diff --git a/sycl/doc/extensions/SPIRV/SPV_INTEL_joint_matrix.asciidoc b/sycl/doc/extensions/SPIRV/SPV_INTEL_joint_matrix.asciidoc
new file mode 100644
index 0000000000000..1f819ecab5a71
--- /dev/null
+++ b/sycl/doc/extensions/SPIRV/SPV_INTEL_joint_matrix.asciidoc
@@ -0,0 +1,480 @@
+:extension_name: SPV_INTEL_joint_matrix
+:capability_name: JointMatrixINTEL
+:capability_token: 6118
+:OpTypeJointMatrixINTEL_token: 6119
+:OpJointMatrixLoadINTEL_token: 6120
+:OpJointMatrixStoreINTEL_token: 6121
+:OpJointMatrixMadINTEL_token: 6122
+:OpJointMatrixSUMadINTEL_token: 6128
+:OpJointMatrixUSMadINTEL_token: 6129
+:OpJointMatrixUUMadINTEL_token: 6130
+
+{extension_name}
+================
+
+
+== Name Strings
+
+{extension_name}
+
+== Contact
+
+To report problems with this extension, please open a new issue at:
+
+https://github.com/intel/llvm
+
+== Contributors
+
+- Alexey Sotkin, Intel +
+- Dounia Khaldi, Intel +
+- Mateusz, Belicki Intel +
+- Dmitry Sidorov, Intel +
+
+== Notice
+
+Copyright (c) 2021 Intel Corporation.  All rights reserved.
+
+== Status
+
+Working Draft
+
+This is a preview extension specification, intended to provide early access to a
+feature for review and community feedback. When the feature matures, this
+specification may be released as a formal extension.
+
+
+Because the interfaces defined by this specification are not final and are
+subject to change they are not intended to be used by shipping software
+products. If you are interested in using this feature in your software product,
+please let us know!
+
+== Version
+
+[width="40%",cols="25,25"]
+|========================================
+| Last Modified Date | {docdate}
+| Revision           | A
+|========================================
+
+== Dependencies
+
+This extension is written against the SPIR-V Specification,
+Version 1.5 Revision 5.
+
+This extension requires SPIR-V 1.0.
+
+== Overview
+
+This extension adds a type and instructions for joint matrices. Such matrices
+are shared among a group of work items and is not private to each work item.
+The type introduced with this extension allows to specify memory scope and
+layout of the matrix, including layouts optimized for particular hardware(AMX) .
+New instructions also allow to specify synchronization scope.
+
+== Extension Name
+
+
+To use this extension within a SPIR-V module, the appropriate *OpExtension* must
+be present in the module:
+
+[subs="attributes"]
+----
+OpExtension "{extension_name}"
+----
+
+== New Capabilities
+
+This extension introduces new capabilities:
+
+[subs="attributes"]
+----
+{capability_name}
+----
+
+== New Instructions
+
+Instructions added under the *{capability_name}* capability:
+
+----
+
+OpTypeJointMatrixINTEL
+OpJointMatrixLoadINTEL
+OpJointMatrixStoreINTEL
+OpJointMatrixMADINTEL
+OpJointMatrixSUMADINTEL
+OpJointMatrixUSMADINTEL
+OpJointMatrixUUMADINTEL
+
+----
+
+== Token Number Assignments
+
+[width="40%"]
+[cols="70%,30%"]
+[grid="rows"]
+|====
+|*{capability_name}*  | {capability_token}
+|*OpTypeJointMatrixINTEL*    | {OpTypeJointMatrixINTEL_token}
+|*OpJointMatrixLoadINTEL*    | {OpJointMatrixLoadINTEL_token}
+|*OpJointMatrixStoreINTEL*   | {OpJointMatrixStoreINTEL_token}
+|*OpJointMatrixMadINTEL*     | {OpJointMatrixMadINTEL_token}
+|*OpJointMatrixSUMadINTEL*   | {OpJointMatrixSUMadINTEL_token}
+|*OpJointMatrixUSMadINTEL*   | {OpJointMatrixUSMadINTEL_token}
+|*OpJointMatrixUUMadINTEL*   | {OpJointMatrixUUMadINTEL_token}
+|====
+
+== Modifications to the SPIR-V Specification, Version 1.5
+
+=== Matrix layout
+
+Add section 3.XX, Matrix layout.
