From 1402989cdd4a5b057640144289b194969e73024e Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Mon, 5 Oct 2026 22:11:24 +0000 Subject: [PATCH 1/5] Prover floor: SP1 6.8.1 GPU server memory model from source (the 24 GB panic, the threshold-sized trace buffers), the floor patch for sp1-gpu, the PC 2 toolchain, build and sweep playbooks Co-Authored-By: Claude Fable 5.1 --- docs/analysis/prover-floor.md | 91 +++++++++ .../prover-floor/sp1-gpu-6.8.1-floor.patch | 183 ++++++++++++++++++ tools/prover-floor/make-build-playbook.sh | 72 +++++++ tools/prover-floor/make-measure-playbook.sh | 15 ++ tools/prover-floor/pc2-build-server.ps1 | 60 ++++++ tools/prover-floor/pc2-floor-measure.ps1 | 65 +++++++ tools/prover-floor/pc2-floor-sweep1.ps1 | 65 +++++++ tools/prover-floor/pc2-toolchain.ps1 | 47 +++++ tools/prover-floor/points-sweep1.txt | 9 + tools/prover-floor/points-sweep2.txt | 6 + 10 files changed, 613 insertions(+) create mode 100644 docs/analysis/prover-floor.md create mode 100644 proving/prover-floor/sp1-gpu-6.8.1-floor.patch create mode 100755 tools/prover-floor/make-build-playbook.sh create mode 100755 tools/prover-floor/make-measure-playbook.sh create mode 100644 tools/prover-floor/pc2-build-server.ps1 create mode 100644 tools/prover-floor/pc2-floor-measure.ps1 create mode 100644 tools/prover-floor/pc2-floor-sweep1.ps1 create mode 100644 tools/prover-floor/pc2-toolchain.ps1 create mode 100644 tools/prover-floor/points-sweep1.txt create mode 100644 tools/prover-floor/points-sweep2.txt diff --git a/docs/analysis/prover-floor.md b/docs/analysis/prover-floor.md new file mode 100644 index 000000000..0b2950ca8 --- /dev/null +++ b/docs/analysis/prover-floor.md @@ -0,0 +1,91 @@ +# The prover floor: why a 12 GB card cannot prove on SP1 6.8.1's GPU server, and the patch + +5 October 2026, 22:00 UTC on (the project lead: "execute if it will solve the issue"). Branch `prover-floor` +(worktree `igneum-wt-prover-floor`). The measured facts this starts from: `docs/plans/proving-v1.md` and the +bench-log entry "proving v1" (branch proving-v1): the GPU server holds 13.9 GB for an empty shard, 20.4 GB at the +adopted v1 shard, 28.3 GB flat from 20 M to 60 M cycles, and no environment knob moved the floor. Every figure +below is from the source at tag v6.8.1 (cloned to `vendor/sp1-6.8.1`, gitignored; the fork is the patch +`proving/prover-floor/sp1-gpu-6.8.1-floor.patch`) or from a PC 2 run named in `docs/bench-log.md` +("prover floor"). Sizes in GiB are computed from the source constants (4-byte field elements); sizes in MiB are +measured by `nvidia-smi` at 1 s. + +## Where the server is built and what it reads + +The SDK downloads `sp1_gpu_server_v6.8.1_x86_64.tar.gz` (133,750,780 bytes) from the SP1 release and runs it from +`$HOME/.sp1/bin/sp1-gpu-server` (`crates/cuda/src/server.rs` 19 to 30, 80 to 99). The source is in the same +repository: `sp1-gpu/crates/server` (the binary), built by `.github/workflows/release.yml` 234 to 314 on CUDA +12.8.1 with Go and protoc (`cargo build --release --bin sp1-gpu-server`). The binary takes no options +(`sp1-gpu/crates/server/src/main.rs` 15 to 18: `--version` only) and reads `CUDA_VISIBLE_DEVICES` (32 to 35); +everything else comes from the environment the host process passes it, through `SP1CoreOpts::default()` +(`crates/core/executor/src/opts.rs` 99 to 140: `SHARD_SIZE`, `ELEMENT_THRESHOLD`, `HEIGHT_THRESHOLD`, +`MINIMAL_TRACE_CHUNK_THRESHOLD`, `TRACE_CHUNK_SLOTS`, `FULL_SIZE_SHARDS`) and the worker counts +(`crates/prover/src/worker/config.rs`). + +## The memory model, term by term + +Every device buffer is sized at construction from constants, not from the shard. The server builds the prover at +the first `Setup` request (`sp1-gpu/crates/server/src/server.rs` 126 to 137) through +`cuda_worker_builder_with_machine` (`sp1-gpu/crates/prover_components/src/builder.rs` 102 to 148): + +| Term | Where | Size | On the device | Moves with the shard | +|---|---|---|---|---| +| The gate | `builder.rs` 35 to 39: `gpu_memory_gb = ceil(total / GiB) + 4`; `panic!("Unsupported GPU memory: {gpu_memory_gb}, must be at least 24GB")` when under 24 | a 12 GB card reads 16, a 16 GB card 20: both refused before any allocation | | no | +| The core element threshold | `builder.rs` 41 to 48: `ELEMENT_THRESHOLD` = 2^28 + 2^27 = 402,653,184 elements (`opts.rs` 12) on a card reading over 30 (a 32 GB card reads 36); minus 2^26 + 2^25 + 2^24 = 285,212,672 on a card reading 24 to 30 (a 24 GB card). The environment's `ELEMENT_THRESHOLD` is read at `opts.rs` 129 and then OVERWRITTEN at `builder.rs` 48, which is why the sweep's `ELEMENT_THRESHOLD` rows changed nothing; `HEIGHT_THRESHOLD` survives (it is not overwritten), which is why the 2^25 + 2^20 row did | sets the next two terms | | no | +| The core trace area, one per shard in flight | `builder.rs` 70 to 71: `num_elts = element_threshold + 2^21` (`CORE_LOG_STACKING_HEIGHT` 21, `crates/prover/src/components.rs` 16) = 404,750,336; allocated on the device at `sp1-gpu/crates/jagged_tracegen/src/lib.rs` 484 to 500 (`allocate_and_initialize_traces`: `max_trace_size` felts + `max_trace_size / 2` u32 column index + 2^14 u32) | 6 bytes an element: **2.26 GiB** for the full threshold, 1.59 GiB for the 24 GB threshold | yes, in full, whatever the shard holds | no | +| The program's preprocessed traces (the proving key) | `sp1-gpu/crates/shard_prover/src/setup.rs` 47 to 58 and 107: the same `allocate_and_initialize_traces(max_trace_size)` at `Setup`, kept in the key cache for the connection's life (`server.rs` 139 to 143) | another **2.26 GiB**, held from `Setup` on | yes | no | +| The pinned host trace buffers | `sp1-gpu/crates/prover_components/src/components.rs` 99 to 103: 4 `PinnedBuffer` of `max_trace_size` felts per prover (core 4 x 1.51 GiB, recursion 4 x 0.5 GiB, shrink 4 x 0.125 GiB, wrap 4 x 0.32 GiB) | 9.8 GiB of pinned host RAM, not device memory (the WSL2 working set the bench saw) | no | no | +| The recursion trace area | `builder.rs` 15 and 95: `RECURSION_TRACE_ALLOCATION` = 2^27 elements, one per recursion tracegen (the recursion program's key at setup and its shard at prove) | 0.75 GiB each | yes | no | +| The shrink and wrap provers | `builder.rs` 16, 19, 117 to 127: 2^25 and 85,376,340 elements, built at `Setup` for every proof mode, used only by the Groth16 and PLONK path | host pinned at build; device only when a wrap runs (never, for a compressed proof) | no | no | +| The codewords (LDE) and the Merkle trees | `sp1-gpu/crates/basefold/src/fri.rs` 92 to 97: every stacked column of 2^21 rows encoded to 2^(21 + 1) rows (`log_blowup` 1); kept until the query phase unless `drop_ldes` (`builder.rs` 52: only on a 24 GB card with `FULL_SIZE_SHARDS`); the preprocessed codewords live in the key | 2 x the padded trace, so up to 2 x the term above | yes | yes, with the padded trace | +| The LogUp GKR layers | `builder.rs` 51: `recompute_gkr_trace = false`, so the first layer stays materialised (`sp1-gpu/crates/logup_gkr/src/tracegen.rs` 169 to 224) | of the order of the interaction count | yes | yes | +| The allocator | `sp1-gpu/crates/cuda/src/task.rs` 152 and 196: the device's default `cudaMallocAsync` pool with its release threshold at `u64::MAX`, so nothing freed is ever returned to the driver: `nvidia-smi` reads the high-water mark of everything live at once | | | | + +So at zero cycles the server already holds the proving key's 2.26 GiB, the shard's 2.26 GiB (both allocated at the +threshold, not at the shard's rows), their codewords and trees, and the recursion program's key and traces (2 x +0.75 GiB and their codewords): the 13.9 GB floor. The shard's own content only adds to the codewords, the GKR +layers and the working buffers, which is the 13.9 to 20.4 GB step from 0.3 M to 4.7 M cycles, and the flat 28.3 GB +from 20 M cycles is the threshold's padded area reached. The witness (5 to 22 KB) never appears. + +## What the patch does (`proving/prover-floor/sp1-gpu-6.8.1-floor.patch`, three files) + +1. `builder.rs`: the panic is gone; the card's memory (or `SP1_GPU_MEMORY_BUDGET_GB`) picks the element threshold + from a tier table (`element_threshold_for_budget`: over 30 as read, the full 402.6 M; 24 to 30, upstream's 24 GB + figure; 18 to 24 (a 16 GB card), 2^27 + 2^26 = 201.3 M; under 18 (a 12 GB card), 2^27 = 134.2 M); + `SP1_GPU_ELEMENT_THRESHOLD` sets it directly and `SP1_GPU_RECURSION_TRACE_ALLOCATION` the recursion buffer. + The chosen numbers are printed as a `FLOOR opts` line. Every other option is as upstream. +2. `jagged_tracegen/src/lib.rs`: with `SP1_GPU_FLOOR_LOG` set, every trace allocation prints its capacity and, + after the shard's traces are in, the elements actually used and the device memory in use. +3. `server.rs`: a `FLOOR memory` line (device used, free, total) after `Setup` and after every proof, with the + proof's time. + +Nothing in the proof changes: the element threshold only moves where the executor splits shards, exactly what +upstream's own 24 GB tier does with the same verifier and the same keys; the recursion program, the verifying key +and the pinned guest ids are untouched. The unpatched verifier (the pv1 host's SDK) is the one that verifies every +measured proof below. + +## The build (PC 2, WSL2 Ubuntu-24.04, job `floor-toolchain-1` then the build job) + +Toolchain found 22:10Z (job `floor-toolchain-1`, 4 s): nvcc 12.8 at `/usr/local/cuda-12.8`, cmake 3.28.3, gcc 13.3, +clang 18, protoc 3.21.12, cargo 1.99.0, no Go. The release workflow installs Go for the server's `native-gnark` +feature (the Groth16 and PLONK wrap through gnark), which a compressed proof never runs, so the build drops that +feature from `sp1-gpu/crates/server/Cargo.toml` and nothing else. `CUDA_ARCHS=86,89,120` (consequences reviewer +C26): the 12 GB tier is sm_86 (RTX 3060) and sm_89 (RTX 4070), the 16 GB tier sm_89 and sm_120 (RTX 5080), PC 2's +5090 is sm_120; the stock server lists sm_80, 86, 89, 90, 100 and 120, which a shipped build repeats. The recipe: +`tools/prover-floor/pc2-build-server.ps1` (generated by `make-build-playbook.sh` from the patch, so the two cannot +drift): clone the tag, `git apply` the patch, `touch` the three files, `cargo build --release --bin sp1-gpu-server` +niced with 8 jobs into `/opt/igneum-floor/target`, the binary copied to `/opt/igneum-floor/home/.sp1/bin/` (the SDK +spawns the server it finds under `$HOME/.sp1/bin`, so `HOME=/opt/igneum-floor/home` selects it and the live +`/root/.sp1/bin/sp1-gpu-server` stays as it is). + +What a measurement on PC 2 can and cannot say (C26). The server's allocation pattern is deterministic in the +budget it is given, so a run with `SP1_GPU_MEMORY_BUDGET_GB=12` on the 5090 shows the peak a 12 GB card's build +would ask for; it does not show that a 3060 proves it in time, nor what the card's display and driver hold. The +public line keeps "24 GB" until the on-order 12 GB card runs the same fixture. Every row names the arch list and +the card. + +What shipping it costs (C26). A patched server means the project signs and distributes its own build of SP1's +prover: the WSL2 package, the DMG's prover inputs, the K1-signed inputs and `evidence.md` carry it, and every SP1 +upgrade repeats the clone, patch, build and measurement. The verifying key and the pinned guest ids do not move +(the patch changes buffer sizes and the shard split, not the circuits), which the `verify-segment` and `--mode +compressed` VERIFIED lines of the unpatched host show on every row below. The packaging path is a row for the +proving plan before 0.3.12, not this branch. diff --git a/proving/prover-floor/sp1-gpu-6.8.1-floor.patch b/proving/prover-floor/sp1-gpu-6.8.1-floor.patch new file mode 100644 index 000000000..8a355f920 --- /dev/null +++ b/proving/prover-floor/sp1-gpu-6.8.1-floor.patch @@ -0,0 +1,183 @@ +diff --git a/sp1-gpu/crates/jagged_tracegen/src/lib.rs b/sp1-gpu/crates/jagged_tracegen/src/lib.rs +index 579f70a..88bfc79 100644 +--- a/sp1-gpu/crates/jagged_tracegen/src/lib.rs ++++ b/sp1-gpu/crates/jagged_tracegen/src/lib.rs +@@ -494,6 +494,11 @@ async fn allocate_and_initialize_traces( + + let total_gb = total_bytes as f64 / (1 << 30) as f64; + tracing::debug!("Allocating {:?} GB of traces", total_gb); ++ if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() { ++ eprintln!( ++ "FLOOR tracegen alloc capacity_elements={max_trace_size} bytes={total_bytes} ({total_gb:.3} GB)" ++ ); ++ } + let mut dense_data: Buffer = + Buffer::with_capacity_in(max_trace_size, backend.clone()); + let mut col_index: Buffer = +@@ -1002,6 +1007,18 @@ pub async fn full_tracegen>( + ) + .await; + ++ if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() { ++ let dense = jagged_mle.dense(); ++ let (free, total) = sp1_gpu_cudart::cuda_memory_info().unwrap_or((0, 0)); ++ eprintln!