sparse conditional constant propagation can discover optimization
opportunities that cannot be found by just combining constant folding
and constant propagation and dead code elimination separately.
This is a re-submit of PR#59575, which fix a broken dominance relationship caught by ssacheck
Updates https://github.com/golang/go/issues/59399
Change-Id: I57482dee38f8e80a610aed4f64295e60c38b7a47
GitHub-Last-Rev: 830016f24e
GitHub-Pull-Request: golang/go#60469
Reviewed-on: https://go-review.googlesource.com/c/go/+/498795
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Heschi Kreinick <heschi@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
Previously, the unified frontend implemented unsafe.Sizeof, etc that
involved derived types by constructing a normal OSIZEOF, etc
expression, including fully instantiating their argument. (When
unsafe.Sizeof is applied to a non-generic type, types2 handles
constant folding it.)
This worked, but involves unnecessary work, since all we really need
to track is the argument type (and the field selections, for
unsafe.Offsetof).
Further, the argument expression could generate temporary variables,
which would then go unused after typecheck replaced the OSIZEOF
expression with an OLITERAL. This results in compiler failures after
CL 523315, which made later passes stricter about expecting the
frontend to not construct unused temporaries.
Fixes#62515.
Change-Id: I37baed048fd2e35648c59243f66c97c24413aa94
Reviewed-on: https://go-review.googlesource.com/c/go/+/527097
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Currently, cmd/compile optimizes `var a = true; var b = a` into `var a
= true; var b = true`. But this may not be safe if we need to
initialize any other global variables between `a` and `b`, and the
initialization involves calling a user-defined function that reassigns
`a`.
This CL changes staticinit to keep track of the initialization
expressions that we've seen so far, and to stop applying the
staticcopy optimization once we've seen an initialization expression
that might have modified another global variable within this package.
To help identify affected initializers, this CL adds a -d=staticcopy
flag to warn when a staticcopy is suppressed and turned into a dynamic
copy.
Currently, `go build -gcflags=all=-d=staticcopy std` reports only four
instances:
```
encoding/xml/xml.go:1600:5: skipping static copy of HTMLEntity+0 with map[string]string{...}
encoding/xml/xml.go:1869:5: skipping static copy of HTMLAutoClose+0 with []string{...}
net/net.go:661:5: skipping static copy of .stmp_31+0 with poll.ErrNetClosing
net/http/transport.go:2566:5: skipping static copy of errRequestCanceled+0 with ~R0
```
Fixes#51913.
Change-Id: Iab41cf6f84c44f7f960e4e62c28a8aeaade4fbcf
Reviewed-on: https://go-review.googlesource.com/c/go/+/395541
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: David Chase <drchase@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Heschi Kreinick <heschi@google.com>
When creating the struct type to hold variables captured by a function
literal, we currently reuse the captured variable names as fields.
However, there's no particular reason to do this: these struct types
aren't visible to users, and it adds extra complexity in making sure
fields belong to the correct packages.
Further, it turns out we were getting that subtly wrong. If two
function literals from different packages capture variables with
identical names starting with an uppercase letter (and in the same
order and with corresponding identical types) end up in the same
function (e.g., due to inlining), then we could end up creating
closure struct types that are "different" (i.e., not types.Identical)
yet end up with equal LinkString representations (which violates
LinkString's contract).
The easy fix is to just always use simple, exported, generated field
names in the struct. This should allow further struct reuse across
packages too, and shrink binary sizes slightly.
Fixes#62498.
Change-Id: I9c973f5087bf228649a8f74f7dc1522d84a26b51
Reviewed-on: https://go-review.googlesource.com/c/go/+/527135
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Keith Randall <khr@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
One of the more tedious quirks of the original frontend (i.e.,
typecheck) to preserve was that it preserved the original
representation of constants into the backend. To fit into the unified
IR model, I ended up implementing a fairly heavyweight workaround:
simply record the original constant's string expression in the export
data, so that diagnostics could still report it back, and match the
old test expectations.
But now that there's just a single frontend to support, it's easy
enough to just update the test expectations and drop this support for
"raw" constant expressions.
Change-Id: I1d859c5109d679879d937a2b213e777fbddf4f2f
Reviewed-on: https://go-review.googlesource.com/c/go/+/526376
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Unfortunately, there isn't a single op that provides the resulting
computation.
At least, I couldn't find one.