+
+[options="header"]
+|====
+2+^| Layout ^| Enabling capability 
+| 0 | *ColumnMajor*            |  *{capability_name}*
+| 1 | *RowMajor*               |  *{capability_name}*
+| 2 | *PackedA* +
+Suitable for VNNI instructions | *{capability_name}*
+| 3 | *PackedB* +
+Suitable for VNNI instructions | *{capability_name}*
+|====
+
+=== Capabilities
+
+Modify Section 3.31, Capability, adding rows to the Capability table:
+
+--
+[options="header"]
+|====
+2+^| Capability ^| Implicitly Declares 
+| {capability_token} | *{capability_name}*
+| Reserved. +
+ +
+See also extension: *{extension_name}*
+|====
+--
+
+=== Instructions
+
+==== 3.37.6 Type-Declaration Instructions
+
+[cols="1,1,6*3",width="100%"]
+|=====
+7+|[[OpTypeJointMatrixINTEL]]*OpTypeJointMatrixINTEL* +
+ +
+Declare a matrix type. +
+ +
+'Component Type' is the type of each component in the resulting type. It must be
+a scalar 'numerical type'. +
+ +
+'Row Count' is the number of rows in the matrix type. It must be a constant
+unsigned 32-bit integer. Behavior is undefined when 'Row Count' is 0 or
+<<OpConstantNull,*OpConstantNull*>>. +
+ +
+'Column Count' is the number of columns in the matrix type. It must be a
+constant unsigned 32-bit integer. Behavior is undefined when 'Column Count' is
+0 or <<OpConstantNull,*OpConstantNull*>>. +
+ +
+'Layout' indicates how the values are arranged internally in the matrix type. 
+It must be the result of a constant instruction. +
+ +
+'Scope' is memory scope for operations on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+
+
+1+|Capability: +
+*{capability_name}*
+1+| 7 | {OpTypeJointMatrixINTEL_token}
+| 'Result <id>'
+| '<id>' +
+'Component Type'
+| '<id>' +
+'Row Count'
+| '<id>' +
+'Column Count'
+| '<id>' +
+'Layout'
+| '<id>' +
+'Scope'
+|=====
+
+
+==== 3.37.8. Memory Instructions
+
+[cols="1,1,7*3",width="100%"]
+|=====
+8+|[[OpJointMatrixLoadINTEL]]*OpJointMatrixLoadINTEL* +
+ +
+Load a matrix through a pointer. +
+ +
+'Result Type' is the type of the loaded matrix. It must be
+<<OpTypeJointMatrixINTEL,OpTypeJointMatrixINTEL>>. +
+ +
+'Pointer' is the pointer to load through. It specifies start of memory region 
+where elements of the matrix are stored and arranged according to 'Layout'. +
+ +
+'Stride' is the number of elements in memory between beginnings of successive
+rows, columns (or words) in the result. It must be a scalar integer type. +
+ +
+'Layout' indicates how the values loaded from memory are arranged. 