( ++ "FLOOR tracegen used preprocessed_elements={} main_elements={} dense_len={} capacity_elements={max_trace_size} device_used_mib={}", ++ dense.preprocessed_offset, ++ dense.main_size(), ++ dense.dense.len(), ++ (total - free) >> 20 ++ ); ++ } ++ + (public_values, jagged_mle, chip_set, permit) + } + +diff --git a/sp1-gpu/crates/prover_components/src/builder.rs b/sp1-gpu/crates/prover_components/src/builder.rs +index 5dccd9d..574d4fa 100644 +--- a/sp1-gpu/crates/prover_components/src/builder.rs ++++ b/sp1-gpu/crates/prover_components/src/builder.rs +@@ -23,28 +23,75 @@ use crate::{ + SP1CudaProverComponents, + }; + ++/// Igneum prover-floor patch (5 October 2026). Upstream sizes every device buffer for a 24 GB card or larger ++/// and panics below that, whatever the shard. Here the card's memory (or `SP1_GPU_MEMORY_BUDGET_GB`) picks a ++/// tier, and `SP1_GPU_ELEMENT_THRESHOLD` / `SP1_GPU_RECURSION_TRACE_ALLOCATION` set the two buffers directly. ++/// The proof format, the verifier and the program ids do not change: the element threshold only decides where ++/// the executor splits shards, as upstream's own 24 GB tier already does. ++fn env_usize(name: &str) -> Option { ++ std::env::var(name).ok().and_then(|s| s.parse::().ok()) ++} ++ ++fn env_f64(name: &str) -> Option { ++ std::env::var(name).ok().and_then(|s| s.parse::().ok()) ++} ++ ++/// The core element threshold for a memory budget in GB (upstream's own figure for the budget, +4, as it ++/// computed it: a 32 GB card is 36, a 24 GB card 28, a 16 GB card 20, a 12 GB card 16). ++pub fn element_threshold_for_budget(gpu_memory_gb: usize, full_size_shards: bool) -> u64 { ++ if gpu_memory_gb > 30 || (full_size_shards && gpu_memory_gb >= 24) { ++ ELEMENT_THRESHOLD ++ } else if gpu_memory_gb >= 24 { ++ ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24) ++ } else if gpu_memory_gb >= 18 { ++ (1 << 27) + (1 << 26) ++ } else { ++ 1 << 27 ++ } ++} ++ ++/// The recursion trace allocation (elements) for a memory budget. ++pub fn recursion_trace_allocation_for_budget(gpu_memory_gb: usize) -> usize { ++ if gpu_memory_gb >= 24 { ++ RECURSION_TRACE_ALLOCATION ++ } else { ++ RECURSION_TRACE_ALLOCATION ++ } ++} ++ ++pub fn gpu_memory_gb() -> usize { ++ let gb = 1024.0 * 1024.0 * 1024.0; ++ match env_f64("SP1_GPU_MEMORY_BUDGET_GB") { ++ Some(b) => (b.ceil() as usize) + 4, ++ None => (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4, ++ } ++} ++ ++pub fn recursion_trace_allocation() -> usize { ++ env_usize("SP1_GPU_RECURSION_TRACE_ALLOCATION") ++ .unwrap_or_else(|| recursion_trace_allocation_for_budget(gpu_memory_gb())) ++} ++ + pub fn local_gpu_opts() -> SP1CoreOpts { + let mut opts = SP1CoreOpts::default(); + + let log2_shard_size = 24; + opts.shard_size = 1 << log2_shard_size; + +- let gb = 1024.0 * 1024.0 * 1024.0; +- +- // Get the amount of memory on the GPU. +- let gpu_memory_gb: usize = (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4; +- +- if gpu_memory_gb < 24 { +- panic!("Unsupported GPU memory: {gpu_memory_gb}, must be at least 24GB"); +- } ++ // The card's memory plus 4, as upstream computed it (a 32 GB card reads 36), or the budget given. ++ let gpu_memory_gb = gpu_memory_gb(); + +- let shard_threshold = if !opts.full_size_shards && gpu_memory_gb <= 30 { +- ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24) +- } else { +- ELEMENT_THRESHOLD ++ let shard_threshold = match env_usize("SP1_GPU_ELEMENT_THRESHOLD") { ++ Some(t) => t as u64, ++ None => element_threshold_for_budget(gpu_memory_gb, opts.full_size_shards), + }; ++ let height_threshold = opts.sharding_threshold.height_threshold; + +- tracing::debug!("Shard threshold: {shard_threshold}"); ++ eprintln!( ++ "FLOOR opts gpu_memory_gb={gpu_memory_gb} element_threshold={shard_threshold} height_threshold={height_threshold} recursion_trace_allocation={} full_size_shards={}", ++ recursion_trace_allocation(), ++ opts.full_size_shards ++ ); + opts.sharding_threshold.element_threshold = shard_threshold; + + opts.global_dependencies_opt = true; +@@ -92,7 +139,7 @@ pub async fn recursion_prover_and_verifier( + ) { + let recursion_verifier = SP1CudaProverComponents::compress_verifier(); + ( +- new_cuda_prover(&recursion_verifier, RECURSION_TRACE_ALLOCATION, 4, false, false, scope) ++ new_cuda_prover(&recursion_verifier, recursion_trace_allocation(), 4, false, false, scope) + .await, + recursion_verifier, + ) +diff --git a/sp1-gpu/crates/server/src/server.rs b/sp1-gpu/crates/server/src/server.rs +index 4035f1f..0d0d907 100644 +--- a/sp1-gpu/crates/server/src/server.rs ++++ b/sp1-gpu/crates/server/src/server.rs +@@ -157,6 +157,7 @@ impl Server { + }; + let pk = CachedProgram { elf: Arc::new(Elf::Dynamic(elf.into())), vk: vk.clone() }; + ctx.pk_cache.insert(elf_hash, pk); ++ floor_memory_line("after setup"); + Response::Setup { id: elf_hash, vk } + } + Request::Destroy { key } => { +@@ -177,15 +178,31 @@ impl Server { + ); + }; + let context = SP1Context::builder().proof_nonce(proof_nonce).build(); +- match prover.prove_with_mode(&cached.elf, stdin, context, mode).await { ++ let started = std::time::Instant::now(); ++ let response = match prover.prove_with_mode(&cached.elf, stdin, context, mode).await { + Ok(proof) => Response::Proof { proof }, + Err(e) => Response::ProverError(e.to_string()), +- } ++ }; ++ floor_memory_line(&format!("after prove {:?} in {:.1} s", mode, started.elapsed().as_secs_f64())); ++ response + } + } + } + } + ++/// Igneum prover-floor patch: the device memory in use (total minus free, as the driver reports it) at the ++/// points that bound a proof, so a run's log carries the terms of the peak without a sampler. ++fn floor_memory_line(what: &str) { ++ if let Ok((free, total)) = sp1_gpu_cudart::cuda_memory_info() { ++ eprintln!( ++ "FLOOR memory {what}: device_used_mib={} free_mib={} total_mib={}", ++ (total - free) >> 20, ++ free >> 20, ++ total >> 20 ++ ); ++ } ++} ++ + fn sha256(data: &[u8]) -> [u8; 32] { + use sha2::{Digest, Sha256}; + let mut hasher = Sha256::new(); diff --git a/tools/prover-floor/make-build-playbook.sh b/tools/prover-floor/make-build-playbook.sh new file mode 100755 index 000000000..07f0d117c --- /dev/null +++ b/tools/prover-floor/make-build-playbook.sh @@ -0,0 +1,72 @@ +#!/usr/bin/env bash +# Writes tools/prover-floor/pc2-build-server.ps1 with proving/prover-floor/sp1-gpu-6.8.1-floor.patch embedded +# (base64), so the playbook and the patch cannot drift. Run after every change to the patch. +set -euo pipefail +HERE="$(cd "$(dirname "$0")" && pwd)"; ROOT="$(cd "$HERE/../.." && pwd)" +PATCH="$ROOT/proving/prover-floor/sp1-gpu-6.8.1-floor.patch" +SHA="$(shasum -a 256 "$PATCH" | cut -c1-64)" +B64="$(base64 < "$PATCH" | tr -d '\n')" +OUT="$HERE/pc2-build-server.ps1" +cat > "$OUT" <\$null); if (\$w) { (\$w -replace "\`0", '').Trim() } else { '/mnt/c' + (\$p.Substring(2) -replace '\\\\', '/') } } +\$patchB64 = '$B64' +[IO.File]::WriteAllBytes((Join-Path \$job 'floor.patch'), [Convert]::FromBase64String(\$patchB64)) +\$patchW = WslPath (Join-Path \$job 'floor.patch') +\$bash = @' +set -uo pipefail +export PATH="\$HOME/.cargo/bin:/usr/local/go/bin:\$PATH" +CUDA_DIR="\$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)" +if [ -z "\$CUDA_DIR" ]; then echo "RESULT build_failed no /usr/local/cuda-12.*"; exit 2; fi +export CUDA_PATH="\$CUDA_DIR" CUDACXX="\$CUDA_DIR/bin/nvcc" PATH="\$CUDA_DIR/bin:\$PATH" LD_LIBRARY_PATH="\$CUDA_DIR/lib64:/usr/lib/wsl/lib:\${LD_LIBRARY_PATH:-}" +stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } +FLOOR=/opt/igneum-floor; SRC=\$FLOOR/sp1; mkdir -p \$FLOOR/bin \$FLOOR/home/.sp1/bin \$FLOOR/logs +PATCH="PATCH_PATH_PLACEHOLDER" +echo "RESULT patch_sha256 \$(sha256sum "\$PATCH" | cut -c1-64) expected $SHA" +echo "RESULT toolchain nvcc=\$(nvcc --version | grep -o 'release [0-9.]*') cargo=\$(cargo --version) go=\$(go version 2>/dev/null || echo MISSING) protoc=\$(protoc --version 2>/dev/null || echo MISSING) cmake=\$(cmake --version 2>/dev/null | head -1 || echo MISSING) nproc=\$(nproc) disk_avail=\$(df -BG /opt | awk 'NR==2 {print \$4}')" +if [ ! -d "\$SRC/.git" ]; then + echo "STAGE clone \$(stamp)" + git clone -q --depth 1 --branch v6.8.1 https://github.com/succinctlabs/sp1 "\$SRC" 2>&1 | tail -2 || { echo "RESULT build_failed clone"; exit 2; } +fi +cd "\$SRC" +git checkout -q -- . && git clean -qfd sp1-gpu/crates >/dev/null 2>&1 +echo "RESULT source \$(git describe --tags --always) \$(git rev-parse HEAD)" +git apply "\$PATCH" || { echo "RESULT build_failed patch does not apply"; exit 2; } +touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs +echo "RESULT patched \$(git diff --stat | tail -1)" +if ! command -v go >/dev/null 2>&1; then + sed -i 's/sp1-prover = { workspace = true, features = \["native-gnark"\] }/sp1-prover = { workspace = true }/' sp1-gpu/crates/server/Cargo.toml + echo "RESULT native_gnark dropped: no go toolchain on PC 2 (the gnark wrap is not used by compressed proofs)" +fi +export CUDA_ARCHS=86,89,120 CARGO_TARGET_DIR=\$FLOOR/target +JOBS=8 +echo "STAGE build \$(stamp) jobs=\$JOBS" +t0=\$(date +%s) +nice -n 19 cargo build --release --bin sp1-gpu-server -j \$JOBS > \$FLOOR/logs/build-\$(date -u +%Y%m%dT%H%M%SZ).log 2>&1 & +BP=\$! +LOG=\$(ls -t \$FLOOR/logs/build-*.log | head -1) +while kill -0 \$BP 2>/dev/null; do sleep 120; echo "STAGE building \$(stamp) \$(( (\$(date +%s) - t0) / 60 )) min: \$(grep -c '^ Compiling' "\$LOG") crates compiled, last: \$(grep '^ Compiling' "\$LOG" | tail -1 | tr -s ' ' | cut -c1-80)"; done +wait \$BP; rc=\$? +echo "RESULT build_exit \$rc time_s=\$(( \$(date +%s) - t0 )) crates=\$(grep -c '^ Compiling' "\$LOG")" +if [ \$rc -ne 0 ]; then echo "RESULT build_failed"; grep -n -B2 -A12 '^error' "\$LOG" | head -80; exit 2; fi +BIN=\$FLOOR/target/release/sp1-gpu-server +cp "\$BIN" \$FLOOR/bin/sp1-gpu-server && cp "\$BIN" \$FLOOR/home/.sp1/bin/sp1-gpu-server && chmod +x \$FLOOR/bin/sp1-gpu-server \$FLOOR/home/.sp1/bin/sp1-gpu-server +echo "RESULT binary bytes=\$(stat -c %s "\$BIN") sha256=\$(sha256sum "\$BIN" | cut -c1-64) version=\$(\$BIN --version 2>/dev/null)" +echo "RESULT elf_targets \$(cuobjdump --list-elf "\$BIN" 2>/dev/null | grep -o 'sm_[0-9]*' | sort -u | tr '\n' ' ')" +echo "RESULT live_server_untouched sha256=\$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) (expected c2642ad1c42e85d8)" +echo "RESULT end \$(stamp)" +'@ +\$bash = \$bash.Replace('PATCH_PATH_PLACEHOLDER', \$patchW) +\$bashFile = Join-Path \$job 'build.sh' +[IO.File]::WriteAllText(\$bashFile, (\$bash -replace "\`r\`n", "\`n"), (New-Object System.Text.UTF8Encoding \$false)) +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath \$bashFile) 2>&1 | ForEach-Object { (\$_ -replace "\`0", '') } +"RESULT end \$(Stamp)" +PS +echo "wrote $OUT ($(wc -c < "$OUT") bytes, patch $SHA)" diff --git a/tools/prover-floor/make-measure-playbook.sh b/tools/prover-floor/make-measure-playbook.sh new file mode 100755 index 000000000..b743de6dd --- /dev/null +++ b/tools/prover-floor/make-measure-playbook.sh @@ -0,0 +1,15 @@ +#!/usr/bin/env bash +# Writes a measurement playbook from pc2-floor-measure.ps1 with the point list given (one `run name fixture env...` +# per line, read from the file in $1), into $2. Fixtures: $EMPTY (block 83616, an empty live shard), $V1 +# (fees-v1-shards2 shard 0, the adopted v1 shard), $FULL (block-338-shard1, the prototype shard), $ONE (block 56). +set -euo pipefail +HERE="$(cd "$(dirname "$0")" && pwd)" +POINTS="$(tr '\n' ';' < "$1" | sed 's/;$//')" +python3 - "$HERE/pc2-floor-measure.ps1" "$2" "$POINTS" <<'PY' +import sys +src, out, points = sys.argv[1], sys.argv[2], sys.argv[3] +s = open(src).read() +s = s.replace("'POINTS_PLACEHOLDER'", "'" + points.replace("'", "''") + "'") +open(out, 'w').write(s) +print("wrote", out, "points:", points.count(';') + 1) +PY diff --git a/tools/prover-floor/pc2-build-server.ps1 b/tools/prover-floor/pc2-build-server.ps1 new file mode 100644 index 000000000..f1359a339 --- /dev/null +++ b/tools/prover-floor/pc2-build-server.ps1 @@ -0,0 +1,60 @@ +# Prover floor (5 October 2026): builds sp1-gpu-server 6.8.1 from source with the Igneum floor patch on PC 2 inside +# WSL2 Ubuntu-24.04 as root, into /opt/igneum-floor (the live /root/.sp1/bin/sp1-gpu-server and /opt/igneum are +# never touched). CPU only: the miners keep mining, the card is not used. Generated by make-build-playbook.sh; +# patch sha256 700173fe2d852a382f050b36437612ea70f9513fa93093e6f86ea72b5e9ebf9b. CUDA_ARCHS=86,89,120 (the 12 GB tier is sm_86 (3060) and sm_89 (4070), the 16 GB tier sm_89 and sm_120; PC 2 runs sm_120; a shipped build lists every target the stock server does: 80, 86, 89, 90, 100, 120). +$ErrorActionPreference = 'Continue' +function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } +"RESULT start $(Stamp)" +$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor' }; New-Item -ItemType Directory -Force -Path $job | Out-Null +function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } +$patchB64 = 'diff --git a/sp1-gpu/crates/jagged_tracegen/src/lib.rs b/sp1-gpu/crates/jagged_tracegen/src/lib.rs
index 579f70a..88bfc79 100644
--- a/sp1-gpu/crates/jagged_tracegen/src/lib.rs
+++ b/sp1-gpu/crates/jagged_tracegen/src/lib.rs
@@ -494,6 +494,11 @@ async fn allocate_and_initialize_traces(
 
