Replace NO-OP round-trip + normalize + epilogue_tma_store with: - get_tmem_load_op + get_smem_store_op paired atoms - One-way TMEM→reg (normalize) →SMEM→GMEM - Eliminates ~3% error from TMEM layout mismatch - O rescale disabled (single KV tile only for now) - Pre-computed TMA partitions outside if blocks
38 lines
1.6 KiB
Python
38 lines
1.6 KiB
Python
"""D1 sweep: paired atoms epilogue (no TMEM round-trip)."""
|
|
import torch, math
|
|
import cutlass.cute as cute
|
|
import cutlass.torch as ct
|
|
import cuda.bindings.driver as cuda
|
|
from dsv4.kernels.attention.fmha import FmhaKernel
|
|
|
|
# Single KV tile (n=128) only — O rescale not needed
|
|
for hd in [64, 128, 256]:
|
|
torch.manual_seed(42)
|
|
n = 128; m = 128
|
|
q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
|
|
k = torch.randn(n, hd, 1, dtype=torch.bfloat16, device='cuda')
|
|
v = torch.randn(n, hd, dtype=torch.bfloat16, device='cuda')
|
|
c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')
|
|
|
|
qf = q[:,:,0].float(); kf = k[:,:,0].float()
|
|
scale = 1.0 / math.sqrt(hd)
|
|
attn = qf @ kf.T * scale; attn = torch.softmax(attn, dim=-1)
|
|
ref = attn @ v.float()
|
|
|
|
v_kernel = v.unsqueeze(-1)
|
|
mQ = ct.from_dlpack(q).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q))
|
|
mK = ct.from_dlpack(k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k))
|
|
mV = ct.from_dlpack(v_kernel).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_kernel))
|
|
mC = ct.from_dlpack(c).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c))
|
|
stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)
|
|
|
|
kernel = FmhaKernel(head_dim=hd, s_k=n)
|
|
print(f'hd={hd}: Compiling...', flush=True)
|
|
compiled = cute.compile(kernel, mQ, mK, mV, mC, stream)
|
|
compiled(mQ, mK, mV, mC, stream)
|
|
torch.cuda.synchronize()
|
|
|
|
out = c[:,:,0].float()
|
|
cos = torch.nn.functional.cosine_similarity(out.flatten().unsqueeze(0), ref.flatten().unsqueeze(0)).item()
|
|
print(f'hd={hd}: cos {cos:.6f} {"PASS" if cos >= 0.99 else "FAIL (need >=0.99)"}')
|