[AMDGPUI][True16][CodeGen] global atomic load i8 in true16 mode (#142822)

Update codegen pattern for global atomic load i8 with d16 instructions

Author: broxigarchen

llvm/lib/Target/AMDGPU/FLATInstructions.td

@@ -1678,15 +1678,12 @@ def : FlatLoadPat_D16 <FLAT_LOAD_SHORT_D16, load_d16_lo_flat, v2f16>;
 let OtherPredicates = [HasFlatGlobalInsts] in {
 
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, atomic_load_aext_8_global, i32>;
-defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, atomic_load_aext_8_global, i16>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, atomic_load_zext_8_global, i32>;
-defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, atomic_load_zext_8_global, i16>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_USHORT, atomic_load_aext_16_global, i32>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_USHORT, atomic_load_nonext_16_global, i16>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_USHORT, atomic_load_zext_16_global, i32>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_USHORT, atomic_load_zext_16_global, i16>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_SBYTE, atomic_load_sext_8_global, i32>;
-defm : GlobalFLATLoadPats <GLOBAL_LOAD_SBYTE, atomic_load_sext_8_global, i16>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, extloadi8_global, i32>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, zextloadi8_global, i32>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_SBYTE, sextloadi8_global, i32>;
@@ -1702,13 +1699,19 @@ defm : GlobalFLATLoadPats <GLOBAL_LOAD_SBYTE, sextloadi8_global, i16>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_SSHORT, atomic_load_sext_16_global, i32>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_USHORT, atomic_load_zext_16_global, i32>;
 defm : GlobalFLATLoadPats <GLOBAL_LOAD_USHORT, load_global, i16>;
+defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, atomic_load_aext_8_global, i16>;
+defm : GlobalFLATLoadPats <GLOBAL_LOAD_UBYTE, atomic_load_zext_8_global, i16>;
+defm : GlobalFLATLoadPats <GLOBAL_LOAD_SBYTE, atomic_load_sext_8_global, i16>;
 }
 
 let OtherPredicates = [HasFlatGlobalInsts, D16PreservesUnusedBits], True16Predicate = UseRealTrue16Insts in {
 defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_UBYTE_D16", extloadi8_global, i16>;
 defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_UBYTE_D16", zextloadi8_global, i16>;
 defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_SBYTE_D16", sextloadi8_global, i16>;
 defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_SHORT_D16", load_global, i16>;
+defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_UBYTE_D16", atomic_load_aext_8_global, i16>;
+defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_UBYTE_D16", atomic_load_zext_8_global, i16>;
+defm : GlobalFLATLoadPats_D16_t16<"GLOBAL_LOAD_SBYTE_D16", atomic_load_sext_8_global, i16>;
 defm : GlobalFLATStorePats_D16_t16<"GLOBAL_STORE_BYTE", truncstorei8_global, i16>;
 defm : GlobalFLATStorePats_D16_t16<"GLOBAL_STORE_SHORT", store_global, i16>;
 } // end OtherPredicates = [HasFlatGlobalInsts, D16PreservesUnusedBits], True16Predicate = UseRealTrue16Insts