Alex Voicu 6ef32188b5

[SPIRV] Add support for bfloat16 atomics via the SPV_INTEL_16bit_atomics extension (#166257) ...

This enables support for atomic RMW ops (add, sub, min and max to be
precise) with `bfloat16` operands, via the [SPV_INTEL_16bit_atomics
extension](https://github.com/intel/llvm/pull/20009). It's logically a
successor to #166031 (I should've used a stack), but I'm putting it up
for early review.

---------

Co-authored-by: Matt Arsenault <arsenm2@gmail.com>

2025-11-09 17:26:14 +00:00

..

SPV_ALTERA_blocking_pipes

[SPIRV] Support for the extension SPV_ALTERA_blocking_pipes (#138675)

2025-11-06 11:59:54 +01:00

SPV_EXT_relaxed_printf_string_address_space

[SPIRV] Add support for the extension SPV_EXT_relaxed_printf_string_address_space (#160245)

2025-09-28 05:50:15 -07:00

SPV_EXT_shader_atomic_float_add

…

SPV_EXT_shader_atomic_float_min_max

…

SPV_INTEL_2d_block_io

…

SPV_INTEL_16bit_atomics

[SPIRV] Add support for bfloat16 atomics via the SPV_INTEL_16bit_atomics extension (#166257)

2025-11-09 17:26:14 +00:00

SPV_INTEL_bfloat16_arithmetic

[SPIRV] Enable bfloat16 arithmetic (#166031)

2025-11-04 18:10:26 +02:00

SPV_INTEL_bfloat16_conversion

…

SPV_INTEL_bindless_images

[SPIRV] Added constraint for SPV_INTEL_bindless_image extension (#160249)

2025-09-28 05:52:19 -07:00

SPV_INTEL_cache_controls

…

SPV_INTEL_float_controls2

…

SPV_INTEL_fp_max_error

…

SPV_INTEL_function_pointers

…

SPV_INTEL_global_variable_fpga_decorations

…

SPV_INTEL_global_variable_host_access

…

SPV_INTEL_inline_assembly

…

SPV_INTEL_int4

…

SPV_INTEL_joint_matrix

…

SPV_INTEL_kernel_attributes

[SPIRV] Enable OpenCL max_work_group_size translation via SPV_INTEL_kernel_attributes (#165891)

2025-11-04 14:37:16 +00:00

SPV_INTEL_long_composites

…

SPV_INTEL_media_block_io

…

SPV_INTEL_memory_access_aliasing

…

SPV_INTEL_predicated_io

[SPIR-V] Add SPV_INTEL_predicated_io extension (#161591)

2025-10-08 23:29:01 +02:00

SPV_INTEL_split_barrier

…

SPV_INTEL_subgroup_matrix_multiply_accumulate

…

SPV_INTEL_subgroups

…

SPV_INTEL_tensor_float32_conversion

…

SPV_INTEL_ternary_bitwise_function

…

SPV_INTEL_usm_storage_classes

…

SPV_INTEL_variable_length_array

…

SPV_KHR_bfloat16

[SPIRV] Add support for the SPIR-V extension SPV_KHR_bfloat16 (#155645)

2025-09-22 14:52:57 +02:00

SPV_KHR_bit_instructions

…

SPV_KHR_cooperative_matrix

…

SPV_KHR_float_controls2

[SPIR-V] Implement SPV_KHR_float_controls2 (#146941)

2025-09-30 16:01:30 +01:00

SPV_KHR_integer_dot_product

[SPIRV] Added Packed Vector Format for SPV_KHR_integer_dot_product (#160088)

2025-09-23 12:04:02 +02:00

SPV_KHR_maximal_reconvergence

[SPIR-V] Generate SPIR-V instructions when 'enable-maximal-reconvergence' function attribute is set (#163682)

2025-10-17 13:12:56 +02:00

SPV_KHR_shader_clock

[SPIRV] Upd SPV_KHR_shader_clock extension (#160147)

2025-10-23 14:51:54 +02:00

SPV_KHR_subgroup_rotate

…

SPV_KHR_uniform_group_instructions

…

both-allowed-disallowed-extension-error.ll

…

enable-all-extensions-avoid-invalid.ll

[SPIRV] Filter disallowed extensions for env (#150051)

2025-08-18 18:33:58 +00:00

enable-all-extensions-but-one.ll

…

enable-all-extensions.ll

[NFC][SPIRV] Add AMDGCN SPIR-V specific defaults to the BE (#165815)

2025-11-04 12:45:53 +00:00

invalid-extension-list-format.ll

…

SPV_EXT_optnone.ll

[NFC][SPIRV] Add AMDGCN SPIR-V specific defaults to the BE (#165815)

2025-11-04 12:45:53 +00:00

SPV_INTEL_arbitrary_precision_integers.ll

…

SPV_INTEL_optnone.ll

…

SPV_KHR_bit_instructions_no_extension.ll

…

SPV_KHR_bit_instructions.ll

…

SPV_KHR_no_integer_wrap_decoration.ll

…

unknown-extension-name.ll

…

unused-but-allowed-SPV_INTEL_arbitrary_precision_integers.ll

…