Rollup merge of #118864 - farnoy:masked-load-store-fixes, r=workingjubilee

Fix alignment passed down to LLVM for simd_masked_load

Follow up to #117953

The alignment for a masked load operation should be that of the element/lane, not the vector as a whole

It can produce miscompilations after the LLVM optimizer notices the higher alignment and promotes this to an unmasked, aligned load followed up by blend/select - https://rust.godbolt.org/z/KEeGbevbb

Author: workingjubilee

compiler/rustc_codegen_llvm/src/intrinsic.rs

@@ -1568,7 +1568,7 @@ fn generic_simd_intrinsic<'ll, 'tcx>(
 
         // Alignment of T, must be a constant integer value:
         let alignment_ty = bx.type_i32();
-        let alignment = bx.const_i32(bx.align_of(values_ty).bytes() as i32);
+        let alignment = bx.const_i32(bx.align_of(values_elem).bytes() as i32);
 
         // Truncate the mask vector to a vector of i1s:
         let (mask, mask_ty) = {

tests/codegen/simd-intrinsic/simd-intrinsic-generic-masked-load.rs

@@ -21,7 +21,7 @@ extern "platform-intrinsic" {
 #[no_mangle]
 pub unsafe fn load_f32x2(mask: Vec2<i32>, pointer: *const f32,
                          values: Vec2<f32>) -> Vec2<f32> {
-    // CHECK: call <2 x float> @llvm.masked.load.v2f32.p0(ptr {{.*}}, i32 {{.*}}, <2 x i1> {{.*}}, <2 x float> {{.*}})
+    // CHECK: call <2 x float> @llvm.masked.load.v2f32.p0(ptr {{.*}}, i32 4, <2 x i1> {{.*}}, <2 x float> {{.*}})
     simd_masked_load(mask, pointer, values)
 }
 

tests/codegen/simd-intrinsic/simd-intrinsic-generic-masked-store.rs

@@ -20,7 +20,7 @@ extern "platform-intrinsic" {
 // CHECK-LABEL: @store_f32x2
 #[no_mangle]
 pub unsafe fn store_f32x2(mask: Vec2<i32>, pointer: *mut f32, values: Vec2<f32>) {
-    // CHECK: call void @llvm.masked.store.v2f32.p0(<2 x float> {{.*}}, ptr {{.*}}, i32 {{.*}}, <2 x i1> {{.*}})
+    // CHECK: call void @llvm.masked.store.v2f32.p0(<2 x float> {{.*}}, ptr {{.*}}, i32 4, <2 x i1> {{.*}})
     simd_masked_store(mask, pointer, values)
 }