[clang] [llvm] [X86][AVX10.2] Support AVX10.2-BF16 new instructions. (PR #101603)

Phoebe Wang via llvm-commits llvm-commits at lists.llvm.org
Tue Aug 27 06:50:37 PDT 2024


================
@@ -910,3 +910,313 @@ multiclass avx10_convert_2op_nomb<string OpcodeStr, AVX512VLVectorVTInfo _dest,
 defm VCVTHF82PH : avx10_convert_2op_nomb<"vcvthf82ph", avx512vl_f16_info,
                                          avx512vl_i8_info, 0x1e, X86vcvthf82ph>,
                   AVX512XDIi8Base, T_MAP5, EVEX, EVEX_CD8<16, CD8VH>;
+
+//-------------------------------------------------
+// AVX10 BF16 instructions
+//-------------------------------------------------
+
+// VADDNEPBF16, VSUBNEPBF16, VMULNEPBF16, VDIVNEPBF16, VMAXPBF16, VMINPBF16
+multiclass avx10_fp_binopne_int_pbf16<bits<8> opc, string OpcodeStr,
+                   X86SchedWriteSizes sched,
+                   bit IsCommutable = 0> {
----------------
phoebewang wrote:

Align within `<`

https://github.com/llvm/llvm-project/pull/101603


More information about the llvm-commits mailing list