* introduce std.atomic.Int
* add src-self-hosted/test.zig which is tested by the main test suite
- it fully utilizes the multithreaded async/await event loop so the
tests should Go Fast
* `stage2/bin/zig build-obj test.zig` is able to spit out an error if 2 exported
functions collide
* ability for `zig test` to accept `--object` and `--assembly`
arguments
* std.build: TestStep supports addLibPath and addObjectFile
* add std.atomic.QueueMpsc.isEmpty
* make std.debug.global_allocator thread-safe
* std.event.Loop: now you have to choose between
- initSingleThreaded
- initMultiThreaded
* std.event.Loop multiplexes coroutines onto kernel threads
* Remove std.event.Loop.stop. Instead the event loop run() function
returns once there are no pending coroutines.
* fix crash in ir.cpp for calling methods under some conditions
* small progress self-hosted compiler, analyzing top level declarations
* Introduce std.event.Lock for synchronizing coroutines
* introduce std.event.Locked(T) for data that only 1 coroutine should
modify at once.
* make the self hosted compiler use multi threaded event loop
* make std.heap.DirectAllocator thread-safe
See #174
TODO:
* call sched_getaffinity instead of hard coding thread pool size 4
* support for Windows and MacOS
* #1194
* #1197
This strategy adds another field to the SwitchBr instruction,
which is the result of the CheckSwitchProngs instruction. The
type of the result is void, and is unused, except that the SwitchBr
instruction will not perform analysis if the CheckSwitchProngs
instruction did not pass analysis. This allows the CheckSwitchProngs
instruction to do implicit casting for its type checking, while
preventing duplicate compile error messages.
previously, await on an early return would try to access the
destroyed coroutine frame; now it copies the result into a
temporary variable before destroying the coroutine frame
Support the `--emit` switch in `zig --emit asm test file.zig`.
The command fails because no tests run (no executable is created) but
it emits the requested file. That seems like a good tradeoff.
Add support for half-precision floating point operations.
Introduce `__extendhfsf2` and `__truncsfhf2` in std/special/compiler_rt.
Add `__gnu_h2f_ieee` and `__gnu_f2h_ieee` as aliases that are used in
Windows builds.
The logic in std/special/compiler_rt/extendXfYf2.zig has been reworked
and can now operate on 16 bits floating point types.
`extendXfYf2()` and `truncXfYf2()` are marked `inline` to work around
a not entirely understood stack alignment issue on Windows when calling
the f16 versions of the builtins.
closes#1122
The modulo operation computed rem(b+rem(a,b), b) which produces -1
for a=1 and b=2.
Switch to a - b * trunc(a/b) which produces the expected result, 1.
closes#1137
when the integer part does not fit in the destination integer type
* Also fix incorrect safety triggered for integer casting an
`i32` to a `u7`. closes#1138
* adds compiler-rt function: `__floatuntidf`
Issue: https://github.com/ziglang/zig/issues/1117
The macOS stage1 Zig compiler should look in Zig's real absolute path
for the Zig stdlib, but os_self_exe_path looks in its path as returned
by _NSGetExecutablePath, which may be a symlink. This means that a
symlinked Zig cannot find the Zig stdlib.
This patch fixes the issue by resolving the _NSGetExecutablePath result
to the real path using realpath() before copying the result to the
output path.
Add wasm32 support to the build-obj, build-exe and build-lib commands
of the stage 1 compiler. Wasm64 should work transparently once it's
supported in upstream LLVM.
To export a function:
// lib.zig - for exposition, not necessary for this example
pub use @import("add.zig");
// add.zig
export fn add(a: i32, b: i32) i32 {
return a + b;
}
To import a function:
// cube.zig
extern fn square(x: i32) i32;
export fn cube(x: i32) i32 {
return x * square(x);
}
any *T -> ?*T cast is allowed implicitly, even
when it occurs deep inside the type, and the cast
is a no-op at runtime.
in order to add this I had to make the comptime value
representation of nullable pointers the same as the
comptime value representation of normal pointers,
so that we don't have to do any recursive transformation
of values when doing this kind of cast.
Now, if a struct has any fields which require comptime,
such as `type`, then the struct is marked as requiring
comptime as well. Same goes for unions.
This means that a function will implicitly be called
at comptime if the return type is a struct which contains
a field of type `type`.
closes#586
* add assertion for trying to do @typeInfo on global error set
* remove TypeInfo.Slice
* add TypeInfo.Pointer.Size with possible values
- One
- Many
- Slice
See #770
