================
@@ -1548,6 +1548,45 @@ let TargetPrefix = "nvvm" in {
Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
def int_nvvm_e5m2x2_to_f16x2_rn_relu :
ClangBuiltin<"__nvvm_e5m2x2_to_f16x2_rn_relu">,
Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
+
+ def int_nvvm_ff_to_e2m3x2_rn : ClangBuiltin<"__nvvm_ff_to_e2m3x2_rn">,
+ Intrinsic<[llvm_i16_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem,
IntrNoCallback]>;
+ def int_nvvm_ff_to_e2m3x2_rn_relu :
ClangBuiltin<"__nvvm_ff_to_e2m3x2_rn_relu">,
+ Intrinsic<[llvm_i16_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem,
IntrNoCallback]>;
+ def int_nvvm_ff_to_e3m2x2_rn : ClangBuiltin<"__nvvm_ff_to_e3m2x2_rn">,
+ Intrinsic<[llvm_i16_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem,
IntrNoCallback]>;
+ def int_nvvm_ff_to_e3m2x2_rn_relu :
ClangBuiltin<"__nvvm_ff_to_e3m2x2_rn_relu">,
+ Intrinsic<[llvm_i16_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem,
IntrNoCallback]>;
+
+ def int_nvvm_e2m3x2_to_f16x2_rn : ClangBuiltin<"__nvvm_e2m3x2_to_f16x2_rn">,
+ Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
+ def int_nvvm_e2m3x2_to_f16x2_rn_relu :
ClangBuiltin<"__nvvm_e2m3x2_to_f16x2_rn_relu">,
+ Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
+ def int_nvvm_e3m2x2_to_f16x2_rn : ClangBuiltin<"__nvvm_e3m2x2_to_f16x2_rn">,
+ Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
+ def int_nvvm_e3m2x2_to_f16x2_rn_relu :
ClangBuiltin<"__nvvm_e3m2x2_to_f16x2_rn_relu">,
+ Intrinsic<[llvm_v2f16_ty], [llvm_i16_ty], [IntrNoMem, IntrNoCallback]>;
----------------
durga4github wrote:
optional:
We may combine this chunk with the e4m3/e5m2 conversions above since they all
take an i16 and return v2f16, to reduce the verbosity. But this can be a
separate NFC change.
https://github.com/llvm/llvm-project/pull/134345
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