     let total_gb = total_bytes as f64 / (1 << 30) as f64;
     tracing::debug!("Allocating {:?} GB of traces", total_gb);
+    if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() {
+        eprintln!(
+            "FLOOR tracegen alloc capacity_elements={max_trace_size} bytes={total_bytes} ({total_gb:.3} GB)"
+        );
+    }
     let mut dense_data: Buffer<Felt, TaskScope> =
         Buffer::with_capacity_in(max_trace_size, backend.clone());
     let mut col_index: Buffer<u32, TaskScope> =
@@ -1002,6 +1007,18 @@ pub async fn full_tracegen<A: CudaTracegenAir<Felt>>(
     )
     .await;
 
+    if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() {
+        let dense = jagged_mle.dense();
+        let (free, total) = sp1_gpu_cudart::cuda_memory_info().unwrap_or((0, 0));
+        eprintln!(
+            "FLOOR tracegen used preprocessed_elements={} main_elements={} dense_len={} capacity_elements={max_trace_size} device_used_mib={}",
+            dense.preprocessed_offset,
+            dense.main_size(),
+            dense.dense.len(),
+            (total - free) >> 20
+        );
+    }
+
     (public_values, jagged_mle, chip_set, permit)
 }
 
diff --git a/sp1-gpu/crates/prover_components/src/builder.rs b/sp1-gpu/crates/prover_components/src/builder.rs
index 5dccd9d..574d4fa 100644
--- a/sp1-gpu/crates/prover_components/src/builder.rs
+++ b/sp1-gpu/crates/prover_components/src/builder.rs
@@ -23,28 +23,75 @@ use crate::{
     SP1CudaProverComponents,
 };
 
+/// Igneum prover-floor patch (5 October 2026). Upstream sizes every device buffer for a 24 GB card or larger
+/// and panics below that, whatever the shard. Here the card's memory (or `SP1_GPU_MEMORY_BUDGET_GB`) picks a
+/// tier, and `SP1_GPU_ELEMENT_THRESHOLD` / `SP1_GPU_RECURSION_TRACE_ALLOCATION` set the two buffers directly.
+/// The proof format, the verifier and the program ids do not change: the element threshold only decides where
+/// the executor splits shards, as upstream's own 24 GB tier already does.
+fn env_usize(name: &str) -> Option<usize> {
+    std::env::var(name).ok().and_then(|s| s.parse::<usize>().ok())
+}
+
+fn env_f64(name: &str) -> Option<f64> {
+    std::env::var(name).ok().and_then(|s| s.parse::<f64>().ok())
+}
+
+/// The core element threshold for a memory budget in GB (upstream's own figure for the budget, +4, as it
+/// computed it: a 32 GB card is 36, a 24 GB card 28, a 16 GB card 20, a 12 GB card 16).
+pub fn element_threshold_for_budget(gpu_memory_gb: usize, full_size_shards: bool) -> u64 {
+    if gpu_memory_gb > 30 || (full_size_shards && gpu_memory_gb >= 24) {
+        ELEMENT_THRESHOLD
+    } else if gpu_memory_gb >= 24 {
+        ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24)
+    } else if gpu_memory_gb >= 18 {
+        (1 << 27) + (1 << 26)
+    } else {
+        1 << 27
+    }
+}
+
+/// The recursion trace allocation (elements) for a memory budget.
+pub fn recursion_trace_allocation_for_budget(gpu_memory_gb: usize) -> usize {
+    if gpu_memory_gb >= 24 {
+        RECURSION_TRACE_ALLOCATION
+    } else {
+        RECURSION_TRACE_ALLOCATION
+    }
+}
+
+pub fn gpu_memory_gb() -> usize {
+    let gb = 1024.0 * 1024.0 * 1024.0;
+    match env_f64("SP1_GPU_MEMORY_BUDGET_GB") {
+        Some(b) => (b.ceil() as usize) + 4,
+        None => (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4,
+    }
+}
+
+pub fn recursion_trace_allocation() -> usize {
+    env_usize("SP1_GPU_RECURSION_TRACE_ALLOCATION")
+        .unwrap_or_else(|| recursion_trace_allocation_for_budget(gpu_memory_gb()))
+}
+
 pub fn local_gpu_opts() -> SP1CoreOpts {
     let mut opts = SP1CoreOpts::default();
 
     let log2_shard_size = 24;
     opts.shard_size = 1 << log2_shard_size;
 
-    let gb = 1024.0 * 1024.0 * 1024.0;
-
-    // Get the amount of memory on the GPU.
-    let gpu_memory_gb: usize = (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4;
-
-    if gpu_memory_gb < 24 {
-        panic!("Unsupported GPU memory: {gpu_memory_gb}, must be at least 24GB");
-    }
+    // The card's memory plus 4, as upstream computed it (a 32 GB card reads 36), or the budget given.
+    let gpu_memory_gb = gpu_memory_gb();
 
-    let shard_threshold = if !opts.full_size_shards && gpu_memory_gb <= 30 {
-        ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24)
-    } else {
-        ELEMENT_THRESHOLD
+    let shard_threshold = match env_usize("SP1_GPU_ELEMENT_THRESHOLD") {
+        Some(t) => t as u64,
+        None => element_threshold_for_budget(gpu_memory_gb, opts.full_size_shards),
     };
+    let height_threshold = opts.sharding_threshold.height_threshold;
 
-    tracing::debug!("Shard threshold: {shard_threshold}");
+    eprintln!(
+        "FLOOR opts gpu_memory_gb={gpu_memory_gb} element_threshold={shard_threshold} height_threshold={height_threshold} recursion_trace_allocation={} full_size_shards={}",
+        recursion_trace_allocation(),
+        opts.full_size_shards
+    );
     opts.sharding_threshold.element_threshold = shard_threshold;
 
     opts.global_dependencies_opt = true;
@@ -92,7 +139,7 @@ pub async fn recursion_prover_and_verifier(
 ) {
     let recursion_verifier = SP1CudaProverComponents::compress_verifier();
     (
-        new_cuda_prover(&recursion_verifier, RECURSION_TRACE_ALLOCATION, 4, false, false, scope)
+        new_cuda_prover(&recursion_verifier, recursion_trace_allocation(), 4, false, false, scope)
             .await,
         recursion_verifier,
     )
diff --git a/sp1-gpu/crates/server/src/server.rs b/sp1-gpu/crates/server/src/server.rs
index 4035f1f..0d0d907 100644
--- a/sp1-gpu/crates/server/src/server.rs
+++ b/sp1-gpu/crates/server/src/server.rs
@@ -157,6 +157,7 @@ impl Server {
                 };
                 let pk = CachedProgram { elf: Arc::new(Elf::Dynamic(elf.into())), vk: vk.clone() };
                 ctx.pk_cache.insert(elf_hash, pk);
+                floor_memory_line("after setup");
                 Response::Setup { id: elf_hash, vk }
             }
             Request::Destroy { key } => {
@@ -177,15 +178,31 @@ impl Server {
                     );
                 };
                 let context = SP1Context::builder().proof_nonce(proof_nonce).build();
-                match prover.prove_with_mode(&cached.elf, stdin, context, mode).await {
+                let started = std::time::Instant::now();
+                let response = match prover.prove_with_mode(&cached.elf, stdin, context, mode).await {
                     Ok(proof) => Response::Proof { proof },
                     Err(e) => Response::ProverError(e.to_string()),
-                }
+                };
+                floor_memory_line(&format!("after prove {:?} in {:.1} s", mode, started.elapsed().as_secs_f64()));
+                response
             }
         }
     }
 }
 
