marfrit/daedalus-fourier
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v3d_runner: buffer pool for QPU dispatch hot path

Browse Source 
Per the QPU-default substrate decree 2026-05-23: the per-dispatch
vkAllocateMemory in dispatch_*_qpu was the biggest single fixable
contributor to QPU dispatch overhead.  This pools v3d_buffer
allocations by power-of-2 size class so the second-and-subsequent
dispatch hits a freelist instead of paying ~10-50us of Mesa-V3D7
memory-allocation cost per call.

API additions (v3d_runner.h):
  - v3d_runner_acquire_buffer(): pulls from per-bucket freelist;
    falls through to v3d_runner_create_buffer() on miss.
  - v3d_runner_release_buffer(): pushes back onto the freelist; the
    backing VkBuffer/VkDeviceMemory only get vkFreeMemory'd in
    v3d_runner_destroy().
  - v3d_runner_pool_total_bytes(): diagnostic watermark.

Size classes 2^8..2^23 (256 B to 8 MiB).  Oversize requests fall
through to non-pooled (vkAllocateMemory) for both ends — pool stays
correct, just degenerates to old behaviour for those calls.

Migration: daedalus_core.c dispatch_*_qpu paths globally swap
create_buffer → acquire_buffer and destroy_buffer → release_buffer.
All five QPU dispatch functions (idct8 / lpf / mc_8h / cdef /
h264_deblock) now reuse buffers across calls.  test_api_idct stays
bit-exact (4096/4096 bytes on CPU/QPU/AUTO substrates on hertz).

Microbench (tests/bench_pool_overhead.c) on hertz (Pi 5,
6.18.29+rpt-rpi-2712, V3D 7.1):

  call 0:  434.89 us  (cold — 3x vkAllocateMemory)
  call 1:  100.06 us  (pool hit on all 3 buffers)
  steady-state:
    p50:    76.44 us
    p90:    90.52 us
    mean:   77.95 us
  first-call / steady-state ratio: 5.7x

The remaining ~76us steady-state is dominated by vkQueueWaitIdle +
shader execution + per-call descriptor-set update + command-buffer
allocation — addressed in follow-on tasks 161 (persistent cmdbuf)
and 162 (dmabuf import for dst, eliminates memcpy in/out).

