[PATCH] D104427: [amdgpu] Improve the from f32 to i64.

[Jay Foad via Phabricator via llvm-commits]

foad added a reviewer: foad.
foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2594
 
-SDValue AMDGPUTargetLowering::LowerFP64_TO_INT(SDValue Op, SelectionDAG &DAG,
-                                               bool Signed) const {
+SDValue AMDGPUTargetLowering::LowerFP3264_TO_INT(SDValue Op, SelectionDAG &DAG,
+                                                 bool Signed) const {
----------------
`LowerFP_TO_INT64` might be a better name?


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2614
+  SDValue Sign;
+  if (SrcVT == MVT::f32) {
+    // However, a 32-bit floating point number has only 23 bits mantissa and
----------------
Only do this if `Signed`?


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2653
+
+  if (SrcVT == MVT::f32) {
+    assert(Sign);
----------------
Only do this if `Signed`?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D104427/new/

https://reviews.llvm.org/D104427