+/// Igneum prover-floor patch: the device memory in use (total minus free, as the driver reports it) at the
+/// points that bound a proof, so a run's log carries the terms of the peak without a sampler.
+fn floor_memory_line(what: &str) {
+    if let Ok((free, total)) = sp1_gpu_cudart::cuda_memory_info() {
+        eprintln!(
+            "FLOOR memory {what}: device_used_mib={} free_mib={} total_mib={}",
+            (total - free) >> 20,
+            free >> 20,
+            total >> 20
+        );
+    }
+}
+
 fn sha256(data: &[u8]) -> [u8; 32] {
     use sha2::{Digest, Sha256};
     let mut hasher = Sha256::new();
' +[IO.File]::WriteAllBytes((Join-Path $job 'floor.patch'), [Convert]::FromBase64String($patchB64)) +$patchW = WslPath (Join-Path $job 'floor.patch') +$bash = @' +set -uo pipefail +export PATH="$HOME/.cargo/bin:/usr/local/go/bin:$PATH" +CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)" +if [ -z "$CUDA_DIR" ]; then echo "RESULT build_failed no /usr/local/cuda-12.*"; exit 2; fi +export CUDA_PATH="$CUDA_DIR" CUDACXX="$CUDA_DIR/bin/nvcc" PATH="$CUDA_DIR/bin:$PATH" LD_LIBRARY_PATH="$CUDA_DIR/lib64:/usr/lib/wsl/lib:${LD_LIBRARY_PATH:-}" +stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } +FLOOR=/opt/igneum-floor; SRC=$FLOOR/sp1; mkdir -p $FLOOR/bin $FLOOR/home/.sp1/bin $FLOOR/logs +PATCH="PATCH_PATH_PLACEHOLDER" +echo "RESULT patch_sha256 $(sha256sum "$PATCH" | cut -c1-64) expected 700173fe2d852a382f050b36437612ea70f9513fa93093e6f86ea72b5e9ebf9b" +echo "RESULT toolchain nvcc=$(nvcc --version | grep -o 'release [0-9.]*') cargo=$(cargo --version) go=$(go version 2>/dev/null || echo MISSING) protoc=$(protoc --version 2>/dev/null || echo MISSING) cmake=$(cmake --version 2>/dev/null | head -1 || echo MISSING) nproc=$(nproc) disk_avail=$(df -BG /opt | awk 'NR==2 {print $4}')" +if [ ! -d "$SRC/.git" ]; then + echo "STAGE clone $(stamp)" + git clone -q --depth 1 --branch v6.8.1 https://github.com/succinctlabs/sp1 "$SRC" 2>&1 | tail -2 || { echo "RESULT build_failed clone"; exit 2; } +fi +cd "$SRC" +git checkout -q -- . && git clean -qfd sp1-gpu/crates >/dev/null 2>&1 +echo "RESULT source $(git describe --tags --always) $(git rev-parse HEAD)" +git apply "$PATCH" || { echo "RESULT build_failed patch does not apply"; exit 2; } +touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs +echo "RESULT patched $(git diff --stat | tail -1)" +if ! command -v go >/dev/null 2>&1; then + sed -i 's/sp1-prover = { workspace = true, features = \["native-gnark"\] }/sp1-prover = { workspace = true }/' sp1-gpu/crates/server/Cargo.toml + echo "RESULT native_gnark dropped: no go toolchain on PC 2 (the gnark wrap is not used by compressed proofs)" +fi +export CUDA_ARCHS=86,89,120 CARGO_TARGET_DIR=$FLOOR/target +JOBS=8 +echo "STAGE build $(stamp) jobs=$JOBS" +t0=$(date +%s) +nice -n 19 cargo build --release --bin sp1-gpu-server -j $JOBS > $FLOOR/logs/build-$(date -u +%Y%m%dT%H%M%SZ).log 2>&1 & +BP=$! +LOG=$(ls -t $FLOOR/logs/build-*.log | head -1) +while kill -0 $BP 2>/dev/null; do sleep 120; echo "STAGE building $(stamp) $(( ($(date +%s) - t0) / 60 )) min: $(grep -c '^ Compiling' "$LOG") crates compiled, last: $(grep '^ Compiling' "$LOG" | tail -1 | tr -s ' ' | cut -c1-80)"; done +wait $BP; rc=$? +echo "RESULT build_exit $rc time_s=$(( $(date +%s) - t0 )) crates=$(grep -c '^ Compiling' "$LOG")" +if [ $rc -ne 0 ]; then echo "RESULT build_failed"; grep -n -B2 -A12 '^error' "$LOG" | head -80; exit 2; fi +BIN=$FLOOR/target/release/sp1-gpu-server +cp "$BIN" $FLOOR/bin/sp1-gpu-server && cp "$BIN" $FLOOR/home/.sp1/bin/sp1-gpu-server && chmod +x $FLOOR/bin/sp1-gpu-server $FLOOR/home/.sp1/bin/sp1-gpu-server +echo "RESULT binary bytes=$(stat -c %s "$BIN") sha256=$(sha256sum "$BIN" | cut -c1-64) version=$($BIN --version 2>/dev/null)" +echo "RESULT elf_targets $(cuobjdump --list-elf "$BIN" 2>/dev/null | grep -o 'sm_[0-9]*' | sort -u | tr '\n' ' ')" +echo "RESULT live_server_untouched sha256=$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) (expected c2642ad1c42e85d8)" +echo "RESULT end $(stamp)" +'@ +$bash = $bash.Replace('PATCH_PATH_PLACEHOLDER', $patchW) +$bashFile = Join-Path $job 'build.sh' +[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } +"RESULT end $(Stamp)" diff --git a/tools/prover-floor/pc2-floor-measure.ps1 b/tools/prover-floor/pc2-floor-measure.ps1 new file mode 100644 index 000000000..d72e9771c --- /dev/null +++ b/tools/prover-floor/pc2-floor-measure.ps1 @@ -0,0 +1,65 @@ +# Prover floor (5 October 2026): the peak GPU memory and the time of one compressed shard proof through the PATCHED +# sp1-gpu-server (/opt/igneum-floor/home/.sp1/bin, reached by HOME=/opt/igneum-floor/home: the SDK spawns the +# server it finds under $HOME/.sp1/bin, sp1-cuda-6.8.1/src/server.rs) on PC 2's RTX 5090, the miners STOPPED by the +# job (--stop-miners) and the live prover switched off for the run (its server would otherwise own the socket). +# Every point: every server killed and its socket unlinked, a 1-s nvidia-smi sampler, one `--mode compressed +# --shard 0` of the pv1 host (/opt/igneum-pv1, the UNPATCHED SDK and verifier: its VERIFIED is the unpatched +# verifier's word on the patched server's proof), the peak, the time, the FLOOR lines the server prints. +# The point list comes from the FLOOR_POINTS environment the job carries, else the default sweep below. +$ErrorActionPreference = 'Continue' +$urlFile = if ($env:IGNEUM_APP_DIR) { Join-Path $env:IGNEUM_APP_DIR 'app.url' } else { Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +if (-not (Test-Path $urlFile)) { $urlFile = Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +$base = (Get-Content $urlFile -Raw).Trim().TrimEnd('/') +function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } +function Prove($on) { try { (Invoke-RestMethod -Method Post -Uri "$base/api/prove" -ContentType 'application/json' -Body (@{on=$on} | ConvertTo-Json -Compress) -TimeoutSec 10) | ConvertTo-Json -Compress } catch { "error: $_" } } +"RESULT start $(Stamp) prover off for the run: $(Prove $false)" +Start-Sleep -Seconds 45 +"RESULT gpus $(Stamp) $((& nvidia-smi --query-gpu=index,name,memory.used,memory.total,utilization.gpu,power.draw --format=csv,noheader,nounits 2>$null) -join ' | ')" +$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor-measure' }; New-Item -ItemType Directory -Force -Path $job | Out-Null +function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } +$jobW = WslPath $job +$emptyW = WslPath (Join-Path $env:LOCALAPPDATA 'igneum\app\jobs\chain-pc2-pv1c\block-83616.json') +$points = if ($env:FLOOR_POINTS) { $env:FLOOR_POINTS } else { 'POINTS_PLACEHOLDER' } +$bash = @' +set -uo pipefail +export PATH="$HOME/.cargo/bin:$PATH" +CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)"; [ -n "$CUDA_DIR" ] && export PATH="$CUDA_DIR/bin:$PATH" && export LD_LIBRARY_PATH="$CUDA_DIR/lib64:/usr/lib/wsl/lib:${LD_LIBRARY_PATH:-}" +stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } +JOB='JOBW_PLACEHOLDER'; H=/opt/igneum-pv1/igneum-prove-host; FX="/root/igneum-prove-pv1/proving/fixtures" +FLOORHOME=/opt/igneum-floor/home; SRV=$FLOORHOME/.sp1/bin/sp1-gpu-server +EMPTY='EMPTY_PLACEHOLDER'; V1="$FX/fees-v1-shards2.json"; FULL="$FX/block-338-shard1.json"; ONE="$FX/block-56-transfers.json" +[ -x "$SRV" ] || { echo "RESULT measure_failed no patched server at $SRV"; exit 2; } +[ -x "$H" ] || { echo "RESULT measure_failed no pv1 host at $H"; exit 2; } +echo "RESULT patched_server sha256=$(sha256sum $SRV | cut -c1-64) version=$($SRV --version 2>/dev/null) host=$(sha256sum $H | cut -c1-16)" +echo "RESULT live_server sha256=$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) untouched" +pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT idle_mib $(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -1)" +run() { # name fixture env... + local name="$1" fx="$2"; shift 2 + local tag="$name-$(basename $fx .json)" + pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock + local csv="$JOB/smi-$tag.csv" log="$JOB/log-$tag.txt" + nvidia-smi --query-gpu=timestamp,memory.used,utilization.gpu --format=csv,noheader,nounits -l 1 > "$csv" 2>/dev/null & + local SMI=$! + local t0=$(date +%s) + env HOME=$FLOORHOME SP1_PROVER=cuda RUST_LOG=off SP1_GPU_FLOOR_LOG=1 "$@" $H "$fx" --mode compressed --shard 0 --out "$JOB/res-$tag.json" > "$log" 2>&1 + local rc=$? + local wall=$(( $(date +%s) - t0 )) + pkill -f sp1-gpu-server 2>/dev/null; sleep 1; kill $SMI 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock + local peak=$(awk -F', *' '{ if ($2+0 > m) m=$2+0 } END { print m+0 }' "$csv") + local n=$(wc -l < "$csv") + local line=$(grep -E "^RESULT compressed shard" "$log" | tail -1 | sed -E 's/.*prove ([0-9.]+) s, proof ([0-9]+) bytes, verify ([0-9.]+) s, ([A-Z ]+);.*/prove_s=\1 bytes=\2 verify_s=\3 \4/') + local cyc=$(grep -E "^RESULT execute shard" "$log" | tail -1 | sed -E 's/.*: ([0-9]+) cycles.*/\1/') + local err=$(grep -iE "error|panick|out of memory|OOM|unsupported" "$log" | grep -v "^FLOOR" | head -1 | cut -c1-200) + echo "RESULT floor cfg=$name fixture=$(basename $fx .json) peak_mib=$peak samples=$n wall_s=$wall cycles=${cyc:-na} ${line:-no_result} exit=$rc env='$*' ${err:+err=$err}" + grep -E "^FLOOR" "$log" | sed "s/^/RESULT floorline cfg=$name fixture=$(basename $fx .json) /" | head -40 +} +POINTS_PLACEHOLDER_BASH +pkill -f sp1-gpu-server 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT measure_end $(stamp)" +'@ +$bash = $bash.Replace('JOBW_PLACEHOLDER', $jobW).Replace('EMPTY_PLACEHOLDER', $emptyW).Replace('POINTS_PLACEHOLDER_BASH', ($points -replace ';', "`n")) +$bashFile = Join-Path $job 'measure.sh' +[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } +"RESULT end $(Stamp) prover back on: $(Prove $true)" diff --git a/tools/prover-floor/pc2-floor-sweep1.ps1 b/tools/prover-floor/pc2-floor-sweep1.ps1 new file mode 100644 index 000000000..f7c5160b7 --- /dev/null +++ b/tools/prover-floor/pc2-floor-sweep1.ps1 @@ -0,0 +1,65 @@ +# Prover floor (5 October 2026): the peak GPU memory and the time of one compressed shard proof through the PATCHED +# sp1-gpu-server (/opt/igneum-floor/home/.sp1/bin, reached by HOME=/opt/igneum-floor/home: the SDK spawns the +# server it finds under $HOME/.sp1/bin, sp1-cuda-6.8.1/src/server.rs) on PC 2's RTX 5090, the miners STOPPED by the +# job (--stop-miners) and the live prover switched off for the run (its server would otherwise own the socket). +# Every point: every server killed and its socket unlinked, a 1-s nvidia-smi sampler, one `--mode compressed +# --shard 0` of the pv1 host (/opt/igneum-pv1, the UNPATCHED SDK and verifier: its VERIFIED is the unpatched +# verifier's word on the patched server's proof), the peak, the time, the FLOOR lines the server prints. +# The point list comes from the FLOOR_POINTS environment the job carries, else the default sweep below. +$ErrorActionPreference = 'Continue' +$urlFile = if ($env:IGNEUM_APP_DIR) { Join-Path $env:IGNEUM_APP_DIR 'app.url' } else { Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +if (-not (Test-Path $urlFile)) { $urlFile = Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +$base = (Get-Content $urlFile -Raw).Trim().TrimEnd('/') +function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } +function Prove($on) { try { (Invoke-RestMethod -Method Post -Uri "$base/api/prove" -ContentType 'application/json' -Body (@{on=$on} | ConvertTo-Json -Compress) -TimeoutSec 10) | ConvertTo-Json -Compress } catch { "error: $_" } } +"RESULT start $(Stamp) prover off for the run: $(Prove $false)" +Start-Sleep -Seconds 45 +"RESULT gpus $(Stamp) $((& nvidia-smi --query-gpu=index,name,memory.used,memory.total,utilization.gpu,power.draw --format=csv,noheader,nounits 2>$null) -join ' | ')" +$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor-measure' }; New-Item -ItemType Directory -Force -Path $job | Out-Null +function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } +$jobW = WslPath $job +$emptyW = WslPath (Join-Path $env:LOCALAPPDATA 'igneum\app\jobs\chain-pc2-pv1c\block-83616.json') +$points = if ($env:FLOOR_POINTS) { $env:FLOOR_POINTS } else { 'run ctrl32 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=32;run ctrl32 "$V1" SP1_GPU_MEMORY_BUDGET_GB=32;run b12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12;run b12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12;run b16 "$V1" SP1_GPU_MEMORY_BUDGET_GB=16;run e26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864;run e26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864;run e25 "$V1" SP1_GPU_ELEMENT_THRESHOLD=33554432;run b12c1 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_WORKER_NORMALIZE_PROGRAM_CACHE_SIZE=1' } +$bash = @' +set -uo pipefail +export PATH="$HOME/.cargo/bin:$PATH" +CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)"; [ -n "$CUDA_DIR" ] && export PATH="$CUDA_DIR/bin:$PATH" && export LD_LIBRARY_PATH="$CUDA_DIR/lib64:/usr/lib/wsl/lib:${LD_LIBRARY_PATH:-}" +stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } +JOB='JOBW_PLACEHOLDER'; H=/opt/igneum-pv1/igneum-prove-host; FX="/root/igneum-prove-pv1/proving/fixtures" +FLOORHOME=/opt/igneum-floor/home; SRV=$FLOORHOME/.sp1/bin/sp1-gpu-server +EMPTY='EMPTY_PLACEHOLDER'; V1="$FX/fees-v1-shards2.json"; FULL="$FX/block-338-shard1.json"; ONE="$FX/block-56-transfers.json" +[ -x "$SRV" ] || { echo "RESULT measure_failed no patched server at $SRV"; exit 2; } +[ -x "$H" ] || { echo "RESULT measure_failed no pv1 host at $H"; exit 2; } +echo "RESULT patched_server sha256=$(sha256sum $SRV | cut -c1-64) version=$($SRV --version 2>/dev/null) host=$(sha256sum $H | cut -c1-16)" +echo "RESULT live_server sha256=$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) untouched" +pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT idle_mib $(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -1)" +run() { # name fixture env... + local name="$1" fx="$2"; shift 2 + local tag="$name-$(basename $fx .json)" + pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock + local csv="$JOB/smi-$tag.csv" log="$JOB/log-$tag.txt" + nvidia-smi --query-gpu=timestamp,memory.used,utilization.gpu --format=csv,noheader,nounits -l 1 > "$csv" 2>/dev/null & + local SMI=$! + local t0=$(date +%s) + env HOME=$FLOORHOME SP1_PROVER=cuda RUST_LOG=off SP1_GPU_FLOOR_LOG=1 "$@" $H "$fx" --mode compressed --shard 0 --out "$JOB/res-$tag.json" > "$log" 2>&1 + local rc=$? + local wall=$(( $(date +%s) - t0 )) + pkill -f sp1-gpu-server 2>/dev/null; sleep 1; kill $SMI 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock + local peak=$(awk -F', *' '{ if ($2+0 > m) m=$2+0 } END { print m+0 }' "$csv") + local n=$(wc -l < "$csv") + local line=$(grep -E "^RESULT compressed shard" "$log" | tail -1 | sed -E 's/.*prove ([0-9.]+) s, proof ([0-9]+) bytes, verify ([0-9.]+) s, ([A-Z ]+);.*/prove_s=\1 bytes=\2 verify_s=\3 \4/') + local cyc=$(grep -E "^RESULT execute shard" "$log" | tail -1 | sed -E 's/.*: ([0-9]+) cycles.*/\1/') + local err=$(grep -iE "error|panick|out of memory|OOM|unsupported" "$log" | grep -v "^FLOOR" | head -1 | cut -c1-200) + echo "RESULT floor cfg=$name fixture=$(basename $fx .json) peak_mib=$peak samples=$n wall_s=$wall cycles=${cyc:-na} ${line:-no_result} exit=$rc env='$*' ${err:+err=$err}" + grep -E "^FLOOR" "$log" | sed "s/^/RESULT floorline cfg=$name fixture=$(basename $fx .json) /" | head -40 +} +POINTS_PLACEHOLDER_BASH +pkill -f sp1-gpu-server 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT measure_end $(stamp)" +'@ +$bash = $bash.Replace('JOBW_PLACEHOLDER', $jobW).Replace('EMPTY_PLACEHOLDER', $emptyW).Replace('POINTS_PLACEHOLDER_BASH', ($points -replace ';', "`n")) +$bashFile = Join-Path $job 'measure.sh' +[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } +"RESULT end $(Stamp) prover back on: $(Prove $true)" diff --git a/tools/prover-floor/pc2-toolchain.ps1 b/tools/prover-floor/pc2-toolchain.ps1 new file mode 100644 index 000000000..2a73536f1 --- /dev/null +++ b/tools/prover-floor/pc2-toolchain.ps1 @@ -0,0 +1,47 @@ +# Prover floor (5 October 2026, the project lead: "execute if it will solve the issue", the 12 GB cards): the toolchain check +# before the sp1-gpu-server source build on PC 2. Reads versions and free space inside WSL2 Ubuntu-24.04 as root. +# Touches nothing: no build, no GPU work (one nvidia-smi query), the live host and server untouched. +$ErrorActionPreference = 'Continue' +function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } +"RESULT start $(Stamp)" +"RESULT gpus $(Stamp) $((& nvidia-smi --query-gpu=index,name,memory.used,memory.total,driver_version --format=csv,noheader,nounits 2>$null) -join ' | ')" +"RESULT host_ram_mb $([math]::Round((Get-CimInstance Win32_OperatingSystem).TotalVisibleMemorySize / 1024))" +$bash = @' +set -uo pipefail +export PATH="$HOME/.cargo/bin:$HOME/.sp1/bin:/usr/local/go/bin:$PATH" +CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)" +[ -n "$CUDA_DIR" ] && export PATH="$CUDA_DIR/bin:$PATH" +v() { local n="$1"; shift; if command -v "$1" >/dev/null 2>&1; then echo "RESULT tool $n $("$@" 2>&1 | head -1 | tr -s ' ' | cut -c1-120)"; else echo "RESULT tool $n MISSING"; fi; } +echo "RESULT cuda_dirs $(ls -d /usr/local/cuda* 2>/dev/null | tr '\n' ' ')" +v nvcc nvcc --version +[ -n "$CUDA_DIR" ] && echo "RESULT nvcc_release $(nvcc --version 2>/dev/null | grep -o 'release [0-9.]