[clang] [llvm] [AArch64] Implement intrinsics for F1CVTL/F2CVTL and BF1CVTL/BF2CVTL (PR #116959)

[Momchil Velikov via cfe-commits]

================
@@ -0,0 +1,48 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme2,+fp8 -verify-machineinstrs -force-streaming < %s | FileCheck %s
+
+; F1CVTL / F2CVTL
+
+define { <vscale x 8 x half>, <vscale x 8 x half> } @f1cvtl(<vscale x 16 x i8> %zm) {
+; CHECK-LABEL: f1cvtl:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    f1cvtl { z0.h, z1.h }, z0.b
+; CHECK-NEXT:    ret
+  %res = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.fp8.f1cvtl.x2(<vscale x 16 x i8> %zm)
+  ret { <vscale x 8 x half>, <vscale x 8 x half> } %res
+}
+
+define { <vscale x 8 x half>, <vscale x 8 x half> } @f2cvtl(<vscale x 16 x i8> %zm) {
+; CHECK-LABEL: f2cvtl:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    f2cvtl { z0.h, z1.h }, z0.b
+; CHECK-NEXT:    ret
+  %res = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.fp8.f2cvtl.x2(<vscale x 16 x i8> %zm)
+  ret { <vscale x 8 x half>, <vscale x 8 x half> } %res
+}
+
+; BF1CVTL / BF2CVTL
+
+define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @bf1cvtl(<vscale x 16 x i8> %zm) {
+; CHECK-LABEL: bf1cvtl:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    bf1cvtl { z0.h, z1.h }, z0.b
+; CHECK-NEXT:    ret
+  %res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.fp8.bf1cvtl.x2(<vscale x 16 x i8> %zm)
+  ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res
+}
+
+define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @bf2cvtl( <vscale x 16 x i8> %zm) {
+; CHECK-LABEL: bf2cvtl:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    bf2cvtl { z0.h, z1.h }, z0.b
+; CHECK-NEXT:    ret
+  %res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sme.fp8.bf2cvtl.x2(<vscale x 16 x i8> %zm)
+  ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res
+}
+
+
+declare { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sme.fp8.f1cvtl.x2(<vscale x 16 x i8>)
----------------
momchil-velikov wrote:

These declarations are unnecessary.


https://github.com/llvm/llvm-project/pull/116959