[libclc] [libclc] Add native half implementation of __clc_normalize (PR #150165)

[Wenju He via cfe-commits]

https://github.com/wenju-he created https://github.com/llvm/llvm-project/pull/150165

This is ported from https://github.com/intel/llvm/blob/sycl/libclc/libspirv/lib/generic/geometric/normalize.cl and can pass a closed-source OpenCL CTS
"test_geometrics geom_normalize --half CL_DEVICE_TYPE_GPU" on intel GPU.

llvm-diff amdgcn--amdhsa.bc shows fpext/fptrunc insts are now removed from normalize function.

>From dc8517b82e812e4238656e4a4ada0057a0487fda Mon Sep 17 00:00:00 2001
From: Wenju He <wenju.he at intel.com>
Date: Wed, 23 Jul 2025 05:42:04 +0200
Subject: [PATCH] [libclc] Add native half implementation of __clc_normalize

This is ported from https://github.com/intel/llvm/blob/sycl/libclc/libspirv/lib/generic/geometric/normalize.cl
and can pass a closed-source OpenCL CTS
"test_geometrics geom_normalize --half CL_DEVICE_TYPE_GPU" on intel GPU.

llvm-diff amdgcn--amdhsa.bc shows fpext/fptrunc insts are now removed
from normalize function.
---
 .../clc/lib/generic/geometric/clc_normalize.inc | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/libclc/clc/lib/generic/geometric/clc_normalize.inc b/libclc/clc/lib/generic/geometric/clc_normalize.inc
index 8a47c6d4826e9..9b2cbc8f19dd0 100644
--- a/libclc/clc/lib/generic/geometric/clc_normalize.inc
+++ b/libclc/clc/lib/generic/geometric/clc_normalize.inc
@@ -10,15 +10,8 @@
 #if (__CLC_VECSIZE_OR_1 == 1 || __CLC_VECSIZE_OR_1 == 2 ||                     \
      __CLC_VECSIZE_OR_1 == 3 || __CLC_VECSIZE_OR_1 == 4)
 
-// Until we have a native FP16 implementation, go via FP32
-#if __CLC_FPSIZE == 16
-
-_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_normalize(__CLC_GENTYPE p) {
-  return __CLC_CONVERT_GENTYPE(__clc_normalize(__CLC_CONVERT_FLOATN(p)));
-}
-
 // Scalar normalize
-#elif defined(__CLC_SCALAR)
+#if defined(__CLC_SCALAR)
 
 _CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_normalize(__CLC_GENTYPE p) {
   return __clc_sign(p);
@@ -27,7 +20,13 @@ _CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_normalize(__CLC_GENTYPE p) {
 // Vector normalize
 #else
 
-#if __CLC_FPSIZE == 32
+#if __CLC_FPSIZE == 16
+
+#define MIN_VAL HALF_MIN
+#define MAX_SQRT 0x1.0p+8h
+#define MIN_SQRT 0x1.0p-8h
+
+#elif __CLC_FPSIZE == 32
 
 #define MIN_VAL FLT_MIN
 #define MAX_SQRT 0x1.0p+86F