Rollup merge of #133395 - calebzulawski:simd_relaxed_fma, r=workingjubilee

Add simd_relaxed_fma intrinsic

Adds compiler support for https://github.com/rust-lang/portable-simd/issues/387#issuecomment-2337169786

r? `@workingjubilee`

cc `@RalfJung` is this kind of nondeterminism a problem for miri/opsem?

compiler/rustc_codegen_cranelift/src/intrinsics/simd.rs

@@ -415,7 +415,8 @@ pub(super) fn codegen_simd_intrinsic_call<'tcx>(
             });
         }
 
-        sym::simd_fma => {
+        // FIXME: simd_relaxed_fma doesn't relax to non-fused multiply-add
+        sym::simd_fma | sym::simd_relaxed_fma => {
             intrinsic_args!(fx, args => (a, b, c); intrinsic);
 
             if !a.layout().ty.is_simd() {

compiler/rustc_codegen_gcc/src/intrinsic/simd.rs

@@ -772,6 +772,7 @@ pub fn generic_simd_intrinsic<'a, 'gcc, 'tcx>(
             sym::simd_flog => "log",
             sym::simd_floor => "floor",
             sym::simd_fma => "fma",
+            sym::simd_relaxed_fma => "fma", // FIXME: this should relax to non-fused multiply-add when necessary
             sym::simd_fpowi => "__builtin_powi",
             sym::simd_fpow => "pow",
             sym::simd_fsin => "sin",

compiler/rustc_codegen_llvm/src/intrinsic.rs

@@ -1534,6 +1534,7 @@ fn generic_simd_intrinsic<'ll, 'tcx>(
             sym::simd_flog => ("log", bx.type_func(&[vec_ty], vec_ty)),
             sym::simd_floor => ("floor", bx.type_func(&[vec_ty], vec_ty)),
             sym::simd_fma => ("fma", bx.type_func(&[vec_ty, vec_ty, vec_ty], vec_ty)),
+            sym::simd_relaxed_fma => ("fmuladd", bx.type_func(&[vec_ty, vec_ty, vec_ty], vec_ty)),
             sym::simd_fpowi => ("powi", bx.type_func(&[vec_ty, bx.type_i32()], vec_ty)),
             sym::simd_fpow => ("pow", bx.type_func(&[vec_ty, vec_ty], vec_ty)),
             sym::simd_fsin => ("sin", bx.type_func(&[vec_ty], vec_ty)),
@@ -1572,6 +1573,7 @@ fn generic_simd_intrinsic<'ll, 'tcx>(
             | sym::simd_fpowi
             | sym::simd_fsin
             | sym::simd_fsqrt
+            | sym::simd_relaxed_fma
             | sym::simd_round
             | sym::simd_trunc
     ) {

compiler/rustc_hir_analysis/src/check/intrinsic.rs

@@ -641,7 +641,9 @@ pub fn check_intrinsic_type(
             | sym::simd_round
             | sym::simd_trunc => (1, 0, vec![param(0)], param(0)),
             sym::simd_fpowi => (1, 0, vec![param(0), tcx.types.i32], param(0)),
-            sym::simd_fma => (1, 0, vec![param(0), param(0), param(0)], param(0)),
+            sym::simd_fma | sym::simd_relaxed_fma => {
+                (1, 0, vec![param(0), param(0), param(0)], param(0))
+            }
             sym::simd_gather => (3, 0, vec![param(0), param(1), param(2)], param(0)),
             sym::simd_masked_load => (3, 0, vec![param(0), param(1), param(2)], param(2)),
             sym::simd_masked_store => (3, 0, vec![param(0), param(1), param(2)], tcx.types.unit),

compiler/rustc_span/src/symbol.rs

@@ -1844,6 +1844,7 @@ symbols! {
         simd_reduce_mul_unordered,
         simd_reduce_or,
         simd_reduce_xor,
+        simd_relaxed_fma,
         simd_rem,
         simd_round,
         simd_saturating_add,

library/core/src/intrinsics/simd.rs

@@ -612,6 +612,20 @@ extern "rust-intrinsic" {
     #[rustc_nounwind]
     pub fn simd_fma<T>(x: T, y: T, z: T) -> T;
 
+    /// Computes `(x*y) + z` for each element, non-deterministically executing either
+    /// a fused multiply-add or two operations with rounding of the intermediate result.
+    ///
+    /// The operation is fused if the code generator determines that target instruction
+    /// set has support for a fused operation, and that the fused operation is more efficient
+    /// than the equivalent, separate pair of mul and add instructions. It is unspecified
+    /// whether or not a fused operation is selected, and that may depend on optimization
+    /// level and context, for example.
+    ///
+    /// `T` must be a vector of floats.
+    #[cfg(not(bootstrap))]
+    #[rustc_nounwind]
+    pub fn simd_relaxed_fma<T>(x: T, y: T, z: T) -> T;
+
     // Computes the sine of each element.
     ///
     /// `T` must be a vector of floats.

tests/ui/simd/intrinsic/float-math-pass.rs

@@ -23,6 +23,7 @@ extern "rust-intrinsic" {
     fn simd_fexp<T>(x: T) -> T;
     fn simd_fexp2<T>(x: T) -> T;
     fn simd_fma<T>(x: T, y: T, z: T) -> T;
+    fn simd_relaxed_fma<T>(x: T, y: T, z: T) -> T;
     fn simd_flog<T>(x: T) -> T;
     fn simd_flog10<T>(x: T) -> T;
     fn simd_flog2<T>(x: T) -> T;
@@ -77,6 +78,9 @@ fn main() {
         let r = simd_fma(x, h, h);
         assert_approx_eq!(x, r);
 
+        let r = simd_relaxed_fma(x, h, h);
+        assert_approx_eq!(x, r);
+
         let r = simd_fsqrt(x);
         assert_approx_eq!(x, r);