+It must be the result of a constant instruction. +
+ +
+'Scope' is syncronization scope for operation on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+ +
+If present, any 'Memory Operands' must begin with a 
+<<Memory_Operands,*memory operand*>> literal. If not present, it is the same as
+specifying the <<Memory_Operands,*memory operand*>> *None*. +
+
+1+|Capability: +
+*{capability_name}*
+1+| 7 + variable | {OpJointMatrixLoadINTEL_token}
+| '<id>' +
+'Result Type'
+|'Result <id>'
+| '<id>' +
+'Pointer'
+| '<id>' +
+'Stride'
+| '<id>' +
+'<<Matrix Layout,Layout>>'
+| '<id>' +
+'Scope'
+| Optional +
+'Memory Access'
+|=====
+
+
+[cols="1,1,6*3",width="100%"]
+|=====
+7+|[[OpJointMatrixStoreINTEL]]*OpJointMatrixStoreINTEL* +
+ +
+Store a matrix through a pointer. +
+ +
+'Pointer' is the pointer to store through. It specifies start of memory region 
+where elements of the matrix must be stored and arranged according to 'Layout'. +
+ +
+'Object' is the matrix to store. It must be
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>>. +
+ +
+'Stride' is the number of elements in memory between beginnings of successive
+rows, columns (or words) of the 'Object'. It must be a scalar integer type. +
+ +
+'Layout' indicates how the values stored to memory are arranged. It must be the
+result of a constant instruction. +
+ +
+'Scope' is syncronization scope for operation on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+ +
+If present, any 'Memory Operands' must begin with a
+<<Memory_Operands,*memory operand*>> literal. If not present, it is the same as
+specifying the <<Memory_Operands,*memory operand*>> *None*. +
+
+1+|Capability: +
+*{capability_name}*
+1+| 6 + variable | {OpJointMatrixStoreINTEL_token}
+| '<id>' +
+'Pointer'
+| '<id>' +
+'Object'
+| '<id>' +
+'Stride'
+| '<id>' +
+'<<Matrix Layout,Layout>>'
+| '<id>' +
+'Scope'
+| Optional +
+'Memory Access'
+|=====
+
+
+==== 3.37.13. Arithmetic Instructions
+
+[cols="1,1,6*3",width="100%"]
+|=====
+7+|[[OpJointMatrixMadINTEL]]*OpJointMatrixMadINTEL* +
+ +
+Multiply matrix 'A' by matrix 'B' and add matrix 'C' to the result of the
+multiplication: `A*B+C`. Here 'A' is a `M x K` matrix, 'B' is a `K x N`
+matrix and 'C' is a `M x N` matrix. +
+ +
+Behavior is undefined if sizes of operands do not meet the conditions above.
+All operands and the 'Result Type' must be
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>>. +
+ +
+'A' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is a signed 'numerical type', 'Row Count' equals to 'M' and
+'Column Count' equals to 'K' +
+ +
+'B' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is a signed 'numerical type', 'Row Count' equals to 'K' and
+'Column Count' equals to 'N' +
+ +
+'C' and 'Result Type' must be a
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> with 'Row Count' equals to
+'M' and 'Column Count' equals to 'N' +
+ +
+'Scope' is syncronization scope for operation on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+
+1+|Capability: +
+*{capability_name}*
+1+| 7 | {OpJointMatrixMadINTEL_token}
+| '<id>' +
+'Result Type'
+|'Result <id>'
+| '<id>' +
+'A'
+| '<id>' +
+'B'
+| '<id>' +
+'C'
+| '<id>' +
+'Scope'
+|=====
+
+[cols="1,1,6*3",width="100%"]
+|=====
+7+|[[OpJointMatrixSUMadINTEL]]*OpJointMatrixSUMadINTEL* +
+ +
+Multiply matrix 'A' by matrix 'B' and add matrix 'C' to the result of the
+multiplication: `A*B+C`. Here 'A' is a `M x K` matrix, 'B' is a `K x N`
+matrix and 'C' is a `M x N` matrix. +
+ +
+Behavior is undefined if sizes of operands do not meet the conditions above.
