scottt

from diffusers import StableDiffusionXLPipeline

pipe = StableDiffusionXLPipeline.from_pretrained(
	"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.bfloat16
).to("cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt, num_inference_steps=30).images[0]

scottt

import torch
from torch.nn.functional import scaled_dot_product_attention
from torch.nn.attention import SDPBackend

###############################################################################
# Check for GPU
###############################################################################
if not torch.cuda.is_available():
    raise SystemExit("CUDA GPU is not available. Please run on a CUDA-enabled device.")

scottt

#!/usr/bin/env python

import os
import sys
import subprocess
import time
from pathlib import Path

# --- Configuration ---

scottt

#!/usr/bin/env python

import os
import sys
import subprocess
import platform
import time
import signal
from pathlib import Path

scottt

#!/usr/bin/env python

import os
import sys
import subprocess
import time
from pathlib import Path

# --- Configuration ---

scottt

PROGRAMS := $(basename $(wildcard *.cpp))

ROCM_PREFIX := $(HOME)/therock-upstream-output/build/dist/rocm
HIP_CFLAGS := -I$(ROCM_PREFIX)/include
AOTRITON_CFLAGS := -D__HIP_PLATFORM_AMD__ -I$(HOME)/aotriton-output/build/install_dir/include
AOTRITON_LIBS := -L$(HOME)/aotriton-output/build/install_dir/lib -laotriton_v2 -L$(ROCM_PREFIX)/lib -lamdhip64

%: %.cpp
	clang++ $(HIP_CFLAGS) $(AOTRITON_CFLAGS) $< $(AOTRITON_LIBS) -o $@

scottt

#!/usr/bin/env python

import os
import sys
import subprocess
import time
from pathlib import Path

# --- Configuration ---

scottt

#include <stdio.h>
#include <stdint.h>
#include <sys/mman.h>

int main()
{
	mprotect((void *)((unsigned long)main & (~0xfff)), 4096,
		 PROT_EXEC|PROT_WRITE);
	{ // gcc and clang puts the "0:", "1:" etc labels below at different places
		char *p;

scottt

CFLAGS := -Wall -Og
PROGRAMS := fork-exec-memset vfork-exec-memset

.PHONY: all
all: $(PROGRAMS)

.PHONY: test
test: all
	./test-fork-exec-memset

scottt

# openssl speed -elapsed -evp aes-128-gcm
You have chosen to measure elapsed time instead of user CPU time.
Doing aes-128-gcm for 3s on 16 size blocks: 55740342 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 64 size blocks: 36792402 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 256 size blocks: 19513330 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 1024 size blocks: 6431553 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 8192 size blocks: 943229 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 16384 size blocks: 478375 aes-128-gcm's in 3.00s
OpenSSL 1.1.1c  28 May 2019
built on: Wed May 29 17:53:30 2019 UTC