From 56253d9e31c0576f024d95929a8fe26428b35176 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Motiejus=20Jak=C5=A1tys?= <motiejus@jakstys.lt>
Date: Sun, 15 Feb 2026 20:41:19 +0000
Subject: [PATCH] x86_64 codegen: fix RoundMode vroundss immediate value

Quoting Vol. 2B 4-590 of [Intel SSA manual][1]:

> Bit 3 of the immediate byte controls processor behavior for a
precision exception <...>

The Direction struct is incorrectly sized to 4 bits, which pushes the
precision exception bit to the reserved bits, which helpfully crashes
under valgrind (but works on real hardware, since CPU ignores it):

``
const std = @import("std");

noinline fn ceil(x: f32) f32 {
    return @ceil(x);
}

test "ceil" {
    try std.testing.expectEqual(@as(f32, 2.0), ceil(1.5));
}
```

With Zig 0.15.1:

```
$ zig test -fno-llvm -mcpu x86_64_v3  -fvalgrind  ceil_test.zig  --test-cmd valgrind --test-cmd --quiet --test-cmd-bin
Illegal instruction at address 0x102d14d
/home/motiejus/code/ceil_test.zig:4:5: 0x102d14d in ceil (ceil_test.zig)
    return @ceil(x);
    ^
/home/motiejus/code/ceil_test.zig:8:52: 0x102d097 in test.ceil (ceil_test.zig)
    try std.testing.expectEqual(@as(f32, 2.0), ceil(1.5));
                                                   ^
/nix/store/n81qdpd96d86ngfv5bqymy26b8kqm654-zig-0.15.1/lib/compiler/test_runner.zig:218:25: 0x1167e80 in mainTerminal (test_runner.zig)
        if (test_fn.func()) |_| {
                        ^
/nix/store/n81qdpd96d86ngfv5bqymy26b8kqm654-zig-0.15.1/lib/compiler/test_runner.zig:66:28: 0x11610a1 in main (test_runner.zig)
        return mainTerminal();
                           ^
/nix/store/n81qdpd96d86ngfv5bqymy26b8kqm654-zig-0.15.1/lib/std/start.zig:618:22: 0x115ae3d in posixCallMainAndExit (std.zig)
            root.main();
                     ^
/nix/store/n81qdpd96d86ngfv5bqymy26b8kqm654-zig-0.15.1/lib/std/start.zig:232:5: 0x115a6d1 in _start (std.zig)
    asm volatile (switch (native_arch) {
    ^
???:?:?: 0x0 in ??? (???)
error: the following test command crashed:
valgrind --quiet /home/motiejus/.cache/zig/o/7cc564b5410fc3facdb6e8768643074e/test
```

Zig 0.15.1 with this patch:

```
zig/zig3 test -fno-llvm -mcpu x86_64_v3  -fvalgrind  ceil_test.zig  --test-cmd valgrind --test-cmd --quiet --test-cmd-bin
All 1 tests passed.
```

Looking through `CodeGen.zig` it _seems_ like the same RoundMode struct
is used for vroundss/vroundps/vcvtps2ph, so update the comment while
we're at it. But I am only 90% sure it's true.

[1]: https://cdrdv2.intel.com/v1/dl/getContent/671200
---
 src/codegen/x86_64/bits.zig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/codegen/x86_64/bits.zig b/src/codegen/x86_64/bits.zig
index 05048109335e0256d91c5f350d7fa900ce08e402..452518e14e90c40c14aebc4f0718f89bc31dc338 100644
--- a/src/codegen/x86_64/bits.zig
+++ b/src/codegen/x86_64/bits.zig
@@ -178,15 +178,15 @@ pub const Condition = enum(u5) {
     }
 };
 
-/// The immediate operand of vcvtps2ph.
-pub const RoundMode = packed struct(u5) {
+/// The immediate operand of vroundss/vroundps/vcvtps2ph/round??.
+pub const RoundMode = packed struct(u4) {
     direction: Direction = .mxcsr,
     precision: enum(u1) {
         normal = 0b0,
         inexact = 0b1,
     } = .normal,
 
-    pub const Direction = enum(u4) {
+    pub const Direction = enum(u3) {
         /// Round to nearest (even)
         nearest = 0b0_00,
         /// Round down (toward -∞)
-- 
2.54.0