*' | head -1)" +v cmake cmake --version +v gcc gcc --version +v g++ g++ --version +v clang clang --version +v go go version +v protoc protoc --version +v cargo cargo --version +v rustc rustc --version +v git git --version +v cuobjdump cuobjdump --version +v pkg-config pkg-config --version +echo "RESULT nproc $(nproc)" +echo "RESULT mem $(free -g | awk '/Mem:/ {print "total_gb=" $2 " available_gb=" $7}')" +echo "RESULT disk_root $(df -BG / | awk 'NR==2 {print "size=" $2 " used=" $3 " avail=" $4}')" +echo "RESULT disk_opt $(df -BG /opt 2>/dev/null | awk 'NR==2 {print "avail=" $4}')" +echo "RESULT registry $(du -sh $HOME/.cargo/registry 2>/dev/null | cut -f1) target_live $(du -sh /root/igneum-prove/proving/igneum-prove/target 2>/dev/null | cut -f1)" +echo "RESULT floor_dir $(ls -d /opt/igneum-floor 2>/dev/null || echo absent)" +echo "RESULT live_server $(ls -l /root/.sp1/bin/sp1-gpu-server 2>/dev/null | awk '{print $5}') sha256 $(sha256sum /root/.sp1/bin/sp1-gpu-server 2>/dev/null | cut -c1-16)" +echo "RESULT live_server_version $($HOME/.sp1/bin/sp1-gpu-server --version 2>/dev/null)" +echo "RESULT github $(timeout 20 git ls-remote --tags https://github.com/succinctlabs/sp1 refs/tags/v6.8.1 2>&1 | cut -c1-60)" +echo "RESULT ld_libs $(ls /usr/lib/wsl/lib/libcuda.so* 2>/dev/null | tr '\n' ' ')" +echo "RESULT wsl_user $(id -un) home $HOME" +echo "RESULT end $(date -u +%Y-%m-%dT%H:%M:%SZ)" +'@ +$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor' }; New-Item -ItemType Directory -Force -Path $job | Out-Null +$bashFile = Join-Path $job 'toolchain.sh' +[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) +function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } +"RESULT end $(Stamp)" diff --git a/tools/prover-floor/points-sweep1.txt b/tools/prover-floor/points-sweep1.txt new file mode 100644 index 000000000..6437d4039 --- /dev/null +++ b/tools/prover-floor/points-sweep1.txt @@ -0,0 +1,9 @@ +run ctrl32 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=32 +run ctrl32 "$V1" SP1_GPU_MEMORY_BUDGET_GB=32 +run b12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12 +run b12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 +run b16 "$V1" SP1_GPU_MEMORY_BUDGET_GB=16 +run e26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864 +run e26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864 +run e25 "$V1" SP1_GPU_ELEMENT_THRESHOLD=33554432 +run b12c1 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_WORKER_NORMALIZE_PROGRAM_CACHE_SIZE=1 diff --git a/tools/prover-floor/points-sweep2.txt b/tools/prover-floor/points-sweep2.txt new file mode 100644 index 000000000..0fde61d44 --- /dev/null +++ b/tools/prover-floor/points-sweep2.txt @@ -0,0 +1,6 @@ +run r26b12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 +run r26b12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 +run r25b12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=33554432 +run r26e26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 +run r26e26 "$ONE" SP1_GPU_ELEMENT_THRESHOLD=67108864 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 +run r26e26 "$FULL" SP1_GPU_ELEMENT_THRESHOLD=67108864 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 From 393a8f831f49e6721260f5316d771e5954f7d717 Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Mon, 5 Oct 2026 22:33:31 +0000 Subject: [PATCH 2/5] Prover floor: the build recipe as it ran (Go pinned, the binary's sha256 and targets), the RISC Zero contingency figures with their source, playbook fixes Co-Authored-By: Claude Fable 5.1 --- docs/analysis/prover-floor.md | 24 +++++++++++++++++++++++ tools/prover-floor/make-build-playbook.sh | 21 +++++++++++++++----- tools/prover-floor/pc2-build-server.ps1 | 21 +++++++++++++++----- 3 files changed, 56 insertions(+), 10 deletions(-) diff --git a/docs/analysis/prover-floor.md b/docs/analysis/prover-floor.md index 0b2950ca8..b46b39272 100644 --- a/docs/analysis/prover-floor.md +++ b/docs/analysis/prover-floor.md @@ -89,3 +89,27 @@ upgrade repeats the clone, patch, build and measurement. The verifying key and t (the patch changes buffer sizes and the shard split, not the circuits), which the `verify-segment` and `--mode compressed` VERIFIED lines of the unpatched host show on every row below. The packaging path is a row for the proving plan before 0.3.12, not this branch. + +## Step 4 contingency, read not measured: RISC Zero's CUDA prover and its memory per segment + +If SP1 could not be brought under 11 GB, the alternative's floor is read from its operators' documentation (not +measured here; a PC 2 run would be the measurement): Boundless' prover guide +(https://docs.boundless.network/provers/performance-optimization) sets the segment size cap by VRAM as 8 GB: +po2 19, 16 GB: po2 20, 20 GB: po2 21, 40 GB: po2 22, with measured peaks po2 20: 13,835 MiB, po2 21: 22,905 MiB, +po2 22: 41,089 MiB; RISC Zero's PR 3761 adds `low_vram` and `pinned_witgen` to fit po2 22 on a 24 GB 4090. So +RISC Zero proves a 2^19-cycle segment inside 8 GB and a 2^20 one inside 16 GB, and a shard of 4.7 M cycles is +9 segments at po2 19 plus lift and join steps (times not on the page). Adopting it would cost a second guest (the +chain rule in the RISC Zero zkVM), a second pinned program id, a second verifier in the node and no shared +aggregation between the two formats: `docs/analysis/amd-proving.md` and the proving plan carry that row already. + +### The build, as it ran (job `floor-build-3`, 22:28:24 to 22:32:29Z) + +Three runs: `floor-build-1` (22:17Z) and `floor-build-2` (22:24Z) failed in 2 to 4 minutes on +`crates/recursion/gnark-ffi/build.rs:70`, "Failed to build Go library: NotFound" (no `go` on PC 2; the first run's +playbook lost its own log, a bug fixed before the second). `floor-build-3` fetched go1.27.1 (tarball sha256 +`63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445`, checked before unpacking under +`/opt/igneum-floor/go`, on the job's PATH only) and built in **240 s** (46 crates on the warm target of run 2, 8 +niced jobs, 16 cores). The binary: `/opt/igneum-floor/bin/sp1-gpu-server`, **166,768,224 bytes, sha256 +`5568108bf7fb9b0e525d8a08926b7046e51136ffaea53f0ca858631d0e938878`**, `--version` 6.8.1, `cuobjdump --list-elf` +sm_86, sm_89, sm_120 (the stock 251,306,680-byte server lists sm_80, 86, 89, 90, 100, 120 and compute_120 PTX). +The live `/root/.sp1/bin/sp1-gpu-server` (c2642ad1...) was never touched; the miners mined throughout. diff --git a/tools/prover-floor/make-build-playbook.sh b/tools/prover-floor/make-build-playbook.sh index 07f0d117c..7845980a1 100755 --- a/tools/prover-floor/make-build-playbook.sh +++ b/tools/prover-floor/make-build-playbook.sh @@ -41,21 +41,32 @@ echo "RESULT source \$(git describe --tags --always) \$(git rev-parse HEAD)" git apply "\$PATCH" || { echo "RESULT build_failed patch does not apply"; exit 2; } touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs echo "RESULT patched \$(git diff --stat | tail -1)" +# Go, as the release workflow installs it (the server's native-gnark feature compiles the gnark library with go; +# the wrap path is never run by a compressed proof, but the feature is upstream's and stays): a pinned tarball +# unpacked under /opt/igneum-floor, on this job's PATH only, no package installed on the PC. if ! command -v go >/dev/null 2>&1; then - sed -i 's/sp1-prover = { workspace = true, features = \["native-gnark"\] }/sp1-prover = { workspace = true }/' sp1-gpu/crates/server/Cargo.toml - echo "RESULT native_gnark dropped: no go toolchain on PC 2 (the gnark wrap is not used by compressed proofs)" + if [ ! -x \$FLOOR/go/bin/go ]; then + echo "STAGE go \$(stamp) fetching go1.27.1 (70,553,950 bytes, sha256 63d339f0...)" + curl -sSL -o \$FLOOR/go.tgz https://go.dev/dl/go1.27.1.linux-amd64.tar.gz || { echo "RESULT build_failed go download"; exit 2; } + echo "63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445 \$FLOOR/go.tgz" | sha256sum -c - >/dev/null || { echo "RESULT build_failed go sha256 mismatch: \$(sha256sum \$FLOOR/go.tgz)"; exit 2; } + echo "RESULT go_tarball sha256 \$(sha256sum \$FLOOR/go.tgz | cut -c1-64) matches 63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445" + tar -xzf \$FLOOR/go.tgz -C \$FLOOR && rm -f \$FLOOR/go.tgz + fi + export PATH="\$FLOOR/go/bin:\$PATH" GOPATH=\$FLOOR/gopath GOCACHE=\$FLOOR/gocache GOFLAGS=-mod=mod fi +echo "RESULT go \$(go version 2>&1 | head -1)" +LOG=\$FLOOR/logs/build.log; : > "\$LOG" +echo "RESULT dirs \$(ls -ld \$FLOOR \$FLOOR/logs 2>&1 | tr '\\n' ' ') pwd=\$(pwd)" export CUDA_ARCHS=86,89,120 CARGO_TARGET_DIR=\$FLOOR/target JOBS=8 echo "STAGE build \$(stamp) jobs=\$JOBS" t0=\$(date +%s) -nice -n 19 cargo build --release --bin sp1-gpu-server -j \$JOBS > \$FLOOR/logs/build-\$(date -u +%Y%m%dT%H%M%SZ).log 2>&1 & +nice -n 19 cargo build --release --bin sp1-gpu-server -j \$JOBS >> "\$LOG" 2>&1 & BP=\$! -LOG=\$(ls -t \$FLOOR/logs/build-*.log | head -1) while kill -0 \$BP 2>/dev/null; do sleep 120; echo "STAGE building \$(stamp) \$(( (\$(date +%s) - t0) / 60 )) min: \$(grep -c '^ Compiling' "\$LOG") crates compiled, last: \$(grep '^ Compiling' "\$LOG" | tail -1 | tr -s ' ' | cut -c1-80)"; done wait \$BP; rc=\$? echo "RESULT build_exit \$rc time_s=\$(( \$(date +%s) - t0 )) crates=\$(grep -c '^ Compiling' "\$LOG")" -if [ \$rc -ne 0 ]; then echo "RESULT build_failed"; grep -n -B2 -A12 '^error' "\$LOG" | head -80; exit 2; fi +if [ \$rc -ne 0 ]; then echo "RESULT build_failed"; echo "== error lines =="; grep -n -B2 -A12 -E '^(error|warning: unused manifest| process didn|caused by)' "\$LOG" | head -100; echo "== log tail =="; tail -n 60 "\$LOG"; exit 2; fi BIN=\$FLOOR/target/release/sp1-gpu-server cp "\$BIN" \$FLOOR/bin/sp1-gpu-server && cp "\$BIN" \$FLOOR/home/.sp1/bin/sp1-gpu-server && chmod +x \$FLOOR/bin/sp1-gpu-server \$FLOOR/home/.sp1/bin/sp1-gpu-server echo "RESULT binary bytes=\$(stat -c %s "\$BIN") sha256=\$(sha256sum "\$BIN" | cut -c1-64) version=\$(\$BIN --version 2>/dev/null)" diff --git a/tools/prover-floor/pc2-build-server.ps1 b/tools/prover-floor/pc2-build-server.ps1 index f1359a339..f35e59b27 100644 --- a/tools/prover-floor/pc2-build-server.ps1 +++ b/tools/prover-floor/pc2-build-server.ps1 @@ -31,21 +31,32 @@ echo "RESULT source $(git describe --tags --always) $(git rev-parse HEAD)" git apply "$PATCH" || { echo "RESULT build_failed patch does not apply"; exit 2; } touch sp1-gpu/crates/prover_components/src/builder.rs sp1-gpu/crates/jagged_tracegen/src/lib.rs sp1-gpu/crates/server/src/server.rs echo "RESULT patched $(git diff --stat | tail -1)" +# Go, as the release workflow installs it (the server's native-gnark feature compiles the gnark library with go; +# the wrap path is never run by a compressed proof, but the feature is upstream's and stays): a pinned tarball +# unpacked under /opt/igneum-floor, on this job's PATH only, no package installed on the PC. if ! command -v go >/dev/null 2>&1; then - sed -i 's/sp1-prover = { workspace = true, features = \["native-gnark"\] }/sp1-prover = { workspace = true }/' sp1-gpu/crates/server/Cargo.toml - echo "RESULT native_gnark dropped: no go toolchain on PC 2 (the gnark wrap is not used by compressed proofs)" + if [ ! -x $FLOOR/go/bin/go ]; then + echo "STAGE go $(stamp) fetching go1.27.1 (70,553,950 bytes, sha256 63d339f0...)" + curl -sSL -o $FLOOR/go.tgz https://go.dev/dl/go1.27.1.linux-amd64.tar.gz || { echo "RESULT build_failed go download"; exit 2; } + echo "63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445 $FLOOR/go.tgz" | sha256sum -c - >/dev/null || { echo "RESULT build_failed go sha256 mismatch: $(sha256sum $FLOOR/go.tgz)"; exit 2; } + echo "RESULT go_tarball sha256 $(sha256sum $FLOOR/go.tgz | cut -c1-64) matches 63d339f0da5ab53635a56f2490a7984dfe12dfcff22ad749f63edaf590168445" + tar -xzf $FLOOR/go.tgz -C $FLOOR && rm -f $FLOOR/go.tgz + fi + export PATH="$FLOOR/go/bin:$PATH" GOPATH=$FLOOR/gopath GOCACHE=$FLOOR/gocache GOFLAGS=-mod=mod fi +echo "RESULT go $(go version 2>&1 | head -1)" +LOG=$FLOOR/logs/build.log; : > "$LOG" +echo "RESULT dirs $(ls -ld $FLOOR $FLOOR/logs 2>&1 | tr '\n' ' ') pwd=$(pwd)" export CUDA_ARCHS=86,89,120 CARGO_TARGET_DIR=$FLOOR/target JOBS=8 echo "STAGE build $(stamp) jobs=$JOBS" t0=$(date +%s) -nice -n 19 cargo build --release --bin sp1-gpu-server -j $JOBS > $FLOOR/logs/build-$(date -u +%Y%m%dT%H%M%SZ).log 2>&1 & +nice -n 19 cargo build --release --bin sp1-gpu-server -j $JOBS >> "$LOG" 2>&1 & BP=$! -LOG=$(ls -t $FLOOR/logs/build-*.log | head -1) while kill -0 $BP 2>/dev/null; do sleep 120; echo "STAGE building $(stamp) $(( ($(date +%s) - t0) / 60 )) min: $(grep -c '^ Compiling' "$LOG") crates compiled, last: $(grep '^ Compiling' "$LOG" | tail -1 | tr -s ' ' | cut -c1-80)"; done wait $BP; rc=$? echo "RESULT build_exit $rc time_s=$(( $(date +%s) - t0 )) crates=$(grep -c '^ Compiling' "$LOG")" -if [ $rc -ne 0 ]; then echo "RESULT build_failed"; grep -n -B2 -A12 '^error' "$LOG" | head -80; exit 2; fi +if [ $rc -ne 0 ]; then echo "RESULT build_failed"; echo "== error lines =="; grep -n -B2 -A12 -E '^(error|warning: unused manifest| process didn|caused by)' "$LOG" | head -100; echo "== log tail =="; tail -n 60 "$LOG"; exit 2; fi BIN=$FLOOR/target/release/sp1-gpu-server cp "$BIN" $FLOOR/bin/sp1-gpu-server && cp "$BIN" $FLOOR/home/.sp1/bin/sp1-gpu-server && chmod +x $FLOOR/bin/sp1-gpu-server $FLOOR/home/.sp1/bin/sp1-gpu-server echo "RESULT binary bytes=$(stat -c %s "$BIN") sha256=$(sha256sum "$BIN" | cut -c1-64) version=$($BIN --version 2>/dev/null)" From 830efc63e1bd520eef3736689e19ac0f41c1c32e Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Mon, 5 Oct 2026 22:41:37 +0000 Subject: [PATCH 3/5] Prover floor patch v2: every trace buffer sized to its padded need (setup keys and shards), the sweep-2 points Co-Authored-By: Claude Fable 5.1 --- .../prover-floor/sp1-gpu-6.8.1-floor.patch | 75 ++++++++++++++++++- tools/prover-floor/pc2-build-server.ps1 | 6 +- tools/prover-floor/pc2-floor-sweep2.ps1 | 65 ++++++++++++++++ tools/prover-floor/points-sweep2.txt | 15 ++-- 4 files changed, 148 insertions(+), 13 deletions(-) create mode 100644 tools/prover-floor/pc2-floor-sweep2.ps1 diff --git a/proving/prover-floor/sp1-gpu-6.8.1-floor.patch b/proving/prover-floor/sp1-gpu-6.8.1-floor.patch index 8a355f920..c66939337 100644 --- a/proving/prover-floor/sp1-gpu-6.8.1-floor.patch +++ b/proving/prover-floor/sp1-gpu-6.8.1-floor.patch @@ -1,8 +1,42 @@ diff --git a/sp1-gpu/crates/jagged_tracegen/src/lib.rs b/sp1-gpu/crates/jagged_tracegen/src/lib.rs -index 579f70a..88bfc79 100644 +index 579f70a..09e73e8 100644 --- a/sp1-gpu/crates/jagged_tracegen/src/lib.rs +++ b/sp1-gpu/crates/jagged_tracegen/src/lib.rs -@@ -494,6 +494,11 @@ async fn allocate_and_initialize_traces( +@@ -481,6 +481,33 @@ async fn device_preprocessed_tracegen>( + named_traces + } + ++/// Igneum prover-floor patch: the dense elements a set of traces will occupy once `generate_jagged_traces` ++/// has laid them out, that is the sum of their buffers padded to the next multiple of 2^log_stacking_height ++/// (the "final padding" step below). Each phase (preprocessed, then main) is padded on its own. ++pub fn padded_trace_elements( ++ traces: &BTreeMap>, ++ log_stacking_height: u32, ++) -> usize { ++ let total: usize = traces ++ .values() ++ .map(|t| match t { ++ Trace::Real(trace) => trace.guts().as_buffer().len(), ++ Trace::Padding(_) => 0, ++ }) ++ .sum(); ++ total.next_multiple_of(1 << log_stacking_height) ++} ++ ++/// Igneum prover-floor patch: the capacity to allocate for a trace set: the exact padded size plus one ++/// stacking height of slack, never more than the prover's `max_trace_size`. `SP1_GPU_FLOOR_EXACT=0` restores ++/// upstream's full-capacity allocation. ++fn floor_capacity(max_trace_size: usize, needed: usize, log_stacking_height: u32) -> usize { ++ if std::env::var("SP1_GPU_FLOOR_EXACT").map(|v| v == "0").unwrap_or(false) { ++ return max_trace_size; ++ } ++ max_trace_size.min(needed + (1 << log_stacking_height)) ++} ++ + async fn allocate_and_initialize_traces( + preprocessed_traces: BTreeMap>, + max_trace_size: usize, +@@ -494,6 +521,11 @@ async fn allocate_and_initialize_traces( let total_gb = total_bytes as f64 / (1 << 30) as f64; tracing::debug!("Allocating {:?} GB of traces", total_gb); @@ -14,7 +48,40 @@ index 579f70a..88bfc79 100644 let mut dense_data: Buffer = Buffer::with_capacity_in(max_trace_size, backend.clone()); let mut col_index: Buffer = -@@ -1002,6 +1007,18 @@ pub async fn full_tracegen>( +@@ -677,9 +709,14 @@ pub async fn setup_tracegen>( + let preprocessed_traces = + device_preprocessed_tracegen(program, host_phase_tracegen, backend).await; + ++ let capacity = floor_capacity( ++ max_trace_size, ++ padded_trace_elements(&preprocessed_traces, log_stacking_height), ++ log_stacking_height, ++ ); + let jagged_traces = allocate_and_initialize_traces( + preprocessed_traces, +- max_trace_size, ++ capacity, + log_stacking_height, + max_log_row_count, + backend, +@@ -984,9 +1021,15 @@ pub async fn full_tracegen>( + + log_chip_stats(machine, &chip_set, &main_traces); + ++ let capacity = floor_capacity( ++ max_trace_size, ++ padded_trace_elements(&preprocessed_traces, log_stacking_height) ++ + padded_trace_elements(&main_traces, log_stacking_height), ++ log_stacking_height, ++ ); + let mut jagged_mle = allocate_and_initialize_traces( + preprocessed_traces, +- max_trace_size, ++ capacity, + log_stacking_height, + max_log_row_count, + backend, +@@ -1002,6 +1045,18 @@ pub async fn full_tracegen>( ) .await; @@ -22,7 +89,7 @@ index 579f70a..88bfc79 100644 + let dense = jagged_mle.dense(); + let (free, total) = sp1_gpu_cudart::cuda_memory_info().unwrap_or((0, 0)); + eprintln!( -+ "FLOOR tracegen used preprocessed_elements={} main_elements={} dense_len={} capacity_elements={max_trace_size} device_used_mib={}", ++ "FLOOR tracegen used preprocessed_elements={} main_elements={} dense_len={} capacity_elements={capacity} max_trace_size={max_trace_size} device_used_mib={}", + dense.preprocessed_offset, + dense.main_size(), + dense.dense.len(), diff --git a/tools/prover-floor/pc2-build-server.ps1 b/tools/prover-floor/pc2-build-server.ps1 index f35e59b27..dd94da4a2 100644 --- a/tools/prover-floor/pc2-build-server.ps1 +++ b/tools/prover-floor/pc2-build-server.ps1 @@ -1,13 +1,13 @@ # Prover floor (5 October 2026): builds sp1-gpu-server 6.8.1 from source with the Igneum floor patch on PC 2 inside # WSL2 Ubuntu-24.04 as root, into /opt/igneum-floor (the live /root/.sp1/bin/sp1-gpu-server and /opt/igneum are # never touched). CPU only: the miners keep mining, the card is not used. Generated by make-build-playbook.sh; -# patch sha256 700173fe2d852a382f050b36437612ea70f9513fa93093e6f86ea72b5e9ebf9b. CUDA_ARCHS=86,89,120 (the 12 GB tier is sm_86 (3060) and sm_89 (4070), the 16 GB tier sm_89 and sm_120; PC 2 runs sm_120; a shipped build lists every target the stock server does: 80, 86, 89, 90, 100, 120). +# patch sha256 08ce05557ee756ff5c302912a0b36910603e67eb786ed58b6529455e0c3b2d52. CUDA_ARCHS=86,89,120 (the 12 GB tier is sm_86 (3060) and sm_89 (4070), the 16 GB tier sm_89 and sm_120; PC 2 runs sm_120; a shipped build lists every target the stock server does: 80, 86, 89, 90, 100, 120). $ErrorActionPreference = 'Continue' function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } "RESULT start $(Stamp)" $job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor' }; New-Item -ItemType Directory -Force -Path $job | Out-Null function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } -$patchB64 = 'diff --git a/sp1-gpu/crates/jagged_tracegen/src/lib.rs b/sp1-gpu/crates/jagged_tracegen/src/lib.rs
index 579f70a..88bfc79 100644
--- a/sp1-gpu/crates/jagged_tracegen/src/lib.rs
+++ b/sp1-gpu/crates/jagged_tracegen/src/lib.rs
@@ -494,6 +494,11 @@ async fn allocate_and_initialize_traces(
 
