Rollup merge of #140034 - RalfJung:simd_select_bitmask-padding, r=workingjubilee

simd_select_bitmask: the 'padding' bits in the mask are just ignored

Fixes https://github.com/rust-lang/rust/issues/137942: we documented simd_select_bitmask to require the 'padding' bits in the mask (the mask can sometimes be longer than the vector; I am referring to these extra bits as 'padding' here)  to be zero, mostly because nobody felt like doing the research for what should be done when they are non-zero. However, codegen is already perfectly happy just ignoring them, so in practice they can have any value. Some of the intrinsic wrappers in stdarch have trouble ensuring that they are zero. So let's just adjust the docs and Miri to permit non-zero 'padding' bits.

Cc ````@Amanieu```` ````@workingjubilee````

5 files changed, 15 insertions, 45 deletions

diff --git a/library/core/src/intrinsics/simd.rs b/library/core/src/intrinsics/simd.rs
index 6afe924f99d..86e3f8509ee 100644
--- a/library/core/src/intrinsics/simd.rs
+++ b/library/core/src/intrinsics/simd.rs
@@ -577,11 +577,9 @@ pub unsafe fn simd_select<M, T>(mask: M, if_true: T, if_false: T) -> T;
 /// For each element, if the bit in `mask` is `1`, select the element from
 /// `if_true`.  If the corresponding bit in `mask` is `0`, select the element from
 /// `if_false`.
+/// The remaining bits of the mask are ignored.
 ///
 /// The bitmask bit order matches `simd_bitmask`.
-///
-/// # Safety
-/// Padding bits must be all zero.
 #[rustc_intrinsic]
 #[rustc_nounwind]
 pub unsafe fn simd_select_bitmask<M, T>(m: M, yes: T, no: T) -> T;
diff --git a/src/tools/miri/src/intrinsics/simd.rs b/src/tools/miri/src/intrinsics/simd.rs
index de5da6ec898..c9250ba1b81 100644
--- a/src/tools/miri/src/intrinsics/simd.rs
+++ b/src/tools/miri/src/intrinsics/simd.rs
@@ -506,7 +506,6 @@ pub trait EvalContextExt<'tcx>: crate::MiriInterpCxExt<'tcx> {
                 };
 
                 let dest_len = u32::try_from(dest_len).unwrap();
-                let bitmask_len = u32::try_from(bitmask_len).unwrap();
                 for i in 0..dest_len {
                     let bit_i = simd_bitmask_index(i, dest_len, this.data_layout().endian);
                     let mask = mask & 1u64.strict_shl(bit_i);
@@ -517,17 +516,7 @@ pub trait EvalContextExt<'tcx>: crate::MiriInterpCxExt<'tcx> {
                     let val = if mask != 0 { yes } else { no };
                     this.write_immediate(*val, &dest)?;
                 }
-                for i in dest_len..bitmask_len {
-                    // If the mask is "padded", ensure that padding is all-zero.
-                    // This deliberately does not use `simd_bitmask_index`; these bits are outside
-                    // the bitmask. It does not matter in which order we check them.
-                    let mask = mask & 1u64.strict_shl(i);
-                    if mask != 0 {
-                        throw_ub_format!(
-                            "a SIMD bitmask less than 8 bits long must be filled with 0s for the remaining bits"
-                        );
-                    }
-                }
+                // The remaining bits of the mask are ignored.
             }
             // Converts a "vector of bool" into a bitmask.
             "bitmask" => {
diff --git a/src/tools/miri/tests/fail/intrinsics/simd-select-bitmask-invalid.rs b/src/tools/miri/tests/fail/intrinsics/simd-select-bitmask-invalid.rs
deleted file mode 100644
index 409098ac3b5..00000000000
--- a/src/tools/miri/tests/fail/intrinsics/simd-select-bitmask-invalid.rs
+++ /dev/null
@@ -1,15 +0,0 @@
-#![feature(core_intrinsics, repr_simd)]
-
-use std::intrinsics::simd::simd_select_bitmask;
-
-#[repr(simd)]
-#[allow(non_camel_case_types)]
-#[derive(Copy, Clone)]
-struct i32x2([i32; 2]);
-
-fn main() {
-    unsafe {
-        let x = i32x2([0, 1]);
-        simd_select_bitmask(0b11111111u8, x, x); //~ERROR: bitmask less than 8 bits long must be filled with 0s for the remaining bits
-    }
-}
diff --git a/src/tools/miri/tests/fail/intrinsics/simd-select-bitmask-invalid.stderr b/src/tools/miri/tests/fail/intrinsics/simd-select-bitmask-invalid.stderr
deleted file mode 100644
index 9acb51d8c5f..00000000000
--- a/src/tools/miri/tests/fail/intrinsics/simd-select-bitmask-invalid.stderr
+++ /dev/null
@@ -1,15 +0,0 @@
-error: Undefined Behavior: a SIMD bitmask less than 8 bits long must be filled with 0s for the remaining bits
-  --> tests/fail/intrinsics/simd-select-bitmask-invalid.rs:LL:CC
-   |
-LL |         simd_select_bitmask(0b11111111u8, x, x);
-   |         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ a SIMD bitmask less than 8 bits long must be filled with 0s for the remaining bits
-   |
-   = help: this indicates a bug in the program: it performed an invalid operation, and caused Undefined Behavior
-   = help: see https://doc.rust-lang.org/nightly/reference/behavior-considered-undefined.html for further information
-   = note: BACKTRACE:
-   = note: inside `main` at tests/fail/intrinsics/simd-select-bitmask-invalid.rs:LL:CC
-
-note: some details are omitted, run with `MIRIFLAGS=-Zmiri-backtrace=full` for a verbose backtrace
-
-error: aborting due to 1 previous error
-
diff --git a/src/tools/miri/tests/pass/intrinsics/portable-simd.rs b/src/tools/miri/tests/pass/intrinsics/portable-simd.rs
index cc753dac215..e14ce51f35a 100644
--- a/src/tools/miri/tests/pass/intrinsics/portable-simd.rs
+++ b/src/tools/miri/tests/pass/intrinsics/portable-simd.rs
@@ -331,6 +331,19 @@ fn simd_mask() {
         );
         assert_eq!(selected1, i32x4::from_array([0, 0, 0, 1]));
         assert_eq!(selected2, selected1);
+        // Non-zero "padding" (the extra bits) is also allowed.
+        let selected1 = simd_select_bitmask::<u8, _>(
+            if cfg!(target_endian = "little") { 0b11111000 } else { 0b11110001 },
+            i32x4::splat(1), // yes
+            i32x4::splat(0), // no
+        );
+        let selected2 = simd_select_bitmask::<[u8; 1], _>(
+            if cfg!(target_endian = "little") { [0b11111000] } else { [0b11110001] },
+            i32x4::splat(1), // yes
+            i32x4::splat(0), // no
+        );
+        assert_eq!(selected1, i32x4::from_array([0, 0, 0, 1]));
+        assert_eq!(selected2, selected1);
     }
 
     // Non-power-of-2 multi-byte mask.