diff options
| author | bors <bors@rust-lang.org> | 2023-10-06 08:04:53 +0000 |
|---|---|---|
| committer | bors <bors@rust-lang.org> | 2023-10-06 08:04:53 +0000 |
| commit | d4ba2b4c7c938cf90c03a265cb31356537f608ad (patch) | |
| tree | a23f402b29354f4c6b415c0bd0f7c68b33a2cf96 | |
| parent | ff057893b8a2f20de2ff258ed8690f5a42fed78a (diff) | |
| parent | e300847864faf93538354b418da0a1612efd36f4 (diff) | |
| download | rust-d4ba2b4c7c938cf90c03a265cb31356537f608ad.tar.gz rust-d4ba2b4c7c938cf90c03a265cb31356537f608ad.zip | |
Auto merge of #116018 - DianQK:simd-wide-sum-test, r=scottmcm
Increasing the SIMD size improves the vectorization possibilities Change the `simd-wide-sum.rs` to pass tests based on the LLVM main branch. For smaller lengths, we cannot expect to always get vectorized. A related discussion at https://rust-lang.zulipchat.com/#narrow/stream/187780-t-compiler.2Fwg-llvm/topic/LLVM.20HEAD.3A.20codegen.2Fsimd.2Fsimd-wide-sum.2Ers.20newly.20failing. r? scottmcm
| -rw-r--r-- | tests/codegen/simd/simd-wide-sum.rs | 26 |
1 files changed, 13 insertions, 13 deletions
diff --git a/tests/codegen/simd/simd-wide-sum.rs b/tests/codegen/simd/simd-wide-sum.rs index 3116f9597bc..6e7d3d9316a 100644 --- a/tests/codegen/simd/simd-wide-sum.rs +++ b/tests/codegen/simd/simd-wide-sum.rs @@ -11,14 +11,14 @@ #![feature(portable_simd)] use std::simd::{Simd, SimdUint}; -const N: usize = 8; +const N: usize = 16; #[no_mangle] // CHECK-LABEL: @wider_reduce_simd pub fn wider_reduce_simd(x: Simd<u8, N>) -> u16 { - // CHECK: zext <8 x i8> - // CHECK-SAME: to <8 x i16> - // CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> + // CHECK: zext <16 x i8> + // CHECK-SAME: to <16 x i16> + // CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> let x: Simd<u16, N> = x.cast(); x.reduce_sum() } @@ -26,9 +26,9 @@ pub fn wider_reduce_simd(x: Simd<u8, N>) -> u16 { #[no_mangle] // CHECK-LABEL: @wider_reduce_loop pub fn wider_reduce_loop(x: Simd<u8, N>) -> u16 { - // CHECK: zext <8 x i8> - // CHECK-SAME: to <8 x i16> - // CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> + // CHECK: zext <16 x i8> + // CHECK-SAME: to <16 x i16> + // CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> let mut sum = 0_u16; for i in 0..N { sum += u16::from(x[i]); @@ -39,9 +39,9 @@ pub fn wider_reduce_loop(x: Simd<u8, N>) -> u16 { #[no_mangle] // CHECK-LABEL: @wider_reduce_iter pub fn wider_reduce_iter(x: Simd<u8, N>) -> u16 { - // CHECK: zext <8 x i8> - // CHECK-SAME: to <8 x i16> - // CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> + // CHECK: zext <16 x i8> + // CHECK-SAME: to <16 x i16> + // CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> x.as_array().iter().copied().map(u16::from).sum() } @@ -52,8 +52,8 @@ pub fn wider_reduce_iter(x: Simd<u8, N>) -> u16 { #[no_mangle] // CHECK-LABEL: @wider_reduce_into_iter pub fn wider_reduce_into_iter(x: Simd<u8, N>) -> u16 { - // CHECK: zext <8 x i8> - // CHECK-SAME: to <8 x i16> - // CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> + // FIXME: It would be nice if this was exactly the same as the above tests, + // but at the time of writing this comment, that didn't happen on LLVM main. + // CHECK: call i16 @llvm.vector.reduce.add x.to_array().into_iter().map(u16::from).sum() } |