================
@@ -959,6 +967,32 @@ def : GCNPat <
}
} // let OtherPredicates = [HasShaderCyclesRegister]
+def SIMM24bitPtr : ImmLeaf <iPTR,
+ [{return isInt<24>(Imm);}]
+>;
+
+multiclass SMPrefetchPat<string type, int cache_type> {
+ def : GCNPat <
+ (smrd_prefetch (SMRDImm i64:$sbase, i32:$offset), timm, timm, (i32
cache_type)),
+ (!cast<SM_Prefetch_Pseudo>("S_PREFETCH_"#type) $sbase, $offset, (i32
SGPR_NULL), (i8 0))
+ >;
+
+ def : GCNPat <
+ (smrd_prefetch (i64 SReg_64:$sbase), timm, timm, (i32 cache_type)),
+ (!cast<SM_Prefetch_Pseudo>("S_PREFETCH_"#type) $sbase, 0, (i32 SGPR_NULL),
(i8 0))
+ >;
+
+ def : GCNPat <
+ (prefetch SIMM24bitPtr:$offset, timm, timm, (i32 cache_type)),
+ (!cast<SM_Prefetch_Pseudo>("S_PREFETCH_"#type#"_PC_REL") (as_i32timm
$offset), (i32 SGPR_NULL), (i8 0))
+ > {
+ let AddedComplexity = 10;
+ }
----------------
rampitec wrote:
I do not think we need to use PC_REL form to prefetch on a function's address.
The instruction can take full 64-bit address, so one can just use this address.
My understanding that PC_REL form can be useful if you expect something like a
huge loop or a local branch and want to prefetch something like 1K from the PC.
I am not sure though how useful this can be at a high language level or even in
IR.
https://github.com/llvm/llvm-project/pull/74576
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
