[clang] [llvm] [X86][AVX10.2] Support AVX10.2-BF16 new instructions. (PR #101603)
Freddy Ye via cfe-commits
cfe-commits at lists.llvm.org
Thu Aug 29 01:26:39 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> {
+ let Predicates = [HasAVX10_2_512] in
+ defm PBF16Z : avx512_fp_packed<opc, OpcodeStr,
----------------
FreddyLeaf wrote:
[7957436](https://github.com/llvm/llvm-project/pull/101603/commits/7957436ac07d1902f3f510de756577c00353dd02)
https://github.com/llvm/llvm-project/pull/101603
More information about the cfe-commits
mailing list