[SYCL][Matrix] Fix typos in SPR and GNR architecture names (#11900)

Author: dkhaldi

sycl/doc/extensions/experimental/sycl_ext_matrix/sycl_ext_oneapi_matrix.asciidoc

@@ -855,32 +855,32 @@ XMX hardware. Note that these can be returned using
 
 ==== Intel AMX Supported Combinations
 This is currently available in devices with the architecture
-`architecture::intel_cpu_spr`, and `architecture::intel_cpu_gnr`. In
-this architecture's implementation, the type of the C matrix must be
-the same as the type of the D matrix. Therefore, that common type is
-shown in a single column in the table below. 
+`architecture::intel_cpu_spr`, and `architecture::intel_cpu_gnr`.
+In this architecture's implementation, the type of the C matrix must
+be the same as the type of the D matrix. Therefore, that common type
+is shown in a single column in the table below.
 
 [frame="none",options="header"]
 |======================
 | A type | B type | C and D type | M | N | K | device
 | `matrix_type::uint8`  | `matrix_type::uint8` |
 `matrix_type::sint32`  |  +<=+ 16 |  +<=+ 16 |  +<=+ 64
-|`architecture::intel_gpu_spr`, `architecture::intel_gpu_gnr`
+|`architecture::intel_cpu_spr`, `architecture::intel_cpu_gnr`
 | `matrix_type::uint8`  | `matrix_type::sint8` |
 `matrix_type::sint32`  |  +<=+ 16 |  +<=+ 16 |  +<=+ 64
-|`architecture::intel_gpu_spr`, `architecture::intel_gpu_gnr`
+|`architecture::intel_cpu_spr`, `architecture::intel_cpu_gnr`
 | `matrix_type::sint8`  | `matrix_type::uint8` |
 `matrix_type::sint32`  |  +<=+ 16 |  +<=+ 16 |  +<=+ 64
-|`architecture::intel_gpu_spr`, `architecture::intel_gpu_gnr`
+|`architecture::intel_cpu_spr`, `architecture::intel_cpu_gnr`
 | `matrix_type::sint8`  | `matrix_type::sint8` |
 `matrix_type::sint32`  |  +<=+ 16 |  +<=+ 16 |  +<=+ 64
-|`architecture::intel_gpu_spr`, `architecture::intel_gpu_gnr`
+|`architecture::intel_cpu_spr`, `architecture::intel_cpu_gnr`
 |  `matrix_type::bf16`       |  `matrix_type::bf16`   |
 `matrix_type::fp32`   |  +<=+ 16 |  +<=+ 16   |  +<=+ 32
-|`architecture::intel_gpu_spr`, `architecture::intel_gpu_gnr`
+|`architecture::intel_cpu_spr`, `architecture::intel_cpu_gnr`
 |  `matrix_type::fp16`       |  `matrix_type::fp16`   |
 `matrix_type::fp32`   |  +<=+ 16 |  +<=+ 16   |  +<=+ 32
-|`architecture::intel_gpu_gnr`
+|`architecture::intel_cpu_gnr`
 |======================
 
 ==== Intel XMX Supported Combinations

sycl/doc/extensions/experimental/sycl_ext_oneapi_device_architecture.asciidoc

@@ -604,8 +604,8 @@ description of the `-fsycl-targets` option.  These are the target names of the
 form "intel_gpu_*", "nvidia_gpu_*", or "amd_gpu_*".
 
 The architecture enumerations `intel_cpu_spr` and `intel_cpu_gnr` do
-not currently work with any of the APIs described in this
-extension. They cannot be used with the `if_architecture_is` function,
+not currently work with any of the APIs described in this extension.
+They cannot be used with the `if_architecture_is` function,
 the `device::ext_oneapi_architecture_is` function, or the
 `info::device::architecture` query descriptor. They currently exist
 only for use with the