Fixes#62469
Change-Id: I236f3965b827aaeb3d70ef9fe89be66b116494f5
Reviewed-on: https://go-review.googlesource.com/c/go/+/526276
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: Keith Randall <khr@google.com>
Generate RLDIC[LR] instead of MOVD mask, Rx; AND Rx, Ry, Rz.
This helps reduce code size, and reduces the latency caused
by the constant load.
Similarly, for smaller-than-register values, truncate constants
which exceed the range of the value's type to avoid needing to
load a constant.
Change-Id: I6019684795eb8962d4fd6d9585d08b17c15e7d64
Reviewed-on: https://go-review.googlesource.com/c/go/+/515576
Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Run-TryBot: Paul Murphy <murp@ibm.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cherry Mui <cherryyz@google.com>
This reverts commit c1dfbf72e1.
Reason for revert: TESTL rule is wrong when the result is used for an ordered comparison.
Fixes#62360
Change-Id: I4d5b6aca24389b0a2bf767bfbc0a9d085359eb38
Reviewed-on: https://go-review.googlesource.com/c/go/+/524255
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Jakub Ciolek <jakub@ciolek.dev>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Bryan Mills <bcmills@google.com>
In CL 522879, I moved the logic for setting Addrtaken from typecheck's
markAddrOf and ComputeAddrtaken directly into ir.NewAddrExpr. However,
I took the logic from markAddrOf, and failed to notice that
ComputeAddrtaken also set Addrtaken on the canonical ONAME.
The result is that if the only address-of expressions were within a
function literal, the canonical variable never got marked Addrtaken.
In turn, this could cause the consistency check in ir.Reassigned to
fail. (Yay for consistency checks turning mistakes into ICEs, rather
than miscompilation.)
Fixes#62313.
Change-Id: Ieab2854cd7fcc1b6c5d1e61de66453add9890a4f
Reviewed-on: https://go-review.googlesource.com/c/go/+/523375
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Bryan Mills <bcmills@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Also gofmt a test file to make sure the parser works.
Fixes#62267.
Change-Id: I9b9f12b06bae7df626231000879b5ed7df3cd9ba
Reviewed-on: https://go-review.googlesource.com/c/go/+/522635
Reviewed-by: Ian Lance Taylor <iant@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Auto-Submit: Bryan Mills <bcmills@google.com>
Run-TryBot: Bryan Mills <bcmills@google.com>
This test passes "-linkmode=external" to 'go run' to link the binary
using the system C linker.
CGO_ENABLED=0 explicitly tells cmd/go not to use the C toolchain,
so the test should not be run in that configuration.
Updates #46330.
Change-Id: I16ac66aac91178045f9decaeb28134061e9711f7
Reviewed-on: https://go-review.googlesource.com/c/go/+/522495
Reviewed-by: Heschi Kreinick <heschi@google.com>
Reviewed-by: Than McIntosh <thanm@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Auto-Submit: Bryan Mills <bcmills@google.com>
Run-TryBot: Bryan Mills <bcmills@google.com>
In go.dev/cl/517775, I moved the frontend's deadcode elimination pass
into unified IR. But I also made a small enhancement: a branch like
"if x || true" is now detected as always taken, so the else branch can
be eliminated.
However, the inliner also has an optimization for delaying the
introduction of the result temporary variables when there's a single
return statement (added in go.dev/cl/266199). Consequently, the
inliner turns "if x || true { return true }; return true" into:
if x || true {
~R0 := true
goto .i0
}
.i0:
// code that uses ~R0
In turn, this confuses phi insertion, because it doesn't recognize
that the "if" statement is always taken, and so ~R0 will always be
initialized.
With this CL, after inlining we instead produce:
_ = x || true
~R0 := true
goto .i0
.i0:
Fixes#62211.
Change-Id: Ic8a12c9eb85833ee4e5d114f60e6c47817fce538
Reviewed-on: https://go-review.googlesource.com/c/go/+/522096
Reviewed-by: Than McIntosh <thanm@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
For large interface -> concrete type switches, we can use a jump
table on some bits of the type hash instead of a binary search on
the type hash.
name old time/op new time/op delta
SwitchTypePredictable-24 1.99ns ± 2% 1.78ns ± 5% -10.87% (p=0.000 n=10+10)
SwitchTypeUnpredictable-24 11.0ns ± 1% 9.1ns ± 2% -17.55% (p=0.000 n=7+9)
Change-Id: Ida4768e5d62c3ce1c2701288b72664aaa9e64259
Reviewed-on: https://go-review.googlesource.com/c/go/+/521497
Reviewed-by: Keith Randall <khr@google.com>
Auto-Submit: Keith Randall <khr@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Run-TryBot: Keith Randall <khr@golang.org>
This lets us combine more write barriers, getting rid of some of the
test+branch and gcWriteBarrier* calls.
