Use memcpy and memset from musl for performance benefit (#277)

Base: commit 37e18b7bf307fa4a8c745feebfcba54a0ba74f30
- src/string/memcpy.c
- src/string/memset.c

This was compiled into assembly with:

 clang-14 -target riscv32 -march=rv32im -O3 -S memcpy.c -nostdlib -fno-builtin -funroll-loops

and labels manually updated to not conflict

License is MIT, see https://git.musl-libc.org/cgit/musl/tree/COPYRIGHT and indicated in the .s files

Signed-off-by: Carsten Munk <carsten@zippie.com>

Signed-off-by: Carsten Munk <carsten@zippie.com>
Co-authored-by: Carsten Munk <carsten@zippie.com>
Co-authored-by: Frank Laub <flaub@risc0.com>

risc0/zkvm/sdk/rust/guest/BUILD.bazel

@@ -8,7 +8,7 @@ rust_library(
     name = "guest",
     srcs = glob(["src/**/*.rs"]),
     crate_name = "risc0_zkvm_guest",
-    data = ["README.md"],
+    data = ["README.md", "src/memset.s", "src/memcpy.s"],
     deps = [
         "//risc0/zkp/rust:zkp_guest",
         "//risc0/zkvm/sdk/rust:zkvm_guest",

risc0/zkvm/sdk/rust/guest/src/lib.rs

@@ -34,7 +34,12 @@ pub mod sha;
 #[cfg(feature = "pure-prove")]
 pub mod sha_insecure;
 
-use core::{arch::asm, mem, ptr};
+use core::{arch::asm, arch::global_asm, mem, ptr};
+
+#[cfg(target_arch = "riscv32")]
+global_asm!(include_str!("memset.s"));
+#[cfg(target_arch = "riscv32")]
+global_asm!(include_str!("memcpy.s"));
 
 extern "C" {
     fn _fault() -> !;