[clang-tools-extra] [llvm] [clang] DAG: Implement promotion for strict_fp_round (PR #74332)

[Phoebe Wang via cfe-commits]

@@ -2621,6 +2642,29 @@ SDValue 
DAGTypeLegalizer::PromoteFloatRes_FP_ROUND(SDNode *N) {
   return DAG.getNode(GetPromotionOpcode(VT, NVT), DL, NVT, Round);
 }
 
+// Explicit operation to reduce precision.  Reduce the value to half precision
+// and promote it back to the legal type.
+SDValue DAGTypeLegalizer::PromoteFloatRes_STRICT_FP_ROUND(SDNode *N) {

phoebewang wrote:

Why we need this given we have a handler here 
https://github.com/llvm/llvm-project/blob/main/llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp#L2996-L3003

https://github.com/llvm/llvm-project/pull/74332
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang-tools-extra] [llvm] [clang] DAG: Implement promotion for strict_fp_round (PR #74332)

[Matt Arsenault via cfe-commits]

@@ -1097,7 +1097,7 @@ def : Pat <
 multiclass f16_fp_Pats {
   // f16_to_fp patterns
   def : GCNPat <
-(f32 (f16_to_fp i32:$src0)),
+(f32 (any_f16_to_fp i32:$src0)),

arsenm wrote:

Yes, with appropriate tests added alongside it 

https://github.com/llvm/llvm-project/pull/74332
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang-tools-extra] [llvm] [clang] DAG: Implement promotion for strict_fp_round (PR #74332)

[Phoebe Wang via cfe-commits]

@@ -1097,7 +1097,7 @@ def : Pat <
 multiclass f16_fp_Pats {
   // f16_to_fp patterns
   def : GCNPat <
-(f32 (f16_to_fp i32:$src0)),
+(f32 (any_f16_to_fp i32:$src0)),

phoebewang wrote:

Should we replace more `f16_to_fp` to `any_f16_to_fp` in this file and other 
target files?

https://github.com/llvm/llvm-project/pull/74332
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits