[libclc] [libclc] Refine __clc_fp*_subnormals_supported and __clc_flush_denormal_if_not_supported (PR #157633)

[Wenju He via cfe-commits]

================
@@ -65,14 +55,12 @@ bool __attribute__((noinline)) __clc_runtime_has_hw_fma32(void);
 
 #define LOG_MAGIC_NUM_SP32 (1 + NUMEXPBITS_SP32 - EXPBIAS_SP32)
 
-_CLC_OVERLOAD _CLC_INLINE float __clc_flush_denormal_if_not_supported(float x) {
-  int ix = __clc_as_int(x);
-  if (!__clc_fp32_subnormals_supported() && ((ix & EXPBITS_SP32) == 0) &&
-      ((ix & MANTBITS_SP32) != 0)) {
-    ix &= SIGNBIT_SP32;
-    x = __clc_as_float(ix);
-  }
-  return x;
+_CLC_OVERLOAD _CLC_INLINE float __clc_soft_flush_denormal(float x) {
+  // Avoid calling __clc_fp32_subnormals_supported here: it uses
----------------
wenju-he wrote:

> You might have less trouble just using canonicalize for now and trying to relax it later

do you mean reverting __clc_soft_flush_denormal to use __clc_fp32_subnormals_supported which uses llvm.canonicalize, or just replacing use of __clc_fp32_subnormals_supported with __builtin_elementwise_canonicalize?

https://github.com/llvm/llvm-project/pull/157633