This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGc4bc416418a2: [LLVM] Add rcp.approx.ftz.f32 intrinsic
(authored by csigg).
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D126369/new/
https://reviews.llvm.org/D126369
Files:
clang/include/clang/Basic/BuiltinsNVPTX.def
llvm/include/llvm/IR/IntrinsicsNVVM.td
llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
Index: llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
===================================================================
--- llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
+++ llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
@@ -1034,6 +1034,8 @@
def INT_NVVM_RCP_RP_D : F_MATH_1<"rcp.rp.f64 \t$dst, $src0;", Float64Regs,
Float64Regs, int_nvvm_rcp_rp_d>;
+def INT_NVVM_RCP_APPROX_FTZ_F : F_MATH_1<"rcp.approx.ftz.f32 \t$dst, $src0;",
+ Float32Regs, Float32Regs, int_nvvm_rcp_approx_ftz_f>;
def INT_NVVM_RCP_APPROX_FTZ_D : F_MATH_1<"rcp.approx.ftz.f64 \t$dst, $src0;",
Float64Regs, Float64Regs, int_nvvm_rcp_approx_ftz_d>;
Index: llvm/include/llvm/IR/IntrinsicsNVVM.td
===================================================================
--- llvm/include/llvm/IR/IntrinsicsNVVM.td
+++ llvm/include/llvm/IR/IntrinsicsNVVM.td
@@ -933,6 +933,8 @@
def int_nvvm_rcp_rp_d : GCCBuiltin<"__nvvm_rcp_rp_d">,
DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+ def int_nvvm_rcp_approx_ftz_f : GCCBuiltin<"__nvvm_rcp_approx_ftz_f">,
+ DefaultAttrsIntrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
def int_nvvm_rcp_approx_ftz_d : GCCBuiltin<"__nvvm_rcp_approx_ftz_d">,
DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
Index: clang/include/clang/Basic/BuiltinsNVPTX.def
===================================================================
--- clang/include/clang/Basic/BuiltinsNVPTX.def
+++ clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -343,6 +343,8 @@
BUILTIN(__nvvm_rcp_rz_d, "dd", "")
BUILTIN(__nvvm_rcp_rm_d, "dd", "")
BUILTIN(__nvvm_rcp_rp_d, "dd", "")
+
+BUILTIN(__nvvm_rcp_approx_ftz_f, "ff", "")
BUILTIN(__nvvm_rcp_approx_ftz_d, "dd", "")
// Sqrt
Index: llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
===================================================================
--- llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
+++ llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
@@ -1034,6 +1034,8 @@
def INT_NVVM_RCP_RP_D : F_MATH_1<"rcp.rp.f64 \t$dst, $src0;", Float64Regs,
Float64Regs, int_nvvm_rcp_rp_d>;
+def INT_NVVM_RCP_APPROX_FTZ_F : F_MATH_1<"rcp.approx.ftz.f32 \t$dst, $src0;",
+ Float32Regs, Float32Regs, int_nvvm_rcp_approx_ftz_f>;
def INT_NVVM_RCP_APPROX_FTZ_D : F_MATH_1<"rcp.approx.ftz.f64 \t$dst, $src0;",
Float64Regs, Float64Regs, int_nvvm_rcp_approx_ftz_d>;
Index: llvm/include/llvm/IR/IntrinsicsNVVM.td
===================================================================
--- llvm/include/llvm/IR/IntrinsicsNVVM.td
+++ llvm/include/llvm/IR/IntrinsicsNVVM.td
@@ -933,6 +933,8 @@
def int_nvvm_rcp_rp_d : GCCBuiltin<"__nvvm_rcp_rp_d">,
DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+ def int_nvvm_rcp_approx_ftz_f : GCCBuiltin<"__nvvm_rcp_approx_ftz_f">,
+ DefaultAttrsIntrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
def int_nvvm_rcp_approx_ftz_d : GCCBuiltin<"__nvvm_rcp_approx_ftz_d">,
DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
Index: clang/include/clang/Basic/BuiltinsNVPTX.def
===================================================================
--- clang/include/clang/Basic/BuiltinsNVPTX.def
+++ clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -343,6 +343,8 @@
BUILTIN(__nvvm_rcp_rz_d, "dd", "")
BUILTIN(__nvvm_rcp_rm_d, "dd", "")
BUILTIN(__nvvm_rcp_rp_d, "dd", "")
+
+BUILTIN(__nvvm_rcp_approx_ftz_f, "ff", "")
BUILTIN(__nvvm_rcp_approx_ftz_d, "dd", "")
// Sqrt
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
