion instead. Tests will be
added in following CL.
Change-Id: Ica5ef291e7963c4af17c124d4a2869e6c8f7b0c7
Reviewed-on: https://go-review.googlesource.com/99995
Reviewed-by: Keith Randall <khr@golang.org>
cmd/asm now supports three-operand form of IMUL,
so instead of using IMUL with resultInArg0, emit IMUL3 instruction.
This results in less redundant MOVs where SSA assigns
different registers to input[0] and dst arguments.
Note: these have exactly the same encoding when reg0=reg1:
IMUL3x $const, reg0, reg1
IMULx $const, reg
Two-operand IMULx is like a crippled IMUL3x, with dst fixed to input[0].
This is why we don't bother to generate IMULx for the case where
dst is the same as input[0].
Change-Id: I4becda475b3dffdd07b6fdf1c75bacc82af654e4
Reviewed-on: https://go-review.googlesource.com/99656
Run-TryBot: Iskander Sharipov <iskander.sharipov@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Giovanni Bajo <rasky@develer.com>
Reviewed-by: Keith Randall <khr@golang.org>
Allow the compiler to generate code like CMPQ 16(AX), $7
It's tricky because it's difficult to spill such a comparison during
flagalloc, because the same memory state might not be available at
the restore locations.
Solve this problem by decomposing the compare+load back into its parts
if it needs to be spilled.
The big win is that the write barrier test goes from:
MOVL runtime.writeBarrier(SB), CX
TESTL CX, CX
JNE 60
to
CMPL runtime.writeBarrier(SB), $0
JNE 59
It's one instruction and one byte smaller.
Fixes#19485Fixes#15245
Update #22460
Binaries are about 0.15% smaller.
Change-Id: I4fd8d1111b6b9924d52f9a0901ca1b2e5cce0836
Reviewed-on: https://go-review.googlesource.com/86035
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
Currently we generate NEGQ for DIV{Q,L,W}. By generating NEGL and NEGW,
we will reduce code size, because NEGL doesn't require rex prefix.
This also guarantees that upper 32 bits are zeroed, so we can revert CL 85736,
and remove zero-extensions of DIVL results.
Also adds test for redundant zero extend elimination.
Fixes#23310
Change-Id: Ic58c3104c255a71371a06e09d10a975bbe5df587
Reviewed-on: https://go-review.googlesource.com/96815
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Popcnt has false dependency on output register and generates
MOVQ $0, reg to break it. But recently we switched MOVQ $0, reg
encoding from xor reg, reg to actual mov $0, reg. This CL updates
code generation for popcnt to use actual XOR.
Change-Id: I4c1fc11e85758b53ba2679165fa55614ec54b27d
Reviewed-on: https://go-review.googlesource.com/82516
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Currently, tail calls on x86 don't adjust the SP on return, so it's
important that the compiler produce a zero-sized frame and disable the
frame pointer. However, these constraints aren't necessary. For
example, on other architectures it's generally necessary to restore
the saved LR before a tail call, so obj simply makes this work.
Likewise, on x86, there's no reason we can't simply make this work.
Hence, this CL adjusts the compiler to use the same tail call
convention for x86 that we use on LR machines by producing a RET with
a target, rather than a JMP with a target. In fact, obj already
understands this convention for x86 except that it's buggy with
non-zero frame sizes. So we also fix this bug obj. As a result of
these fixes, the compiler no longer needs to mark wrappers as
NoFramePointer since it's now perfectly fine to save the frame
pointer.
In fact, this eliminates the only use of NoFramePointer in the
compiler, which will enable further cleanups.
This also fixes what is very nearly, but not quite, a code generation
bug. NoFramePointer becomes obj.NOFRAME in the object file, which on
ppc64 and s390x means to omit the saved LR. Hence, on these
architectures, NoFramePointer (and NOFRAME) is only safe to set on
leaf functions. However, on *most* architectures, wrappers aren't
necessarily leaf functions because they may call DUFFZERO. We're saved
on ppc64 and s390x only because the compiler doesn't have the rules to
produce DUFFZERO calls on these architectures. Hence, this only works
because the set of LR architectures that implement NOFRAME is disjoint
from the set where the compiler produces DUFFZERO operations. (I
discovered this whole mess when I attempted to add NOFRAME support to
arm.)
Change-Id: Icc589aeb86beacb850d0a6a80bd3024974a33947
Reviewed-on: https://go-review.googlesource.com/92035
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
We already do this for floor/ceil, but RoundToEven was added later.
