[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ad272dc1-1b85-41ef-8454-4888a5ab95ee@intel.com>
Date: Tue, 12 Mar 2024 09:07:15 -0700
From: "Chang S. Bae" <chang.seok.bae@...el.com>
To: Muhammad Usama Anjum <usama.anjum@...labora.com>, Shuah Khan
<shuah@...nel.org>, Dave Hansen <dave.hansen@...ux.intel.com>, "Kirill A.
Shutemov" <kirill.shutemov@...ux.intel.com>, "Peter Zijlstra (Intel)"
<peterz@...radead.org>, Weihong Zhang <weihong.zhang@...el.com>, Binbin Wu
<binbin.wu@...ux.intel.com>, angquan yu <angquan21@...il.com>
CC: <kernel@...labora.com>, <linux-kselftest@...r.kernel.org>,
<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] selftests: x86: skip the tests if prerequisites aren't
fulfilled
On 3/12/2024 2:26 AM, Muhammad Usama Anjum wrote:
>
> How can we check if AMX is available or not?
After a successful check_cpuid_xsave(), examining CPUID(eax=0xd, ecx=0)
EDX: EAX, which reports the support bits of XCR0, can give assurance of
AMX availability. Perhaps, this change is considerable on top of your patch:
static int check_cpuid_xtiledata(void)
{
uint32_t eax, ebx, ecx, edx;
+ uint64_t xfeatures;
__cpuid_count(CPUID_LEAF_XSTATE, CPUID_SUBLEAF_XSTATE_USER,
eax, ebx, ecx, edx);
+ xfeatures = eax + ((uint64_t)edx << 32);
+ if ((xfeatures & XFEATURE_MASK_XTILE) != XFEATURE_MASK_XTILE) {
+ ksft_print_msg("no AMX support\n");
+ return -1;
+ }
Nevertheless, I still believe that using arch_prctl(ARCH_GET_XCOMP_SUPP,
..) remains a simple and legitimate approach for directly checking
dynamic feature support from the kernel:
https://docs.kernel.org/arch/x86/xstate.html
Thanks,
Chang
Powered by blists - more mailing lists