[PATCH] D119157: [NVPTX] Add ex2 f16 support

[Artem Belevich via Phabricator via cfe-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG69a8350c232a: [NVPTX] Add ex2.approx.f16/f16x2 support (authored by npmiller, committed by tra).

Changed prior to commit:
  https://reviews.llvm.org/D119157?vs=406507&id=410932#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D119157/new/

https://reviews.llvm.org/D119157

Files:
  llvm/include/llvm/IR/IntrinsicsNVVM.td
  llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
  llvm/test/CodeGen/NVPTX/f16-ex2.ll


Index: llvm/test/CodeGen/NVPTX/f16-ex2.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/NVPTX/f16-ex2.ll
@@ -0,0 +1,20 @@
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_75 -mattr=+ptx70 | FileCheck %s
+
+declare half @llvm.nvvm.ex2.approx.f16(half)
+declare <2 x half> @llvm.nvvm.ex2.approx.f16x2(<2 x half>)
+
+; CHECK-LABEL: exp2_half
+define half @exp2_half(half %0) {
+  ; CHECK-NOT: call
+  ; CHECK: ex2.approx.f16
+  %res = call half @llvm.nvvm.ex2.approx.f16(half %0);
+  ret half %res
+}
+
+; CHECK-LABEL: exp2_2xhalf
+define <2 x half> @exp2_2xhalf(<2 x half> %0) {
+  ; CHECK-NOT: call
+  ; CHECK: ex2.approx.f16x2
+  %res = call <2 x half> @llvm.nvvm.ex2.approx.f16x2(<2 x half> %0);
+  ret <2 x half> %res
+}
Index: llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
===================================================================
--- llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
+++ llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
@@ -907,6 +907,10 @@
   Float32Regs, Float32Regs, int_nvvm_ex2_approx_f>;
 def INT_NVVM_EX2_APPROX_D : F_MATH_1<"ex2.approx.f64 \t$dst, $src0;",
   Float64Regs, Float64Regs, int_nvvm_ex2_approx_d>;
+def INT_NVVM_EX2_APPROX_F16 : F_MATH_1<"ex2.approx.f16 \t$dst, $src0;",
+  Float16Regs, Float16Regs, int_nvvm_ex2_approx_f16, [hasPTX70, hasSM75]>;
+def INT_NVVM_EX2_APPROX_F16X2 : F_MATH_1<"ex2.approx.f16x2 \t$dst, $src0;",
+  Float16x2Regs, Float16x2Regs, int_nvvm_ex2_approx_f16x2, [hasPTX70, hasSM75]>;
 
 def INT_NVVM_LG2_APPROX_FTZ_F : F_MATH_1<"lg2.approx.ftz.f32 \t$dst, $src0;",
   Float32Regs, Float32Regs, int_nvvm_lg2_approx_ftz_f>;
Index: llvm/include/llvm/IR/IntrinsicsNVVM.td
===================================================================
--- llvm/include/llvm/IR/IntrinsicsNVVM.td
+++ llvm/include/llvm/IR/IntrinsicsNVVM.td
@@ -828,6 +828,10 @@
       DefaultAttrsIntrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
   def int_nvvm_ex2_approx_d : GCCBuiltin<"__nvvm_ex2_approx_d">,
       DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
+  def int_nvvm_ex2_approx_f16 : GCCBuiltin<"__nvvm_ex2_approx_f16">,
+      DefaultAttrsIntrinsic<[llvm_half_ty], [llvm_half_ty], [IntrNoMem]>;
+  def int_nvvm_ex2_approx_f16x2 : GCCBuiltin<"__nvvm_ex2_approx_f16x2">,
+      DefaultAttrsIntrinsic<[llvm_v2f16_ty], [llvm_v2f16_ty], [IntrNoMem]>;
 
   def int_nvvm_lg2_approx_ftz_f : GCCBuiltin<"__nvvm_lg2_approx_ftz_f">,
       DefaultAttrsIntrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D119157.410932.patch
Type: text/x-patch
Size: 2515 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220223/41042b9f/attachment.bin>