================
@@ -66,13 +65,11 @@ 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;
+ // Avoid calling __clc_fp32_subnormals_supported here: it uses
+ // llvm.canonicalize, which quiets sNaN.
+ return __builtin_fabsf(x) < 0x1p-149f
+ ? __builtin_elementwise_copysign(0.0f, x)
+ : x;
----------------
wenju-he wrote:
If denormal is not supported
* returns signed zero for denormal input since __builtin_fabsf result is 0
* return x if x is not denormal
If denormal is supported
* returns x as is regardless if x is denormal or not.
So this function only flushes to zero if denormal is not supported, right?
https://github.com/llvm/llvm-project/pull/157633
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
