gallivm: disable f16c when not using AVX

f16c intrinsic can only be emitted when AVX is used. So when we disable AVX
due to forcing 128bit vectors we must not use this intrinsic (depending on
llvm version, this worked previously because llvm used AVX even when we didn't
tell it to, however I've seen this fail with llvm 3.3 since
718249843b which seems to have the side effect
of disabling avx in llvm albeit it only touches sse flags really, but
with ea421e919a it's now really disabled).
Albeit being able to use AVX with 128bit vectors also would have its uses, the
code as is really was meant to emulate jit code creation for less capable cpus.
v2: add some (ifdefed out) missing de-featuring options for simulating
less capable cpus.

Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
This commit is contained in:
Roland Scheidegger 2015-10-26 16:44:47 +01:00
parent a61be1a798
commit 711489648b

View file

@ -427,6 +427,7 @@ lp_build_init(void)
*/
util_cpu_caps.has_avx = 0;
util_cpu_caps.has_avx2 = 0;
util_cpu_caps.has_f16c = 0;
}
#ifdef PIPE_ARCH_PPC_64
@ -458,7 +459,9 @@ lp_build_init(void)
util_cpu_caps.has_sse3 = 0;
util_cpu_caps.has_ssse3 = 0;
util_cpu_caps.has_sse4_1 = 0;
util_cpu_caps.has_sse4_2 = 0;
util_cpu_caps.has_avx = 0;
util_cpu_caps.has_avx2 = 0;
util_cpu_caps.has_f16c = 0;
#endif