With the new write barriers, it's easy to add a few non-pointer writes
to the set of values written.
We allow up to 2 non-pointer writes between pointer writes. This is enough
for, for example, adjacent slice fields.
Fixes#62126
Change-Id: I872d0fa9cc4eb855e270ffc0223b39fde1723c4b
Reviewed-on: https://go-review.googlesource.com/c/go/+/521498
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: Keith Randall <khr@google.com>
Currently, the types package has IsRuntimePkg and IsReflectPkg
predicates for testing if a Pkg is the runtime or reflect packages.
IsRuntimePkg returns "true" for any "CompilingRuntime" package, which
includes all of the packages imported by the runtime. This isn't
inherently wrong, except that all but one use of it is of the form "is
this Sym a specific runtime.X symbol?" for which we clearly only want
the package "runtime" itself. IsRuntimePkg was introduced (as
isRuntime) in CL 37538 as part of separating the real runtime package
from the compiler built-in fake runtime package. As of that CL, the
"runtime" package couldn't import any other packages, so this was
adequate at the time.
We could fix this by just changing the implementation of IsRuntimePkg,
but the meaning of this API is clearly somewhat ambiguous. Instead, we
replace it with a new RuntimeSymName function that returns the name of
a symbol if it's in package "runtime", or "" if not. This is what
every call site (except one) actually wants, which lets us simplify
the callers, and also more clearly addresses the ambiguity between
package "runtime" and the general concept of a runtime package.
IsReflectPkg doesn't have the same issue of ambiguity, but it
parallels IsRuntimePkg and is used in the same way, so we replace it
with a new ReflectSymName for consistency.
Change-Id: If3a81d7d11732a9ab2cac9488d17508415cfb597
Reviewed-on: https://go-review.googlesource.com/c/go/+/521696
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
This CL adds FMADDS,FMSUBS,FNMADDS,FNMSUBS SSA support for riscv
Change-Id: I1e7dd322b46b9e0f4923dbba256303d69ed12066
Reviewed-on: https://go-review.googlesource.com/c/go/+/506616
Reviewed-by: Joel Sing <joel@sing.id.au>
Reviewed-by: David Chase <drchase@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: M Zhuo <mzh@golangcn.org>
There's no need for distinct hmap and hiter types for each map.
Shaves 9kB off cmd/go binary size.
Change-Id: I7bc3b2d8ec82e7fcd78c1cb17733ebd8b615990a
Reviewed-on: https://go-review.googlesource.com/c/go/+/521615
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
If we're not using the upper bits, don't bother issuing a
sign/zero extension operation.
For arm64, after CL 520916 which fixed a correctness bug with
extensions but as a side effect leaves many unnecessary ones
still in place.
Change-Id: I5f4fe4efbf2e9f80969ab5b9a6122fb812dc2ec0
Reviewed-on: https://go-review.googlesource.com/c/go/+/521496
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
This CL implements the remainder of the zero-copy string->[]byte
conversion optimization initially attempted in go.dev/cl/520395, but
fixes the tracking of mutations due to ODEREF/ODOTPTR assignments, and
adds more comprehensive tests that I should have included originally.
However, this CL also keeps it behind the -d=zerocopy flag. The next
CL will enable it by default (for easier rollback).
Updates #2205.
Change-Id: Ic330260099ead27fc00e2680a59c6ff23cb63c2b
Reviewed-on: https://go-review.googlesource.com/c/go/+/520599
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Than McIntosh <thanm@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
This reverts CL 520395.
Reason for revert: thanm@ pointed out failure cases.
Change-Id: I3fd60b73118be3652be2c08b77ab39e793b42110
Reviewed-on: https://go-review.googlesource.com/c/go/+/520596
Reviewed-by: Dmitri Shuralyov <dmitshur@golang.org>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Than McIntosh <thanm@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
This CL enables the latent support for string->[]byte conversions
added go.dev/cl/520259.
One catch is that we need to make sure []byte("") evaluates to a
non-nil slice, even if "" is (nil, 0). This CL addresses that by
adding a "ptr != nil" check for OSTR2BYTESTMP, unless the NonNil flag
is set.
The existing uses of OSTR2BYTESTMP (which aren't concerned about
[]byte("") evaluating to nil) are updated to set this flag.
Fixes#2205.
