diff --git a/muh/include/muh/hardware.cuh b/muh/include/muh/hardware.cuh index ec1b0c7c..b623e7e4 100644 --- a/muh/include/muh/hardware.cuh +++ b/muh/include/muh/hardware.cuh @@ -34,8 +34,8 @@ struct hardware_capability { .max_shared_memory_per_block = 49152, // 48 KiB, TBD .max_registers_per_thread = 255, .l2_cache_size_bytes = 6 * 1024 * 1024, // 6 MiB, TBD - .memory_bandwidth_gbps = 900, // TBD - .sm_count = 50, // 50c in the spec + .memory_bandwidth_gbps = 900, // Confirmed: 1200MHz mem clock // TBD + .sm_count = 16, // CONFIRMED: ixsmi shows 16 SMs per BI-V100 // 50c in the spec .vendor = vendor_t::iluvatar, .arch_version = 100, }; diff --git a/muh_kernel_map.py b/muh_kernel_map.py index 33dc7081..5f9c01cc 100644 --- a/muh_kernel_map.py +++ b/muh_kernel_map.py @@ -49,9 +49,9 @@ BI_V100 = { "max_registers_per_thread": 255, "l2_cache_size_bytes": 6 * 1024 * 1024, # 6 MiB "memory_bandwidth_gbps": 900, - "sm_count": 50, + "sm_count": 16 # CONFIRMED 2026-08-01, # Derived - "bandwidth_per_sm_gbps": 900 / 50, # 18 GB/s ≈ A100 level + "bandwidth_per_sm_gbps": 900 / 16 # 56.25 GB/s per SM, # 18 GB/s ≈ A100 level } SM100 = {