Intrinsify it also.
name old time/op new time/op delta
RoundToEven-8 3.00ns ± 1% 0.68ns ± 2% -77.34% (p=0.000 n=10+10)
Change-Id: Ib158cbceb436c6725b2d9353a526c5c4be19bcad
Reviewed-on: https://go-review.googlesource.com/74852
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
Reviewed-by: Keith Randall <khr@golang.org>
Add a compiler intrinsic for getcallersp. So we are able to get
rid of the argument (not done in this CL).
Change-Id: Ic38fda1c694f918328659ab44654198fb116668d
Reviewed-on: https://go-review.googlesource.com/69350
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
Reviewed-by: David Chase <drchase@google.com>
Combine setcc and store of result into setcc that writes directly to memory.
Triggers 200+ times in go tool.
Fixes#21630
Change-Id: Iafa22607426f4120140c88fae4b9aecb46e0bba8
Reviewed-on: https://go-review.googlesource.com/67950
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
First step towards removing the mandatory argument for
getcallerpc, which solves certain problems for the runtime.
This might also slightly improve performance.
Intrinsic enabled on 386, amd64, amd64p32,
runtime asm implementation removed on those architectures.
Now-superfluous argument remains in getcallerpc signature
(for a future CL; non-386/amd64 asm funcs ignore it).
Added getcallerpc to the "not a real function" test
in dcl.go, that story is a little odd with respect to
unexported functions but that is not this CL.
Fixes#17327.
Change-Id: I5df1ad91f27ee9ac1f0dd88fa48f1329d6306c3e
Reviewed-on: https://go-review.googlesource.com/31851
Run-TryBot: David Chase <drchase@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Austin Clements <austin@google.com>
Currently we only use 1 and 4 as a scale for indexed 4-byte load.
In code generated in #20711 we can use indexed load with scale=8,
to improve performance:
name old time/op new time/op delta
GM-6 108µs ± 0% 95µs ± 0% -12.06% (p=0.000 n=10+10)
So add new ops and combine loadidx1(shift 3..).. into loadidx8,
same for stores.
Change-Id: I5ed1c250ac40960e20606580cf9de221e75b72f1
Reviewed-on: https://go-review.googlesource.com/46134
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Went mainly for the ones that make no sense, such as the ones
mid-sentence or after commas.
Change-Id: Ie245d2c19cc7428a06295635cf6a9482ade25ff0
Reviewed-on: https://go-review.googlesource.com/57293
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Run-TryBot: Daniel Martí <mvdan@mvdan.cc>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Implement int reg <-> fp reg moves on amd64.
If we see a load to int reg followed by an int->fp move, then we can just
load to the fp reg instead. Same for stores.
math.Abs is now:
MOVQ "".x+8(SP), AX
SHLQ $1, AX
SHRQ $1, AX
MOVQ AX, "".~r1+16(SP)
math.Copysign is now:
MOVQ "".x+8(SP), AX
SHLQ $1, AX
SHRQ $1, AX
MOVQ "".y+16(SP), CX
SHRQ $63, CX
SHLQ $63, CX
ORQ CX, AX
MOVQ AX, "".~r2+24(SP)
math.Float64bits is now:
MOVSD "".x+8(SP), X0
MOVSD X0, "".~r1+16(SP)
(it would be nicer to use a non-SSE reg for this, nothing is perfect)
And due to the fix for #21440, the inlined version of these improve as well.
name old time/op new time/op delta
Abs 1.38ns ± 5% 0.89ns ±10% -35.54% (p=0.000 n=10+10)
Copysign 1.56ns ± 7% 1.35ns ± 6% -13.77% (p=0.000 n=9+10)
Fixes#13095
Change-Id: Ibd7f2792412a6668608780b0688a77062e1f1499
Reviewed-on: https://go-review.googlesource.com/58732
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
We can add a constant to loaction in memory with 1 instruction,
as opposed to load+add+store, so add a new op and relevent ssa rules.
Triggers in e. g. encoding/json isValidNumber:
NumberIsValid-6 36.4ns ± 0% 35.2ns ± 1% -3.32% (p=0.000 n=6+10)
Shaves ~2.5 kb from go tool.
Change-Id: I7ba576676c2522432360f77b290cecb9574a93c3
Reviewed-on: https://go-review.googlesource.com/54431
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