     let total_gb = total_bytes as f64 / (1 << 30) as f64;
     tracing::debug!("Allocating {:?} GB of traces", total_gb);
+    if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() {
+        eprintln!(
+            "FLOOR tracegen alloc capacity_elements={max_trace_size} bytes={total_bytes} ({total_gb:.3} GB)"
+        );
+    }
     let mut dense_data: Buffer<Felt, TaskScope> =
         Buffer::with_capacity_in(max_trace_size, backend.clone());
     let mut col_index: Buffer<u32, TaskScope> =
@@ -1002,6 +1007,18 @@ pub async fn full_tracegen<A: CudaTracegenAir<Felt>>(
     )
     .await;
 
+    if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() {
+        let dense = jagged_mle.dense();
+        let (free, total) = sp1_gpu_cudart::cuda_memory_info().unwrap_or((0, 0));
+        eprintln!(
+            "FLOOR tracegen used preprocessed_elements={} main_elements={} dense_len={} capacity_elements={max_trace_size} device_used_mib={}",
+            dense.preprocessed_offset,
+            dense.main_size(),
+            dense.dense.len(),
+            (total - free) >> 20
+        );
+    }
+
     (public_values, jagged_mle, chip_set, permit)
 }
 
diff --git a/sp1-gpu/crates/prover_components/src/builder.rs b/sp1-gpu/crates/prover_components/src/builder.rs
index 5dccd9d..574d4fa 100644
--- a/sp1-gpu/crates/prover_components/src/builder.rs
+++ b/sp1-gpu/crates/prover_components/src/builder.rs
@@ -23,28 +23,75 @@ use crate::{
     SP1CudaProverComponents,
 };
 
+/// Igneum prover-floor patch (5 October 2026). Upstream sizes every device buffer for a 24 GB card or larger
+/// and panics below that, whatever the shard. Here the card's memory (or `SP1_GPU_MEMORY_BUDGET_GB`) picks a
+/// tier, and `SP1_GPU_ELEMENT_THRESHOLD` / `SP1_GPU_RECURSION_TRACE_ALLOCATION` set the two buffers directly.
+/// The proof format, the verifier and the program ids do not change: the element threshold only decides where
+/// the executor splits shards, as upstream's own 24 GB tier already does.
+fn env_usize(name: &str) -> Option<usize> {
+    std::env::var(name).ok().and_then(|s| s.parse::<usize>().ok())
+}
+
+fn env_f64(name: &str) -> Option<f64> {
+    std::env::var(name).ok().and_then(|s| s.parse::<f64>().ok())
+}
+
+/// The core element threshold for a memory budget in GB (upstream's own figure for the budget, +4, as it
+/// computed it: a 32 GB card is 36, a 24 GB card 28, a 16 GB card 20, a 12 GB card 16).
+pub fn element_threshold_for_budget(gpu_memory_gb: usize, full_size_shards: bool) -> u64 {
+    if gpu_memory_gb > 30 || (full_size_shards && gpu_memory_gb >= 24) {
+        ELEMENT_THRESHOLD
+    } else if gpu_memory_gb >= 24 {
+        ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24)
+    } else if gpu_memory_gb >= 18 {
+        (1 << 27) + (1 << 26)
+    } else {
+        1 << 27
+    }
+}
+
+/// The recursion trace allocation (elements) for a memory budget.
+pub fn recursion_trace_allocation_for_budget(gpu_memory_gb: usize) -> usize {
+    if gpu_memory_gb >= 24 {
+        RECURSION_TRACE_ALLOCATION
+    } else {
+        RECURSION_TRACE_ALLOCATION
+    }
+}
+
+pub fn gpu_memory_gb() -> usize {
+    let gb = 1024.0 * 1024.0 * 1024.0;
+    match env_f64("SP1_GPU_MEMORY_BUDGET_GB") {
+        Some(b) => (b.ceil() as usize) + 4,
+        None => (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4,
+    }
+}
+
+pub fn recursion_trace_allocation() -> usize {
+    env_usize("SP1_GPU_RECURSION_TRACE_ALLOCATION")
+        .unwrap_or_else(|| recursion_trace_allocation_for_budget(gpu_memory_gb()))
+}
+
 pub fn local_gpu_opts() -> SP1CoreOpts {
     let mut opts = SP1CoreOpts::default();
 
     let log2_shard_size = 24;
     opts.shard_size = 1 << log2_shard_size;
 
-    let gb = 1024.0 * 1024.0 * 1024.0;
-
-    // Get the amount of memory on the GPU.
-    let gpu_memory_gb: usize = (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4;
-
-    if gpu_memory_gb < 24 {
-        panic!("Unsupported GPU memory: {gpu_memory_gb}, must be at least 24GB");
-    }
+    // The card's memory plus 4, as upstream computed it (a 32 GB card reads 36), or the budget given.
+    let gpu_memory_gb = gpu_memory_gb();
 
-    let shard_threshold = if !opts.full_size_shards && gpu_memory_gb <= 30 {
-        ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24)
-    } else {
-        ELEMENT_THRESHOLD
+    let shard_threshold = match env_usize("SP1_GPU_ELEMENT_THRESHOLD") {
+        Some(t) => t as u64,
+        None => element_threshold_for_budget(gpu_memory_gb, opts.full_size_shards),
     };
+    let height_threshold = opts.sharding_threshold.height_threshold;
 
-    tracing::debug!("Shard threshold: {shard_threshold}");
+    eprintln!(
+        "FLOOR opts gpu_memory_gb={gpu_memory_gb} element_threshold={shard_threshold} height_threshold={height_threshold} recursion_trace_allocation={} full_size_shards={}",
+        recursion_trace_allocation(),
+        opts.full_size_shards
+    );
     opts.sharding_threshold.element_threshold = shard_threshold;
 
     opts.global_dependencies_opt = true;
@@ -92,7 +139,7 @@ pub async fn recursion_prover_and_verifier(
 ) {
     let recursion_verifier = SP1CudaProverComponents::compress_verifier();
     (
-        new_cuda_prover(&recursion_verifier, RECURSION_TRACE_ALLOCATION, 4, false, false, scope)
+        new_cuda_prover(&recursion_verifier, recursion_trace_allocation(), 4, false, false, scope)
             .await,
         recursion_verifier,
     )
diff --git a/sp1-gpu/crates/server/src/server.rs b/sp1-gpu/crates/server/src/server.rs
index 4035f1f..0d0d907 100644
--- a/sp1-gpu/crates/server/src/server.rs
+++ b/sp1-gpu/crates/server/src/server.rs
@@ -157,6 +157,7 @@ impl Server {
                 };
                 let pk = CachedProgram { elf: Arc::new(Elf::Dynamic(elf.into())), vk: vk.clone() };
                 ctx.pk_cache.insert(elf_hash, pk);
+                floor_memory_line("after setup");
                 Response::Setup { id: elf_hash, vk }
             }
             Request::Destroy { key } => {
@@ -177,15 +178,31 @@ impl Server {
                     );
                 };
                 let context = SP1Context::builder().proof_nonce(proof_nonce).build();
-                match prover.prove_with_mode(&cached.elf, stdin, context, mode).await {
+                let started = std::time::Instant::now();
+                let response = match prover.prove_with_mode(&cached.elf, stdin, context, mode).await {
                     Ok(proof) => Response::Proof { proof },
                     Err(e) => Response::ProverError(e.to_string()),
-                }
+                };
+                floor_memory_line(&format!("after prove {:?} in {:.1} s", mode, started.elapsed().as_secs_f64()));
+                response
             }
         }
     }
 }
 
+/// Igneum prover-floor patch: the device memory in use (total minus free, as the driver reports it) at the
+/// points that bound a proof, so a run's log carries the terms of the peak without a sampler.
+fn floor_memory_line(what: &str) {
+    if let Ok((free, total)) = sp1_gpu_cudart::cuda_memory_info() {
+        eprintln!(
+            "FLOOR memory {what}: device_used_mib={} free_mib={} total_mib={}",
+            (total - free) >> 20,
+            free >> 20,
+            total >> 20
+        );
+    }
+}
+
 fn sha256(data: &[u8]) -> [u8; 32] {
     use sha2::{Digest, Sha256};
     let mut hasher = Sha256::new();
' +$patchB64 = 'diff --git a/sp1-gpu/crates/jagged_tracegen/src/lib.rs b/sp1-gpu/crates/jagged_tracegen/src/lib.rs
index 579f70a..09e73e8 100644
--- a/sp1-gpu/crates/jagged_tracegen/src/lib.rs
+++ b/sp1-gpu/crates/jagged_tracegen/src/lib.rs
@@ -481,6 +481,33 @@ async fn device_preprocessed_tracegen<A: CudaTracegenAir<Felt>>(
     named_traces
 }
 
+/// Igneum prover-floor patch: the dense elements a set of traces will occupy once `generate_jagged_traces`
+/// has laid them out, that is the sum of their buffers padded to the next multiple of 2^log_stacking_height
+/// (the "final padding" step below). Each phase (preprocessed, then main) is padded on its own.
+pub fn padded_trace_elements(
+    traces: &BTreeMap<String, Trace<TaskScope>>,
+    log_stacking_height: u32,
+) -> usize {
+    let total: usize = traces
+        .values()
+        .map(|t| match t {
+            Trace::Real(trace) => trace.guts().as_buffer().len(),
+            Trace::Padding(_) => 0,
+        })
+        .sum();
+    total.next_multiple_of(1 << log_stacking_height)
+}
+
+/// Igneum prover-floor patch: the capacity to allocate for a trace set: the exact padded size plus one
+/// stacking height of slack, never more than the prover's `max_trace_size`. `SP1_GPU_FLOOR_EXACT=0` restores
+/// upstream's full-capacity allocation.
+fn floor_capacity(max_trace_size: usize, needed: usize, log_stacking_height: u32) -> usize {
+    if std::env::var("SP1_GPU_FLOOR_EXACT").map(|v| v == "0").unwrap_or(false) {
+        return max_trace_size;
+    }
+    max_trace_size.min(needed + (1 << log_stacking_height))
+}
+
 async fn allocate_and_initialize_traces(
     preprocessed_traces: BTreeMap<String, Trace<TaskScope>>,
     max_trace_size: usize,
@@ -494,6 +521,11 @@ async fn allocate_and_initialize_traces(
 
     let total_gb = total_bytes as f64 / (1 << 30) as f64;
     tracing::debug!("Allocating {:?} GB of traces", total_gb);
+    if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() {
+        eprintln!(
+            "FLOOR tracegen alloc capacity_elements={max_trace_size} bytes={total_bytes} ({total_gb:.3} GB)"
+        );
+    }
     let mut dense_data: Buffer<Felt, TaskScope> =
         Buffer::with_capacity_in(max_trace_size, backend.clone());
     let mut col_index: Buffer<u32, TaskScope> =
@@ -677,9 +709,14 @@ pub async fn setup_tracegen<A: CudaTracegenAir<Felt>>(
     let preprocessed_traces =
         device_preprocessed_tracegen(program, host_phase_tracegen, backend).await;
 
+    let capacity = floor_capacity(
+        max_trace_size,
+        padded_trace_elements(&preprocessed_traces, log_stacking_height),
+        log_stacking_height,
+    );
     let jagged_traces = allocate_and_initialize_traces(
         preprocessed_traces,
-        max_trace_size,
+        capacity,
         log_stacking_height,
         max_log_row_count,
         backend,
@@ -984,9 +1021,15 @@ pub async fn full_tracegen<A: CudaTracegenAir<Felt>>(
 
     log_chip_stats(machine, &chip_set, &main_traces);
 