Change-Id: I35a9cb16c164cd86156b7560915aba5108d8b523
Reviewed-on: https://go-review.googlesource.com/c/go/+/520395
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Currently, we rewrite:
go f(new(T))
into:
tmp := new(T)
go func() { f(tmp) }()
However, we can both shrink the closure and improve escape analysis by
instead rewriting it into:
go func() { f(new(T)) }()
This CL does that.
Change-Id: Iae16a476368da35123052ca9ff41c49159980458
Reviewed-on: https://go-review.googlesource.com/c/go/+/520340
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Normalizing go/defer statements to always use functions with zero
parameters and zero results was added to escape analysis, because that
was the earliest point at which all three frontends converged. Now
that we only have the unified frontend, we can do it during typecheck,
which is where we perform all other desugaring and normalization
rewrites.
Change-Id: Iebf7679b117fd78b1dffee2974bbf85ebc923b23
Reviewed-on: https://go-review.googlesource.com/c/go/+/520260
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
I previously used a clumsy hack to copy Closgen back and forth while
inlining, to handle when an inlined function contains closures, which
need to each be uniquely numbered.
The real solution was to name the closures using r.inlCaller, rather
than r.curfn. This CL adds a helper method to do exactly this.
Change-Id: I510553b5d7a8f6581ea1d21604e834fd6338cb06
Reviewed-on: https://go-review.googlesource.com/c/go/+/520339
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
This CL extends escape analysis in two ways.
First, we already optimize directly called closures. For example,
given:
var x int // already stack allocated today
p := func() *int { return &x }()
we don't need to move x to the heap, because we can statically track
where &x flows. This CL extends the same idea to work for indirectly
called closures too, as long as we know everywhere that they're
called. For example:
var x int // stack allocated after this CL
f := func() *int { return &x }
p := f()
This will allow a subsequent CL to move the generation of go/defer
wrappers earlier.
Second, this CL adds tracking to detect when pointer values flow to
the pointee operand of an indirect assignment statement (i.e., flows
to p in "*p = x") or to builtins that modify memory (append, copy,
clear). This isn't utilized in the current CL, but a subsequent CL
will make use of it to better optimize string->[]byte conversions.
Updates #2205.
Change-Id: I610f9c531e135129c947684833e288ce64406f35
Reviewed-on: https://go-review.googlesource.com/c/go/+/520259
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Auto-Submit: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
For aggregate-typed arguments passed to a call, expandCalls
decomposed them into parts in the same block where the value
was created. This is not necessarily the call block, and in
the case where stores are involved, can change the memory
leaving that block, and getting that right is problematic.
Instead, do all the expanding in the same block as the call,
which avoids the problems of (1) not being able to reorder
loads/stores across a block boundary to conform to memory
order and (2) (incorrectly, not) exposing the new memory to
consumers in other blocks. Putting it all in the same block
as the call allows reordering, and the call creates its own
new memory (which is already dealt with correctly).
Fixes#61992.
Change-Id: Icc7918f0d2dd3c480cc7f496cdcd78edeca7f297
Reviewed-on: https://go-review.googlesource.com/c/go/+/519276
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: David Chase <drchase@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Open-coded defer slots are assigned indices upfront, so they're
logically like elements in an array. Without reassigning the indices,
we need to keep all of the elements alive so their relative offsets
are correct.
Fixes#61895.
Change-Id: Ie0191fdb33276f4e8ed0becb69086524fff022b2
Reviewed-on: https://go-review.googlesource.com/c/go/+/517856
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
CL 497276 added optimization for len(string([]byte)) by avoiding call to
slicebytetostring. However, the bytes to string expression may contain
init nodes, which need to be preserved. Otherwise, it would make the
liveness analysis confusing about the lifetime of temporary variables
created by init nodes.
Fixes#61778
Change-Id: I6d1280a7d61bcc75f11132af41bda086f084ab54
Reviewed-on: https://go-review.googlesource.com/c/go/+/516375
Run-TryBot: Cuong Manh Le <cuong.manhle.vn@gmail.com>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
Auto-Submit: Cuong Manh Le <cuong.manhle.vn@gmail.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Stop using BTSconst and friends when ORLconst can be used instead.
OR can be issued by more function units than BTS can, so it could
lead to better IPC. OR might take a few more bytes to encode, but
not a lot more.
Still use BTSconst for cases where the constant otherwise wouldn't
fit and would require a separate movabs instruction to materialize
the constant. This happens when setting bits 31-63 of 64-bit targets.
Add BTS-to-memory operations so we don't need to load/bts/store.