+All operands and the 'Result Type' must be
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>>. +
+ +
+'A' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is a signed 'numerical type', 'Row Count' equals to 'M' and
+'Column Count' equals to 'K' +
+ +
+'B' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is an unsigned 'numerical type', 'Row Count' equals to 'K' and
+'Column Count' equals to 'N' +
+ +
+'C' and 'Result Type' must be a
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> with 'Row Count' equals to
+'M' and 'Column Count' equals to 'N' +
+ +
+'Scope' is syncronization scope for operation on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+
+1+|Capability: +
+*{capability_name}*
+1+| 7 | {OpJointMatrixSUMadINTEL_token}
+| '<id>' +
+'Result Type'
+|'Result <id>'
+| '<id>' +
+'A'
+| '<id>' +
+'B'
+| '<id>' +
+'C'
+| '<id>' +
+'Scope'
+|=====
+
+[cols="1,1,6*3",width="100%"]
+|=====
+7+|[[OpJointMatrixUSMadINTEL]]*OpJointMatrixUSMadINTEL* +
+ +
+Multiply matrix 'A' by matrix 'B' and add matrix 'C' to the result of the
+multiplication: `A*B+C`. Here 'A' is a `M x K` matrix, 'B' is a `K x N`
+matrix and 'C' is a `M x N` matrix. +
+ +
+Behavior is undefined if sizes of operands do not meet the conditions above.
+All operands and the 'Result Type' must be
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>>. +
+ +
+'A' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is an unsigned 'numerical type', 'Row Count' equals to 'M' and
+'Column Count' equals to 'K' +
+ +
+'B' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is a signed 'numerical type', 'Row Count' equals to 'K' and
+'Column Count' equals to 'N' +
+ +
+'C' and 'Result Type' must be a
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> with 'Row Count' equals to
+'M' and 'Column Count' equals to 'N' +
+ +
+'Scope' is syncronization scope for operation on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+
+1+|Capability: +
+*{capability_name}*
+1+| 7 | {OpJointMatrixUSMadINTEL_token}
+| '<id>' +
+'Result Type'
+|'Result <id>'
+| '<id>' +
+'A'
+| '<id>' +
+'B'
+| '<id>' +
+'C'
+| '<id>' +
+'Scope'
+|=====
+
+[cols="1,1,6*3",width="100%"]
+|=====
+7+|[[OpJointMatrixUUMadINTEL]]*OpJointMatrixUUMadINTEL* +
+ +
+Multiply matrix 'A' by matrix 'B' and add matrix 'C' to the result of the
+multiplication: `A*B+C`. Here 'A' is a `M x K` matrix, 'B' is a `K x N`
+matrix and 'C' is a `M x N` matrix. +
+ +
+Behavior is undefined if sizes of operands do not meet the conditions above.
+All operands and the 'Result Type' must be
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>>. +
+ +
+'A' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is an unsigned 'numerical type', 'Row Count' equals to 'M' and
+'Column Count' equals to 'K' +
+ +
+'B' must be a <<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> whose
+'Component Type' is an unsigned 'numerical type', 'Row Count' equals to 'K' and
+'Column Count' equals to 'N' +
+ +
+'C' and 'Result Type' must be a
+<<OpTypeJointMatrixINTEL,*OpTypeJointMatrixINTEL*>> with 'Row Count' equals to
+'M' and 'Column Count' equals to 'N' +
+ +
+'Scope' is syncronization scope for operation on the matrix. It must be the
+result of a constant instruction with scalar 'integer type'. +
+
+1+|Capability: +
+*{capability_name}*
+1+| 7 | {OpJointMatrixUUMadINTEL_token}
+| '<id>' +
+'Result Type'
+|'Result <id>'
+| '<id>' +
+'A'
+| '<id>' +
+'B'
+| '<id>' +
+'C'
+| '<id>' +
+'Scope'
+|=====
+
+=== Issues
+
+None
+
+Revision History
+----------------
+
+[cols="5,15,15,70"]
+[grid="rows"]
+[options="header"]
+|========================================
+|Rev|Date|Author|Changes
+|1|2021-02-16|Alexey Sotkin|Initial revision
+|1|2021-09-06|Dmitry Sidorov|Split OpJointMatrixMadINTEL instruction into 4
+|========================================