+    let capacity = floor_capacity(
+        max_trace_size,
+        padded_trace_elements(&preprocessed_traces, log_stacking_height)
+            + padded_trace_elements(&main_traces, log_stacking_height),
+        log_stacking_height,
+    );
     let mut jagged_mle = allocate_and_initialize_traces(
         preprocessed_traces,
-        max_trace_size,
+        capacity,
         log_stacking_height,
         max_log_row_count,
         backend,
@@ -1002,6 +1045,18 @@ pub async fn full_tracegen<A: CudaTracegenAir<Felt>>(
     )
     .await;
 
+    if std::env::var("SP1_GPU_FLOOR_LOG").is_ok() {
+        let dense = jagged_mle.dense();
+        let (free, total) = sp1_gpu_cudart::cuda_memory_info().unwrap_or((0, 0));
+        eprintln!(
+            "FLOOR tracegen used preprocessed_elements={} main_elements={} dense_len={} capacity_elements={capacity} max_trace_size={max_trace_size} device_used_mib={}",
+            dense.preprocessed_offset,
+            dense.main_size(),
+            dense.dense.len(),
+            (total - free) >> 20
+        );
+    }
+
     (public_values, jagged_mle, chip_set, permit)
 }
 
diff --git a/sp1-gpu/crates/prover_components/src/builder.rs b/sp1-gpu/crates/prover_components/src/builder.rs
index 5dccd9d..574d4fa 100644
--- a/sp1-gpu/crates/prover_components/src/builder.rs
+++ b/sp1-gpu/crates/prover_components/src/builder.rs
@@ -23,28 +23,75 @@ use crate::{
     SP1CudaProverComponents,
 };
 
+/// Igneum prover-floor patch (5 October 2026). Upstream sizes every device buffer for a 24 GB card or larger
+/// and panics below that, whatever the shard. Here the card's memory (or `SP1_GPU_MEMORY_BUDGET_GB`) picks a
+/// tier, and `SP1_GPU_ELEMENT_THRESHOLD` / `SP1_GPU_RECURSION_TRACE_ALLOCATION` set the two buffers directly.
+/// The proof format, the verifier and the program ids do not change: the element threshold only decides where
+/// the executor splits shards, as upstream's own 24 GB tier already does.
+fn env_usize(name: &str) -> Option<usize> {
+    std::env::var(name).ok().and_then(|s| s.parse::<usize>().ok())
+}
+
+fn env_f64(name: &str) -> Option<f64> {
+    std::env::var(name).ok().and_then(|s| s.parse::<f64>().ok())
+}
+
+/// The core element threshold for a memory budget in GB (upstream's own figure for the budget, +4, as it
+/// computed it: a 32 GB card is 36, a 24 GB card 28, a 16 GB card 20, a 12 GB card 16).
+pub fn element_threshold_for_budget(gpu_memory_gb: usize, full_size_shards: bool) -> u64 {
+    if gpu_memory_gb > 30 || (full_size_shards && gpu_memory_gb >= 24) {
+        ELEMENT_THRESHOLD
+    } else if gpu_memory_gb >= 24 {
+        ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24)
+    } else if gpu_memory_gb >= 18 {
+        (1 << 27) + (1 << 26)
+    } else {
+        1 << 27
+    }
+}
+
+/// The recursion trace allocation (elements) for a memory budget.
+pub fn recursion_trace_allocation_for_budget(gpu_memory_gb: usize) -> usize {
+    if gpu_memory_gb >= 24 {
+        RECURSION_TRACE_ALLOCATION
+    } else {
+        RECURSION_TRACE_ALLOCATION
+    }
+}
+
+pub fn gpu_memory_gb() -> usize {
+    let gb = 1024.0 * 1024.0 * 1024.0;
+    match env_f64("SP1_GPU_MEMORY_BUDGET_GB") {
+        Some(b) => (b.ceil() as usize) + 4,
+        None => (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4,
+    }
+}
+
+pub fn recursion_trace_allocation() -> usize {
+    env_usize("SP1_GPU_RECURSION_TRACE_ALLOCATION")
+        .unwrap_or_else(|| recursion_trace_allocation_for_budget(gpu_memory_gb()))
+}
+
 pub fn local_gpu_opts() -> SP1CoreOpts {
     let mut opts = SP1CoreOpts::default();
 
     let log2_shard_size = 24;
     opts.shard_size = 1 << log2_shard_size;
 
-    let gb = 1024.0 * 1024.0 * 1024.0;
-
-    // Get the amount of memory on the GPU.
-    let gpu_memory_gb: usize = (((cuda_memory_info().unwrap().1 as f64) / gb).ceil() as usize) + 4;
-
-    if gpu_memory_gb < 24 {
-        panic!("Unsupported GPU memory: {gpu_memory_gb}, must be at least 24GB");
-    }
+    // The card's memory plus 4, as upstream computed it (a 32 GB card reads 36), or the budget given.
+    let gpu_memory_gb = gpu_memory_gb();
 
-    let shard_threshold = if !opts.full_size_shards && gpu_memory_gb <= 30 {
-        ELEMENT_THRESHOLD - (1 << 26) - (1 << 25) - (1 << 24)
-    } else {
-        ELEMENT_THRESHOLD
+    let shard_threshold = match env_usize("SP1_GPU_ELEMENT_THRESHOLD") {
+        Some(t) => t as u64,
+        None => element_threshold_for_budget(gpu_memory_gb, opts.full_size_shards),
     };
+    let height_threshold = opts.sharding_threshold.height_threshold;
 
-    tracing::debug!("Shard threshold: {shard_threshold}");
+    eprintln!(
+        "FLOOR opts gpu_memory_gb={gpu_memory_gb} element_threshold={shard_threshold} height_threshold={height_threshold} recursion_trace_allocation={} full_size_shards={}",
+        recursion_trace_allocation(),
+        opts.full_size_shards
+    );
     opts.sharding_threshold.element_threshold = shard_threshold;
 
     opts.global_dependencies_opt = true;
@@ -92,7 +139,7 @@ pub async fn recursion_prover_and_verifier(
 ) {
     let recursion_verifier = SP1CudaProverComponents::compress_verifier();
     (
-        new_cuda_prover(&recursion_verifier, RECURSION_TRACE_ALLOCATION, 4, false, false, scope)
+        new_cuda_prover(&recursion_verifier, recursion_trace_allocation(), 4, false, false, scope)
             .await,
         recursion_verifier,
     )
diff --git a/sp1-gpu/crates/server/src/server.rs b/sp1-gpu/crates/server/src/server.rs
index 4035f1f..0d0d907 100644
--- a/sp1-gpu/crates/server/src/server.rs
+++ b/sp1-gpu/crates/server/src/server.rs
@@ -157,6 +157,7 @@ impl Server {
                 };
                 let pk = CachedProgram { elf: Arc::new(Elf::Dynamic(elf.into())), vk: vk.clone() };
                 ctx.pk_cache.insert(elf_hash, pk);
+                floor_memory_line("after setup");
                 Response::Setup { id: elf_hash, vk }
             }
             Request::Destroy { key } => {
@@ -177,15 +178,31 @@ impl Server {
                     );
                 };
                 let context = SP1Context::builder().proof_nonce(proof_nonce).build();
-                match prover.prove_with_mode(&cached.elf, stdin, context, mode).await {
+                let started = std::time::Instant::now();
+                let response = match prover.prove_with_mode(&cached.elf, stdin, context, mode).await {
                     Ok(proof) => Response::Proof { proof },
                     Err(e) => Response::ProverError(e.to_string()),
-                }
+                };
+                floor_memory_line(&format!("after prove {:?} in {:.1} s", mode, started.elapsed().as_secs_f64()));
+                response
             }
         }
     }
 }
 
