saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix crash on Windows server 2016 on Intel Gen4 Xeon processors (#17611)

Browse source 
This adds an additional check before enabling MlasGemmU8S8DispatchAmx
for GEMM operations. After checking the CPUID for AMX-TILE and AMX-INT8,
an additional check is added that checks value of the XCR0 register.

The value in the OXR0 register is set by the OS and indicates support
for various CPU features. In this case the bits indicating XTILECFG and
XTILEDATA support are checked.

### Description
This adds an additional check before enabling MlasGemmU8S8DispatchAmx
for GEMM operations. After checking the CPUID for AMX-TILE and AMX-INT8,
an additional check is added that checks value of the XCR0 register.

The value in the OXR0 register is set by the OS and indicates support
for various CPU features. In this case the bits indicating XTILECFG and
XTILEDATA support are checked.



### Motivation and Context
Fix for crash reported directly by customer. When running older Windows
server OS on newer Gen4 Xeon processors.

Signed-off-by: Nash <george.nash@intel.com>
This commit is contained in:
George Nash 2023-09-21 09:25:41 -07:00 committed by GitHub
parent 5b9cd91a9c
commit f299016cbe
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
onnxruntime/core/mlas/lib/platform.cpp
View file

@ -112,6 +112,14 @@ MLAS_INTERNAL_DATA MLAS_DECLSPEC_ALIGN(const int16_t MlasOpmask16BitTableAvx512[
#define _XCR_XFEATURE_ENABLED_MASK 0
#endif
#if !defined(XFEATURE_MASK_XTILE)
#define XFEATURE_XTILECFG 17
#define XFEATURE_XTILEDATA 18
#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
#endif
inline
uint64_t
MlasReadExtendedControlRegister(
@ -142,11 +150,6 @@ bool
MlasInitAMX()
{
#if defined(__linux__)
#define XFEATURE_XTILECFG 17
#define XFEATURE_XTILEDATA 18
#define XFEATURE_MASK_XTILECFG (1 << XFEATURE_XTILECFG)
#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
#define ARCH_GET_XCOMP_PERM 0x1022
#define ARCH_REQ_XCOMP_PERM 0x1023
@ -417,7 +420,9 @@ Return Value:
// Check if the processor supports AMX-TILE and AMX-INT8
// features.
//
if ((Cpuid7[3] & 0b1 << 24) != 0 && (Cpuid7[3] & 0b1 << 25) != 0) {
if ((Cpuid7[3] & 0b1 << 24) != 0 &&
(Cpuid7[3] & 0b1 << 25) != 0 &&
(xcr0 & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE) {
if (MlasInitAMX()) {
this->GemmU8U8Dispatch = &MlasGemmU8S8DispatchAmx;
this->GemmU8S8Dispatch = &MlasGemmU8S8DispatchAmx;