ISimdVector issue (GVM resolution doesn't report [Intrinsic]?) #93174
Description
[MethodImpl(MethodImplOptions.NoInlining)]
private static bool Foo1<TVector>(ref int t1, ref int t2)
where TVector : struct, ISimdVector<TVector, int>
{
TVector vec1 = TVector.LoadUnsafe(ref t1);
TVector vec2 = TVector.LoadUnsafe(ref t2);
return vec1 == vec2;
}
[MethodImpl(MethodImplOptions.NoInlining)]
private static bool Foo2<TVector>(ref int t1, ref int t2)
where TVector : struct, ISimdVector<TVector, int>
{
TVector vec1 = TVector.LoadUnsafe(ref t1);
TVector vec2 = TVector.LoadUnsafe(ref t2);
return vec1.Equals(vec2);
}Current codegen for FooX<Vector128<int>>(...):
; Assembly listing for method Foo1
G_M44695_IG01: ;; offset=0x0000
sub rsp, 72
vzeroupper
G_M44695_IG02: ;; offset=0x0007
vmovups xmm0, xmmword ptr [rcx]
vmovaps xmmword ptr [rsp+0x30], xmm0
vmovups xmm0, xmmword ptr [rdx]
vmovaps xmmword ptr [rsp+0x20], xmm0
mov rax, qword ptr [rsp+0x30]
mov qword ptr [rsp+0x18], rax
mov rax, qword ptr [rsp+0x20]
mov qword ptr [rsp+0x10], rax
mov eax, dword ptr [rsp+0x18]
cmp dword ptr [rsp+0x10], eax
jne SHORT G_M44695_IG08
G_M44695_IG03: ;; offset=0x0039
mov eax, dword ptr [rsp+0x1C]
cmp dword ptr [rsp+0x14], eax
jne SHORT G_M44695_IG08
G_M44695_IG04: ;; offset=0x0043
mov rax, qword ptr [rsp+0x38]
mov qword ptr [rsp+0x08], rax
mov rax, qword ptr [rsp+0x28]
mov qword ptr [rsp], rax
mov eax, dword ptr [rsp+0x08]
cmp dword ptr [rsp], eax
jne SHORT G_M44695_IG06
G_M44695_IG05: ;; offset=0x005F
mov eax, dword ptr [rsp+0x0C]
cmp dword ptr [rsp+0x04], eax
jne SHORT G_M44695_IG06
mov eax, 1
jmp SHORT G_M44695_IG07
G_M44695_IG06: ;; offset=0x0070
xor eax, eax
G_M44695_IG07: ;; offset=0x0072
jmp SHORT G_M44695_IG09
G_M44695_IG08: ;; offset=0x0074
xor eax, eax
G_M44695_IG09: ;; offset=0x0076
add rsp, 72
ret
; Total bytes of code 123
; Assembly listing for method Foo2
G_M34100_IG01: ;; offset=0x0000
vzeroupper
G_M34100_IG02: ;; offset=0x0003
vmovups xmm0, xmmword ptr [rcx]
vpcmpd k1, xmm0, xmmword ptr [rdx], 4
kortestb k1, k1
sete al
movzx rax, al
G_M34100_IG03: ;; offset=0x0018
ret
; Total bytes of code 25Both Foo1 and Foo2 are expected to produce the same codegen. It looks like vec1 == vec2; was inlined into slow path of Vector128.op_Equality as if [Intrinsic] didn't exist on it. Equals works fine because it's a non-Intrinsic wrapper around intrinsic ==.
cc @tannergooding @dotnet/jit-contrib
We need to fix this issue before we start adopting ISimdVector