+/// Igneum prover-floor patch: the device memory in use (total minus free, as the driver reports it) at the
+/// points that bound a proof, so a run's log carries the terms of the peak without a sampler.
+fn floor_memory_line(what: &str) {
+    if let Ok((free, total)) = sp1_gpu_cudart::cuda_memory_info() {
+        eprintln!(
+            "FLOOR memory {what}: device_used_mib={} free_mib={} total_mib={}",
+            (total - free) >> 20,
+            free >> 20,
+            total >> 20
+        );
+    }
+}
+
 fn sha256(data: &[u8]) -> [u8; 32] {
     use sha2::{Digest, Sha256};
     let mut hasher = Sha256::new();
' [IO.File]::WriteAllBytes((Join-Path $job 'floor.patch'), [Convert]::FromBase64String($patchB64)) $patchW = WslPath (Join-Path $job 'floor.patch') $bash = @' @@ -19,7 +19,7 @@ export CUDA_PATH="$CUDA_DIR" CUDACXX="$CUDA_DIR/bin/nvcc" PATH="$CUDA_DIR/bin:$P stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } FLOOR=/opt/igneum-floor; SRC=$FLOOR/sp1; mkdir -p $FLOOR/bin $FLOOR/home/.sp1/bin $FLOOR/logs PATCH="PATCH_PATH_PLACEHOLDER" -echo "RESULT patch_sha256 $(sha256sum "$PATCH" | cut -c1-64) expected 700173fe2d852a382f050b36437612ea70f9513fa93093e6f86ea72b5e9ebf9b" +echo "RESULT patch_sha256 $(sha256sum "$PATCH" | cut -c1-64) expected 08ce05557ee756ff5c302912a0b36910603e67eb786ed58b6529455e0c3b2d52" echo "RESULT toolchain nvcc=$(nvcc --version | grep -o 'release [0-9.]*') cargo=$(cargo --version) go=$(go version 2>/dev/null || echo MISSING) protoc=$(protoc --version 2>/dev/null || echo MISSING) cmake=$(cmake --version 2>/dev/null | head -1 || echo MISSING) nproc=$(nproc) disk_avail=$(df -BG /opt | awk 'NR==2 {print $4}')" if [ ! -d "$SRC/.git" ]; then echo "STAGE clone $(stamp)" diff --git a/tools/prover-floor/pc2-floor-sweep2.ps1 b/tools/prover-floor/pc2-floor-sweep2.ps1 new file mode 100644 index 000000000..485e0f5c7 --- /dev/null +++ b/tools/prover-floor/pc2-floor-sweep2.ps1 @@ -0,0 +1,65 @@ +# Prover floor (5 October 2026): the peak GPU memory and the time of one compressed shard proof through the PATCHED +# sp1-gpu-server (/opt/igneum-floor/home/.sp1/bin, reached by HOME=/opt/igneum-floor/home: the SDK spawns the +# server it finds under $HOME/.sp1/bin, sp1-cuda-6.8.1/src/server.rs) on PC 2's RTX 5090, the miners STOPPED by the +# job (--stop-miners) and the live prover switched off for the run (its server would otherwise own the socket). +# Every point: every server killed and its socket unlinked, a 1-s nvidia-smi sampler, one `--mode compressed +# --shard 0` of the pv1 host (/opt/igneum-pv1, the UNPATCHED SDK and verifier: its VERIFIED is the unpatched +# verifier's word on the patched server's proof), the peak, the time, the FLOOR lines the server prints. +# The point list comes from the FLOOR_POINTS environment the job carries, else the default sweep below. +$ErrorActionPreference = 'Continue' +$urlFile = if ($env:IGNEUM_APP_DIR) { Join-Path $env:IGNEUM_APP_DIR 'app.url' } else { Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +if (-not (Test-Path $urlFile)) { $urlFile = Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +$base = (Get-Content $urlFile -Raw).Trim().TrimEnd('/') +function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } +function Prove($on) { try { (Invoke-RestMethod -Method Post -Uri "$base/api/prove" -ContentType 'application/json' -Body (@{on=$on} | ConvertTo-Json -Compress) -TimeoutSec 10) | ConvertTo-Json -Compress } catch { "error: $_" } } +"RESULT start $(Stamp) prover off for the run: $(Prove $false)" +Start-Sleep -Seconds 45 +"RESULT gpus $(Stamp) $((& nvidia-smi --query-gpu=index,name,memory.used,memory.total,utilization.gpu,power.draw --format=csv,noheader,nounits 2>$null) -join ' | ')" +$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor-measure' }; New-Item -ItemType Directory -Force -Path $job | Out-Null +function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } +$jobW = WslPath $job +$emptyW = WslPath (Join-Path $env:LOCALAPPDATA 'igneum\app\jobs\chain-pc2-pv1c\block-83616.json') +$points = if ($env:FLOOR_POINTS) { $env:FLOOR_POINTS } else { 'run x12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12;run x12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12;run x12 "$ONE" SP1_GPU_MEMORY_BUDGET_GB=12;run x12 "$FULL" SP1_GPU_MEMORY_BUDGET_GB=12;run xe26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864;run xe26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864;run x16 "$V1" SP1_GPU_MEMORY_BUDGET_GB=16;run x32 "$V1" SP1_GPU_MEMORY_BUDGET_GB=32;run x12r "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=100663296' } +$bash = @' +set -uo pipefail +export PATH="$HOME/.cargo/bin:$PATH" +CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)"; [ -n "$CUDA_DIR" ] && export PATH="$CUDA_DIR/bin:$PATH" && export LD_LIBRARY_PATH="$CUDA_DIR/lib64:/usr/lib/wsl/lib:${LD_LIBRARY_PATH:-}" +stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } +JOB='JOBW_PLACEHOLDER'; H=/opt/igneum-pv1/igneum-prove-host; FX="/root/igneum-prove-pv1/proving/fixtures" +FLOORHOME=/opt/igneum-floor/home; SRV=$FLOORHOME/.sp1/bin/sp1-gpu-server +EMPTY='EMPTY_PLACEHOLDER'; V1="$FX/fees-v1-shards2.json"; FULL="$FX/block-338-shard1.json"; ONE="$FX/block-56-transfers.json" +[ -x "$SRV" ] || { echo "RESULT measure_failed no patched server at $SRV"; exit 2; } +[ -x "$H" ] || { echo "RESULT measure_failed no pv1 host at $H"; exit 2; } +echo "RESULT patched_server sha256=$(sha256sum $SRV | cut -c1-64) version=$($SRV --version 2>/dev/null) host=$(sha256sum $H | cut -c1-16)" +echo "RESULT live_server sha256=$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) untouched" +pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT idle_mib $(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -1)" +run() { # name fixture env... + local name="$1" fx="$2"; shift 2 + local tag="$name-$(basename $fx .json)" + pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock + local csv="$JOB/smi-$tag.csv" log="$JOB/log-$tag.txt" + nvidia-smi --query-gpu=timestamp,memory.used,utilization.gpu --format=csv,noheader,nounits -l 1 > "$csv" 2>/dev/null & + local SMI=$! + local t0=$(date +%s) + env HOME=$FLOORHOME SP1_PROVER=cuda RUST_LOG=off SP1_GPU_FLOOR_LOG=1 "$@" $H "$fx" --mode compressed --shard 0 --out "$JOB/res-$tag.json" > "$log" 2>&1 + local rc=$? + local wall=$(( $(date +%s) - t0 )) + pkill -f sp1-gpu-server 2>/dev/null; sleep 1; kill $SMI 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock + local peak=$(awk -F', *' '{ if ($2+0 > m) m=$2+0 } END { print m+0 }' "$csv") + local n=$(wc -l < "$csv") + local line=$(grep -E "^RESULT compressed shard" "$log" | tail -1 | sed -E 's/.*prove ([0-9.]+) s, proof ([0-9]+) bytes, verify ([0-9.]+) s, ([A-Z ]+);.*/prove_s=\1 bytes=\2 verify_s=\3 \4/') + local cyc=$(grep -E "^RESULT execute shard" "$log" | tail -1 | sed -E 's/.*: ([0-9]+) cycles.*/\1/') + local err=$(grep -iE "error|panick|out of memory|OOM|unsupported" "$log" | grep -v "^FLOOR" | head -1 | cut -c1-200) + echo "RESULT floor cfg=$name fixture=$(basename $fx .json) peak_mib=$peak samples=$n wall_s=$wall cycles=${cyc:-na} ${line:-no_result} exit=$rc env='$*' ${err:+err=$err}" + grep -E "^FLOOR" "$log" | sed "s/^/RESULT floorline cfg=$name fixture=$(basename $fx .json) /" | head -40 +} +POINTS_PLACEHOLDER_BASH +pkill -f sp1-gpu-server 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT measure_end $(stamp)" +'@ +$bash = $bash.Replace('JOBW_PLACEHOLDER', $jobW).Replace('EMPTY_PLACEHOLDER', $emptyW).Replace('POINTS_PLACEHOLDER_BASH', ($points -replace ';', "`n")) +$bashFile = Join-Path $job 'measure.sh' +[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } +"RESULT end $(Stamp) prover back on: $(Prove $true)" diff --git a/tools/prover-floor/points-sweep2.txt b/tools/prover-floor/points-sweep2.txt index 0fde61d44..6b5f0ee56 100644 --- a/tools/prover-floor/points-sweep2.txt +++ b/tools/prover-floor/points-sweep2.txt @@ -1,6 +1,9 @@ -run r26b12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 -run r26b12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 -run r25b12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=33554432 -run r26e26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 -run r26e26 "$ONE" SP1_GPU_ELEMENT_THRESHOLD=67108864 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 -run r26e26 "$FULL" SP1_GPU_ELEMENT_THRESHOLD=67108864 SP1_GPU_RECURSION_TRACE_ALLOCATION=67108864 +run x12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12 +run x12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 +run x12 "$ONE" SP1_GPU_MEMORY_BUDGET_GB=12 +run x12 "$FULL" SP1_GPU_MEMORY_BUDGET_GB=12 +run xe26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864 +run xe26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864 +run x16 "$V1" SP1_GPU_MEMORY_BUDGET_GB=16 +run x32 "$V1" SP1_GPU_MEMORY_BUDGET_GB=32 +run x12r "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 SP1_GPU_RECURSION_TRACE_ALLOCATION=100663296 From 5bc7ce9b5586421b1d1325ed40d3e592e9f715d0 Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Mon, 5 Oct 2026 22:42:17 +0000 Subject: [PATCH 4/5] Prover floor: sweep 1 table and reading (the Setup-time keys bind at 12.7 GB) Co-Authored-By: Claude Fable 5.1 --- docs/analysis/prover-floor.md | 37 +++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/docs/analysis/prover-floor.md b/docs/analysis/prover-floor.md index b46b39272..4d2130801 100644 --- a/docs/analysis/prover-floor.md +++ b/docs/analysis/prover-floor.md @@ -113,3 +113,40 @@ niced jobs, 16 cores). The binary: `/opt/igneum-floor/bin/sp1-gpu-server`, **166 `5568108bf7fb9b0e525d8a08926b7046e51136ffaea53f0ca858631d0e938878`**, `--version` 6.8.1, `cuobjdump --list-elf` sm_86, sm_89, sm_120 (the stock 251,306,680-byte server lists sm_80, 86, 89, 90, 100, 120 and compute_120 PTX). The live `/root/.sp1/bin/sp1-gpu-server` (c2642ad1...) was never touched; the miners mined throughout. + +## Sweep 1 (job `floor-sweep-1`, 22:34:56 to 22:37:55Z): the shard term gone, a second floor found + +PC 2's RTX 5090 (32,607 MiB, idle 1,755 MiB with the miners stopped and the live prover off), the patched server +`5568108b...` (sm_86, sm_89, sm_120; the build above), the unpatched pv1 host `dae6b006...` as client and +verifier, one `--mode compressed --shard 0` per point, every server killed and its socket unlinked around every +point, peak = `nvidia-smi memory.used` at 1 s (the idle 1,755 MiB inside it), time = the compressed proof. +Every proof VERIFIED (1,272,897 bytes, verify 0.037 to 0.040 s), so the unpatched verifier accepts every proof +of the patched server. + +| Config (environment to the patched server) | Fixture | Cycles | Peak MiB | Prove s | Verified | +|---|---|---|---|---|---| +| control: `SP1_GPU_MEMORY_BUDGET_GB=32` (upstream's sizes) | empty live shard (block 83616) | 280,706 | 13,892 | 2.2 | yes | +| control | v1 shard (fees-v1-shards2 shard 0) | 4,717,439 | 20,516 | 4.2 | yes | +| 12 GB tier: budget 12 (threshold 2^27) | empty | 280,706 | 12,740 | 2.4 | yes | +| 12 GB tier | v1 shard | 4.7 M | 15,396 | 4.1 | yes | +| 12 GB tier + `SP1_WORKER_NORMALIZE_PROGRAM_CACHE_SIZE=1` | v1 shard | 4.7 M | 15,428 | 4.0 | yes | +| 16 GB tier: budget 16 (2^27 + 2^26) | v1 shard | 4.7 M | 18,628 | 3.8 | yes | +| `SP1_GPU_ELEMENT_THRESHOLD=67108864` (2^26) | empty | 280,706 | 12,772 | 3.1 | yes | +| 2^26 | v1 shard (split into 4 core shards) | 4.7 M | **12,708** | 5.3 | yes | +| `SP1_GPU_ELEMENT_THRESHOLD=33554432` (2^25) | v1 shard | 4.7 M | 12,836 | 8.5 | yes | + +Reading. The control reproduces the proving agent's curve (13.9 and 20.4 GB), so the patched server behaves as +the stock one at the stock sizes. The shard's term follows the threshold as the model says (20.5 GB at 402 M +elements, 15.4 at 134 M, 12.7 at 67 M), and then stops: 2^26 and 2^25 both sit at 12.7 to 12.8 GB for the empty +shard and the v1 shard alike. The `FLOOR memory after setup` line names the rest: **9,703 MiB in use before the +first shard** (2^26; 11,623 at the stock sizes), and the `FLOOR tracegen alloc` lines at Setup are five +allocations of 134,217,728 elements (the recursion keys, 0.75 GB each, each using 90,177,536 elements: 35.6 M +preprocessed and 54.5 M main at prove time), one of 33,554,432 (the shrink key, 0.19 GB) and one core key at the +threshold. The `NORMALIZE_PROGRAM_CACHE_SIZE` knob does not reach them (they are keys built at `Setup`, not the +program LRU). The time cost of the split: the v1 shard at 2^26 is 4 core shards and 5.3 s against 4.2 s (1.26x); +at 2^27 it is 4.1 s with no split. + +So after sweep 1 the binding term is the Setup-time keys allocated at full capacity, and patch v2 sizes every +trace buffer (keys and shards) to its padded need: `padded_trace_elements` in `jagged_tracegen/src/lib.rs` +(each phase pads to the next multiple of 2^21 rows, `generate_jagged_traces`'s "final padding"), applied in +`setup_tracegen` and `full_tracegen`, one stacking height of slack, `SP1_GPU_FLOOR_EXACT=0` restoring upstream. From 8e2686d008903a3e0bb5d952dcd5ea96e68b706b Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Mon, 5 Oct 2026 22:42:31 +0000 Subject: [PATCH 5/5] Prover floor: the beside-the-miner sweep playbook (sweep 3) Co-Authored-By: Claude Fable 5.1 --- tools/prover-floor/pc2-floor-sweep3-miner.ps1 | 66 +++++++++++++++++++ tools/prover-floor/points-sweep3-miner.txt | 4 ++ 2 files changed, 70 insertions(+) create mode 100644 tools/prover-floor/pc2-floor-sweep3-miner.ps1 create mode 100644 tools/prover-floor/points-sweep3-miner.txt diff --git a/tools/prover-floor/pc2-floor-sweep3-miner.ps1 b/tools/prover-floor/pc2-floor-sweep3-miner.ps1 new file mode 100644 index 000000000..8282cc4e4 --- /dev/null +++ b/tools/prover-floor/pc2-floor-sweep3-miner.ps1 @@ -0,0 +1,66 @@ +# Published WITHOUT --stop-miners: the beside-the-miner pair (the 5090 mining at full rate on the same card). +# Prover floor (5 October 2026): the peak GPU memory and the time of one compressed shard proof through the PATCHED +# sp1-gpu-server (/opt/igneum-floor/home/.sp1/bin, reached by HOME=/opt/igneum-floor/home: the SDK spawns the +# server it finds under $HOME/.sp1/bin, sp1-cuda-6.8.1/src/server.rs) on PC 2's RTX 5090, the miners STOPPED by the +# job (--stop-miners) and the live prover switched off for the run (its server would otherwise own the socket). +# Every point: every server killed and its socket unlinked, a 1-s nvidia-smi sampler, one `--mode compressed +# --shard 0` of the pv1 host (/opt/igneum-pv1, the UNPATCHED SDK and verifier: its VERIFIED is the unpatched +# verifier's word on the patched server's proof), the peak, the time, the FLOOR lines the server prints. +# The point list comes from the FLOOR_POINTS environment the job carries, else the default sweep below. +$ErrorActionPreference = 'Continue' +$urlFile = if ($env:IGNEUM_APP_DIR) { Join-Path $env:IGNEUM_APP_DIR 'app.url' } else { Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +if (-not (Test-Path $urlFile)) { $urlFile = Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +$base = (Get-Content $urlFile -Raw).Trim().TrimEnd('/') +function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } +function Prove($on) { try { (Invoke-RestMethod -Method Post -Uri "$base/api/prove" -ContentType 'application/json' -Body (@{on=$on} | ConvertTo-Json -Compress) -TimeoutSec 10) | ConvertTo-Json -Compress } catch { "error: $_" } } +"RESULT start $(Stamp) prover off for the run: $(Prove $false)" +Start-Sleep -Seconds 45 +"RESULT gpus $(Stamp) $((& nvidia-smi --query-gpu=index,name,memory.used,memory.total,utilization.gpu,power.draw --format=csv,noheader,nounits 2>$null) -join ' | ')" +$job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-floor-measure' }; New-Item -ItemType Directory -Force -Path $job | Out-Null +function WslPath($p) { $w = (& wsl.exe -d Ubuntu-24.04 -u root -- wslpath -a ($p -replace '\\', '/') 2>$null); if ($w) { ($w -replace "`0", '').Trim() } else { '/mnt/c' + ($p.Substring(2) -replace '\\', '/') } } +$jobW = WslPath $job +$emptyW = WslPath (Join-Path $env:LOCALAPPDATA 'igneum\app\jobs\chain-pc2-pv1c\block-83616.json') +$points = if ($env:FLOOR_POINTS) { $env:FLOOR_POINTS } else { 'run m12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12;run m12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12;run me26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864;run me26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864' } +$bash = @' +set -uo pipefail +export PATH="$HOME/.cargo/bin:$PATH" +CUDA_DIR="$(ls -d /usr/local/cuda-12.* 2>/dev/null | sort -V | tail -1 || true)"; [ -n "$CUDA_DIR" ] && export PATH="$CUDA_DIR/bin:$PATH" && export LD_LIBRARY_PATH="$CUDA_DIR/lib64:/usr/lib/wsl/lib:${LD_LIBRARY_PATH:-}" +stamp() { date -u +%Y-%m-%dT%H:%M:%SZ; } +JOB='JOBW_PLACEHOLDER'; H=/opt/igneum-pv1/igneum-prove-host; FX="/root/igneum-prove-pv1/proving/fixtures" +FLOORHOME=/opt/igneum-floor/home; SRV=$FLOORHOME/.sp1/bin/sp1-gpu-server +EMPTY='EMPTY_PLACEHOLDER'; V1="$FX/fees-v1-shards2.json"; FULL="$FX/block-338-shard1.json"; ONE="$FX/block-56-transfers.json" +[ -x "$SRV" ] || { echo "RESULT measure_failed no patched server at $SRV"; exit 2; } +[ -x "$H" ] || { echo "RESULT measure_failed no pv1 host at $H"; exit 2; } +echo "RESULT patched_server sha256=$(sha256sum $SRV | cut -c1-64) version=$($SRV --version 2>/dev/null) host=$(sha256sum $H | cut -c1-16)" +echo "RESULT live_server sha256=$(sha256sum /root/.sp1/bin/sp1-gpu-server | cut -c1-16) untouched" +pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT idle_mib $(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -1)" +run() { # name fixture env... + local name="$1" fx="$2"; shift 2 + local tag="$name-$(basename $fx .json)" + pkill -f sp1-gpu-server 2>/dev/null; sleep 2; rm -f /tmp/sp1-cuda-*.sock + local csv="$JOB/smi-$tag.csv" log="$JOB/log-$tag.txt" + nvidia-smi --query-gpu=timestamp,memory.used,utilization.gpu --format=csv,noheader,nounits -l 1 > "$csv" 2>/dev/null & + local SMI=$! + local t0=$(date +%s) + env HOME=$FLOORHOME SP1_PROVER=cuda RUST_LOG=off SP1_GPU_FLOOR_LOG=1 "$@" $H "$fx" --mode compressed --shard 0 --out "$JOB/res-$tag.json" > "$log" 2>&1 + local rc=$? + local wall=$(( $(date +%s) - t0 )) + pkill -f sp1-gpu-server 2>/dev/null; sleep 1; kill $SMI 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock + local peak=$(awk -F', *' '{ if ($2+0 > m) m=$2+0 } END { print m+0 }' "$csv") + local n=$(wc -l < "$csv") + local line=$(grep -E "^RESULT compressed shard" "$log" | tail -1 | sed -E 's/.*prove ([0-9.]+) s, proof ([0-9]+) bytes, verify ([0-9.]+) s, ([A-Z ]+);.*/prove_s=\1 bytes=\2 verify_s=\3 \4/') + local cyc=$(grep -E "^RESULT execute shard" "$log" | tail -1 | sed -E 's/.*: ([0-9]+) cycles.*/\1/') + local err=$(grep -iE "error|panick|out of memory|OOM|unsupported" "$log" | grep -v "^FLOOR" | head -1 | cut -c1-200) + echo "RESULT floor cfg=$name fixture=$(basename $fx .json) peak_mib=$peak samples=$n wall_s=$wall cycles=${cyc:-na} ${line:-no_result} exit=$rc env='$*' ${err:+err=$err}" + grep -E "^FLOOR" "$log" | sed "s/^/RESULT floorline cfg=$name fixture=$(basename $fx .json) /" | head -40 +} +POINTS_PLACEHOLDER_BASH +pkill -f sp1-gpu-server 2>/dev/null; sleep 1; rm -f /tmp/sp1-cuda-*.sock +echo "RESULT measure_end $(stamp)" +'@ +$bash = $bash.Replace('JOBW_PLACEHOLDER', $jobW).Replace('EMPTY_PLACEHOLDER', $emptyW).Replace('POINTS_PLACEHOLDER_BASH', ($points -replace ';', "`n")) +$bashFile = Join-Path $job 'measure.sh' +[IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) +& wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } +"RESULT end $(Stamp) prover back on: $(Prove $true)" diff --git a/tools/prover-floor/points-sweep3-miner.txt b/tools/prover-floor/points-sweep3-miner.txt new file mode 100644 index 000000000..dbd349a63 --- /dev/null +++ b/tools/prover-floor/points-sweep3-miner.txt @@ -0,0 +1,4 @@ +run m12 "$EMPTY" SP1_GPU_MEMORY_BUDGET_GB=12 +run m12 "$V1" SP1_GPU_MEMORY_BUDGET_GB=12 +run me26 "$V1" SP1_GPU_ELEMENT_THRESHOLD=67108864 +run me26 "$EMPTY" SP1_GPU_ELEMENT_THRESHOLD=67108864