wylab/llama.cpp-rocm
1
0
Fork 0
forked from wylab/llama.cpp
Code Pull Requests Actions 28 Packages Activity

update hw info

Browse Source
This commit is contained in:
arthw
2026-03-31 09:24:40 +08:00
parent 8dc96153c3
commit 2985be3324
2 changed files with 67 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/sycl_hw.cpp
+52 -47
View File
@@ -5,58 +5,63 @@ using namespace std;
/*defined in
* /opt/intel/oneapi/compiler/latest/include/sycl/ext/oneapi/experimental/device_architecture.def
*/
static map<gpu_arch, const char*> arch2name = {
{gpu_arch::intel_gpu_bdw, "intel_gpu_bdw"},
{gpu_arch::intel_gpu_skl, "intel_gpu_skl"},
{gpu_arch::intel_gpu_kbl, "intel_gpu_kbl"},
{gpu_arch::intel_gpu_cfl, "intel_gpu_cfl"},
{gpu_arch::intel_gpu_apl, "intel_gpu_apl"},
{gpu_arch::intel_gpu_glk, "intel_gpu_glk"},
{gpu_arch::intel_gpu_whl, "intel_gpu_whl"},
{gpu_arch::intel_gpu_aml, "intel_gpu_aml"},
{gpu_arch::intel_gpu_cml, "intel_gpu_cml"},
{gpu_arch::intel_gpu_icllp, "intel_gpu_icllp"},
{gpu_arch::intel_gpu_ehl, "intel_gpu_ehl"},
{gpu_arch::intel_gpu_tgllp, "intel_gpu_tgllp"},
{gpu_arch::intel_gpu_rkl, "intel_gpu_rkl"},
{gpu_arch::intel_gpu_adl_s, "intel_gpu_adl_s"},
{gpu_arch::intel_gpu_adl_p, "intel_gpu_adl_p"},
{gpu_arch::intel_gpu_adl_n, "intel_gpu_adl_n"},
{gpu_arch::intel_gpu_dg1, "intel_gpu_dg1"},
{gpu_arch::intel_gpu_acm_g10, "intel_gpu_acm_g10"},
{gpu_arch::intel_gpu_acm_g11, "intel_gpu_acm_g11"},
{gpu_arch::intel_gpu_acm_g12, "intel_gpu_acm_g12"},
{gpu_arch::intel_gpu_pvc, "intel_gpu_pvc"},
{gpu_arch::intel_gpu_pvc_vg, "intel_gpu_pvc_vg"},
{gpu_arch::intel_gpu_mtl_u, "intel_gpu_mtl_u"},
{gpu_arch::intel_gpu_mtl_h, "intel_gpu_mtl_h"},
{gpu_arch::intel_gpu_arl_h, "intel_gpu_arl_h"},
{gpu_arch::intel_gpu_bmg_g21, "intel_gpu_bmg_g21"},
{gpu_arch::intel_gpu_bmg_g31, "intel_gpu_bmg_g31"},
{gpu_arch::intel_gpu_lnl_m, "intel_gpu_lnl_m"},
{gpu_arch::intel_gpu_ptl_h, "intel_gpu_ptl_h"},
{gpu_arch::intel_gpu_ptl_u, "intel_gpu_ptl_u"},
{gpu_arch::intel_gpu_wcl, "intel_gpu_wcl"}
static map<gpu_arch, std::pair<const char*, sycl_intel_gpu_family>> arch2name = {
{gpu_arch::intel_gpu_bdw, {"intel_gpu_bdw", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_skl, {"intel_gpu_skl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_kbl, {"intel_gpu_kbl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_cfl, {"intel_gpu_cfl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_apl, {"intel_gpu_apl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_glk, {"intel_gpu_glk", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_whl, {"intel_gpu_whl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_aml, {"intel_gpu_aml", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_cml, {"intel_gpu_cml", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_icllp, {"intel_gpu_icllp", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_ehl, {"intel_gpu_ehl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_tgllp, {"intel_gpu_tgllp", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_rkl, {"intel_gpu_rkl", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_adl_s, {"intel_gpu_adl_s", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_adl_p, {"intel_gpu_adl_p", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_adl_n, {"intel_gpu_adl_n", GPU_FAMILY_IGPU_NON_XE}},
