[clang] [llvm] [AArch64][SME] Add intrinsics for multi-vector BFCLAMP (PR #88251)
Momchil Velikov via cfe-commits
cfe-commits at lists.llvm.org
Wed Apr 10 06:17:52 PDT 2024
================
@@ -2148,6 +2148,11 @@ let TargetGuard = "sme2" in {
def SVSCLAMP_X4 : SInst<"svclamp[_single_{d}_x4]", "44dd", "csil", MergeNone, "aarch64_sve_sclamp_single_x4", [IsStreaming], []>;
def SVUCLAMP_X4 : SInst<"svclamp[_single_{d}_x4]", "44dd", "UcUsUiUl", MergeNone, "aarch64_sve_uclamp_single_x4", [IsStreaming], []>;
def SVFCLAMP_X4 : SInst<"svclamp[_single_{d}_x4]", "44dd", "hfd", MergeNone, "aarch64_sve_fclamp_single_x4", [IsStreaming], []>;
+
+ let TargetGuard = "b16b16"in {
----------------
momchil-velikov wrote:
I does not work. A test for target features (in `Sema`) would catch that.
https://github.com/llvm/llvm-project/pull/88251
More information about the cfe-commits
mailing list