Fixes#61694
Change-Id: I00379608df8fb0167cb01466e97d11dec7c1596c
Reviewed-on: https://go-review.googlesource.com/c/go/+/515755
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Fixes#61629
This reduce the pressure on regalloc because then the loop only keep alive
one value (the iterator) instead of the iterator and the upper bound since
the comparison now acts against an immediate, often zero which can be skipped.
This optimize things like:
for i := 0; i < n; i++ {
Or a range over a slice where the index is not used:
for _, v := range someSlice {
Or the new range over int from #61405:
for range n {
It is hit in 975 unique places while doing ./make.bash.
Change-Id: I5facff8b267a0b60ea3c1b9a58c4d74cdb38f03f
Reviewed-on: https://go-review.googlesource.com/c/go/+/512935
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Jorropo <jorropo.pgm@gmail.com>
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: David Chase <drchase@google.com>
Reviewed-by: Keith Randall <khr@golang.org>
Auto-Submit: Keith Randall <khr@golang.org>
s==s is always true for strings. This comes up in NaN testing in
generic code, where we want x==x to compile completely away except for
float types.
Fixes#60777
Change-Id: I3ce054b5121354de2f9751b010fb409f148cb637
Reviewed-on: https://go-review.googlesource.com/c/go/+/503795
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
If we load 2 values and then store those 2 loaded values, we can likely
perform that operation with a single wider load and store.
Fixes#60709
Change-Id: Ifc5f92c2f1b174c6ed82a69070f16cec6853c770
Reviewed-on: https://go-review.googlesource.com/c/go/+/502295
Reviewed-by: David Chase <drchase@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
Run-TryBot: Keith Randall <khr@golang.org>
The compiler/assembler's -S output prints relocation type
numerically, which is hard to understand. Every time I need to
count the relocation type constants to figure out which relocation
it actually is. Print the symbolic name instead.
Change-Id: I4866873bbae8b3dc0ee212609cb00280f9164243
Reviewed-on: https://go-review.googlesource.com/c/go/+/501856
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Than McIntosh <thanm@google.com>
Run-TryBot: Cherry Mui <cherryyz@google.com>
(ANDCCconst [y] (MOV.*reg x)) should only be merged when zero
extending. Otherwise, sign bits are lost on negative values.
(ANDCCconst [0xFF] (MOVBreg x)) should be simplified to a zero
extension of x. Likewise for the MOVHreg variant.
Fixes#61297
Change-Id: I04e4fd7dc6a826e870681f37506620d48393698b
Reviewed-on: https://go-review.googlesource.com/c/go/+/508775
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Paul Murphy <murp@ibm.com>
Reviewed-by: Bryan Mills <bcmills@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
User code is unlikely to be correct, but don't crash the compiler
when the offset of a pointer in an object is not a multiple of the
pointer size.
Fixes#61187
Change-Id: Ie56bfcb38556c5dd6f702ae4ec1d4534c6acd420
Reviewed-on: https://go-review.googlesource.com/c/go/+/508555
Reviewed-by: Cherry Mui <cherryyz@google.com>
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@google.com>
According to RISCV manual 11.6:
FMADD x,y,z computes x*y+z and
FNMADD x,y,z => -x*y-z
FMSUB x,y,z => x*y-z
FNMSUB x,y,z => -x*y+z respectively
However our implement of SSA convert FMADD -x,y,z to FNMADD x,y,z which
is wrong and should be convert to FNMSUB according to manual.
Change-Id: Ib297bc83824e121fd7dda171ed56ea9694a4e575
Reviewed-on: https://go-review.googlesource.com/c/go/+/506575
Run-TryBot: M Zhuo <mzh@golangcn.org>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: David Chase <drchase@google.com>
Reviewed-by: Joedian Reid <joedian@golang.org>
Reviewed-by: Michael Munday <mike.munday@lowrisc.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
The large-function phi placement algorithm evidently doesn't like the
same pseudo-variable being used to represent expressions of varying
types.
Instead, use the same tactic as used for "valVar" (ssa.go:6585--6587),
which is to just generate a fresh marker node each time.
Maybe we could just use the OMIN/OMAX nodes themselves as the key
(like we do for OANDAND/OOROR), but that just seems needlessly risky
for negligible memory savings. Using fresh marker values each time
seems obviously safe by comparison.
Fixes#61041.
Change-Id: Ie2600c9c37b599c2e26ae01f5f8a433025d7fd08
Reviewed-on: https://go-review.googlesource.com/c/go/+/506679
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