Refs daedalus-fourier task #160.
This commit is contained in:
Claude (noether)
2026-05-23 19:52:50 +02:00
parent 3ecfc8b0ef
commit 0a042a8e95
5 changed files with 322 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/daedalus_core.c
+43 -43
View File
@@ -291,13 +291,13 @@ static int dispatch_idct8_qpu(daedalus_ctx *ctx,
}
v3d_buffer buf_coeffs = {0}, buf_dst = {0}, buf_meta = {0};
if (v3d_runner_create_buffer(ctx->runner, coeff_bytes, &buf_coeffs)) return -1;
if (v3d_runner_create_buffer(ctx->runner, max_byte_touched, &buf_dst)) {
v3d_runner_destroy_buffer(ctx->runner, &buf_coeffs); return -1;
if (v3d_runner_acquire_buffer(ctx->runner, coeff_bytes, &buf_coeffs)) return -1;
if (v3d_runner_acquire_buffer(ctx->runner, max_byte_touched, &buf_dst)) {
v3d_runner_release_buffer(ctx->runner, &buf_coeffs); return -1;
}
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &buf_meta)) {
v3d_runner_destroy_buffer(ctx->runner, &buf_dst);
v3d_runner_destroy_buffer(ctx->runner, &buf_coeffs); return -1;
if (v3d_runner_acquire_buffer(ctx->runner, meta_bytes, &buf_meta)) {
v3d_runner_release_buffer(ctx->runner, &buf_dst);
v3d_runner_release_buffer(ctx->runner, &buf_coeffs); return -1;
}
/* Upload. Coeffs and meta are straight copies. Dst we copy the
@@ -344,15 +344,15 @@ static int dispatch_idct8_qpu(daedalus_ctx *ctx,
/* Read-back dst. */
memcpy(dst, buf_dst.mapped, max_byte_touched);
v3d_runner_destroy_buffer(ctx->runner, &buf_meta);
v3d_runner_destroy_buffer(ctx->runner, &buf_dst);
v3d_runner_destroy_buffer(ctx->runner, &buf_coeffs);
v3d_runner_release_buffer(ctx->runner, &buf_meta);
v3d_runner_release_buffer(ctx->runner, &buf_dst);
v3d_runner_release_buffer(ctx->runner, &buf_coeffs);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &buf_meta);
v3d_runner_destroy_buffer(ctx->runner, &buf_dst);
v3d_runner_destroy_buffer(ctx->runner, &buf_coeffs);
v3d_runner_release_buffer(ctx->runner, &buf_meta);
v3d_runner_release_buffer(ctx->runner, &buf_dst);
v3d_runner_release_buffer(ctx->runner, &buf_coeffs);
return -1;
}
@@ -424,9 +424,9 @@ static int dispatch_lpf_qpu(daedalus_ctx *ctx, int wd_8,
size_t dst_window_size = hi - lo;
v3d_buffer buf_meta = {0}, buf_dst = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &buf_meta)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_window_size, &buf_dst)) {
v3d_runner_destroy_buffer(ctx->runner, &buf_meta); return -1;
if (v3d_runner_acquire_buffer(ctx->runner, meta_bytes, &buf_meta)) return -1;
if (v3d_runner_acquire_buffer(ctx->runner, dst_window_size, &buf_dst)) {
v3d_runner_release_buffer(ctx->runner, &buf_meta); return -1;
}
memcpy(buf_dst.mapped, dst + lo, dst_window_size);
@@ -468,12 +468,12 @@ static int dispatch_lpf_qpu(daedalus_ctx *ctx, int wd_8,
memcpy(dst + lo, buf_dst.mapped, dst_window_size);
v3d_runner_destroy_buffer(ctx->runner, &buf_dst);
v3d_runner_destroy_buffer(ctx->runner, &buf_meta);
v3d_runner_release_buffer(ctx->runner, &buf_dst);
v3d_runner_release_buffer(ctx->runner, &buf_meta);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &buf_dst);
v3d_runner_destroy_buffer(ctx->runner, &buf_meta);
v3d_runner_release_buffer(ctx->runner, &buf_dst);
v3d_runner_release_buffer(ctx->runner, &buf_meta);
return -1;
}
@@ -509,9 +509,9 @@ static int dispatch_mc_8h_qpu(daedalus_ctx *ctx,
}
v3d_buffer bm = {0}, bd = {0}, bs = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_create_buffer(ctx->runner, src_max, &bs)) { v3d_runner_destroy_buffer(ctx->runner, &bd); v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_acquire_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_acquire_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_release_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_acquire_buffer(ctx->runner, src_max, &bs)) { v3d_runner_release_buffer(ctx->runner, &bd); v3d_runner_release_buffer(ctx->runner, &bm); return -1; }
memcpy(bs.mapped, src, src_max);
memcpy(bd.mapped, dst, dst_max);
@@ -545,14 +545,14 @@ static int dispatch_mc_8h_qpu(daedalus_ctx *ctx,
memcpy(dst, bd.mapped, dst_max);
v3d_runner_destroy_buffer(ctx->runner, &bs);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_release_buffer(ctx->runner, &bs);
v3d_runner_release_buffer(ctx->runner, &bd);
v3d_runner_release_buffer(ctx->runner, &bm);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bs);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_release_buffer(ctx->runner, &bs);
v3d_runner_release_buffer(ctx->runner, &bd);
v3d_runner_release_buffer(ctx->runner, &bm);
return -1;
}
@@ -588,9 +588,9 @@ static int dispatch_cdef_qpu(daedalus_ctx *ctx,
size_t tmp_bytes = tmp_max_u16 * sizeof(uint16_t);
v3d_buffer bm = {0}, bd = {0}, bt = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_create_buffer(ctx->runner, tmp_bytes, &bt)) { v3d_runner_destroy_buffer(ctx->runner, &bd); v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_acquire_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_acquire_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_release_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_acquire_buffer(ctx->runner, tmp_bytes, &bt)) { v3d_runner_release_buffer(ctx->runner, &bd); v3d_runner_release_buffer(ctx->runner, &bm); return -1; }
/* tmp may need padding before block-origin offset (caller-allocated). Just
* copy from caller; we assume meta[i].tmp_off_u16 is consistent with how
@@ -630,14 +630,14 @@ static int dispatch_cdef_qpu(daedalus_ctx *ctx,
memcpy(dst, bd.mapped, dst_max);
v3d_runner_destroy_buffer(ctx->runner, &bt);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_release_buffer(ctx->runner, &bt);
v3d_runner_release_buffer(ctx->runner, &bd);
v3d_runner_release_buffer(ctx->runner, &bm);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bt);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_release_buffer(ctx->runner, &bt);
v3d_runner_release_buffer(ctx->runner, &bd);
v3d_runner_release_buffer(ctx->runner, &bm);
return -1;
}
@@ -670,8 +670,8 @@ static int dispatch_h264_deblock_qpu(daedalus_ctx *ctx,
}
v3d_buffer bm = {0}, bd = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_acquire_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_acquire_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_release_buffer(ctx->runner, &bm); return -1; }
memcpy(bd.mapped, dst, dst_max);
uint32_t *m = bm.mapped;
@@ -706,12 +706,12 @@ static int dispatch_h264_deblock_qpu(daedalus_ctx *ctx,
memcpy(dst, bd.mapped, dst_max);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_release_buffer(ctx->runner, &bd);
v3d_runner_release_buffer(ctx->runner, &bm);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_release_buffer(ctx->runner, &bd);
v3d_runner_release_buffer(ctx->runner, &bm);
return -1;
}