{gpu_arch::intel_gpu_dg1, {"intel_gpu_dg1", GPU_FAMILY_DGPU_CLIENT_GAME}},
{gpu_arch::intel_gpu_acm_g10, {"intel_gpu_acm_g10", GPU_FAMILY_DGPU_CLIENT_GAME}},
{gpu_arch::intel_gpu_acm_g11, {"intel_gpu_acm_g11", GPU_FAMILY_DGPU_CLIENT_GAME}},
{gpu_arch::intel_gpu_acm_g12, {"intel_gpu_acm_g12", GPU_FAMILY_DGPU_CLIENT_GAME}},
{gpu_arch::intel_gpu_pvc, {"intel_gpu_pvc", GPU_FAMILY_DGPU_CLOUD}},
{gpu_arch::intel_gpu_pvc_vg, {"intel_gpu_pvc_vg", GPU_FAMILY_DGPU_CLOUD}},
{gpu_arch::intel_gpu_mtl_u, {"intel_gpu_mtl_u", GPU_FAMILY_IGPU_XE}},
{gpu_arch::intel_gpu_mtl_h, {"intel_gpu_mtl_h", GPU_FAMILY_IGPU_XE}},
{gpu_arch::intel_gpu_arl_h, {"intel_gpu_arl_h", GPU_FAMILY_IGPU_XE}},
{gpu_arch::intel_gpu_bmg_g21, {"intel_gpu_bmg_g21", GPU_FAMILY_DGPU_CLIENT_GAME}},
{gpu_arch::intel_gpu_bmg_g31, {"intel_gpu_bmg_g31", GPU_FAMILY_DGPU_CLIENT_GAME}},
{gpu_arch::intel_gpu_lnl_m, {"intel_gpu_lnl_m", GPU_FAMILY_IGPU_XE}},
{gpu_arch::intel_gpu_ptl_h, {"intel_gpu_ptl_h", GPU_FAMILY_IGPU_XE}},
{gpu_arch::intel_gpu_ptl_u, {"intel_gpu_ptl_u", GPU_FAMILY_IGPU_XE}},
{gpu_arch::intel_gpu_wcl, {"intel_gpu_wcl", GPU_FAMILY_IGPU_XE}}
};
sycl_hw_info get_device_hw_info(sycl::device* device_ptr) {
sycl_hw_info res;
int32_t id =
device_ptr->get_info<sycl::ext::intel::info::device::device_id>();
res.device_id = id;
sycl_hw_info res;
int32_t id =
device_ptr->get_info<sycl::ext::intel::info::device::device_id>();
res.device_id = id;
res.name = device_ptr->get_info<sycl::info::device::name>();
res.name = device_ptr->get_info<sycl::info::device::name>();
syclex::architecture arch =
device_ptr->get_info<syclex::info::device::architecture>();
res.arch = arch;
syclex::architecture arch =
device_ptr->get_info<syclex::info::device::architecture>();
res.arch = arch;
map<syclex::architecture, const char*>::iterator it = arch2name.find(res.arch);
if (it != arch2name.end()) {
res.arch_name = it->second;
} else {
res.arch_name = "unknown";
}
map<syclex::architecture,
std::pair<const char*, sycl_intel_gpu_family>>::iterator it =
arch2name.find(res.arch);
if (it != arch2name.end()) {
res.arch_name = it->second.first;
res.gpu_family = it->second.second;
} else {
res.arch_name = "unknown";
res.gpu_family = GPU_FAMILY_UKNOWN;
}
return res;
return res;
}
ggml/src/ggml-sycl/sycl_hw.hpp
+15
View File
@@ -11,11 +11,26 @@
namespace syclex = sycl::ext::oneapi::experimental;
using gpu_arch = sycl::ext::oneapi::experimental::architecture;
// It's used to mark the GPU computing capacity in Flash-attention OP
// The value must flow the order of performance.
enum sycl_intel_gpu_family {
GPU_FAMILY_UKNOWN = -1,
// Normal iGPU in Intel Core CPU, before Meteor Lake iGPU(Xe)
GPU_FAMILY_IGPU_NON_XE = 0,
// iGPU with Xe core, Meteor Lake iGPU or newer.
GPU_FAMILY_IGPU_XE = 1,
// dGPU for gaming in client/data center, DG1/FLex 140 or newer.
GPU_FAMILY_DGPU_CLIENT_GAME = 2,
// dGPU for AI in cloud, PVC or newer.
GPU_FAMILY_DGPU_CLOUD = 3
};
struct sycl_hw_info {
syclex::architecture arch;
const char* arch_name;
int32_t device_id;
std::string name;
sycl_intel_gpu_family gpu_family;
};
sycl_hw_info get_device_hw_info(sycl::device *device_ptr);