This document discusses the development of an OpenCL compiler called VC4C for the VideoCore IV GPU found in the Raspberry Pi. It provides an overview of the VC4 architecture including its quad processing units, texture and memory lookup unit, uniform cache, and vertex pipe memory. It then introduces VC4C as an open-source project that compiles OpenCL to optimized assembly for the VC4. Several challenges are discussed such as limited registers, cache incoherency, and complex iteration patterns from OpenCL IDs. Optimization techniques explored include constant handling, vectorization, kernel fusion, and software pipelining. In conclusion, VC4C remains a work in progress but provides an opportunity for compiler optimization on an unoptimized

1. VC4C: Development of OpenCL
Compiler for VideoCore4
RaspberryPiのGPUを使うOSS OpenCL
コンパイラ開発の現状と課題
2018/11/10 コンパイラ勉強会@fixstars

2. 私は誰
・光のインターネットの闇
@no_maddo
・ideinのエンジニア

3. 本日のトピック
- VideoCore IV（以下VC4)の紹介
- Architecture
- Memory characteristics
- VC4Cの紹介
- ドイツの方のOSSプロジェクト、私じゃないよ
- Master論文のためのプロジェクトだったらしい
- VC4Cならではの考慮点
- VC4きつい
- OpenCLきつい

4. Idein’s technology
・Execute mobilenet v2 1.0 224x224: 8.4 FPS ~= 140ms

5. Why we can archive the performance?
・Performance maximam performance of VideoCore IV
・Hand-assembling parallel GPU code
・Run only on GPU
・No return during execution of the inference
・CPU usage is very low
・Pi Zero ($ 5 computer!!!) archive the performance

6. For the detail…..
See our president presentation

7. Why we “try” the OSS compiler?
・We don’t use VC4C in production now
・Tunning assembly is “hard”
・Diesel, TensorComprehension
・In near future, happy to write good performance
mathematical kernels in compiler…...

8. Architecture Introduction

9. VC4 overview

10. VC4 overview

11. QPU / Quad Processing Unit

12. QPU / Quad Processing Unit
・general purpose register A/B x32 (=64 registers)
・accumulator register r[0-3] (= 4 registers)

13. VC4 overview

14. TMU / Texture and Memory Lookup Unit

15. TMU / Texture and Memory Lookup Unit

16. TMU / Texture and Memory Lookup Unit

17. VC4 overview

18. Uniform cache

19. Uniform cache

20. Uniform cache

21. VC4 overview

22. VPM / Vertex Pipe Memory

23. VPM / Vertex Pipe Memory

24. Efficient data transfer

25. Assembly Example: Hello World
mov(r0, uniform) # load from uniform & set it to `r0
setup_vpm_write() # prepare for vpm write
mov(vpm, 1) # write 1 row (16 elements) to vpm
setup_dma_store(nrows=1)# declaration to output 1 row
mov(vpm_st_addr, r0) # start write to the address of `r0
wait_dma_store() # sync dma_store
exit()
See the repository: py-videocore

26. Ex: A = A * 2 + 1
ldi(ra1, 64)
ldi(rb1, 16)
mov(rb0, uniform)
mov(ra0, uniform)
imul24(r1, element_number,4)
iadd(r1, uniform, r1)
L.loop
iadd(r1, r1, ra1).mov(tmu0_s, r1)
mutex_acquire()
setup_vpm_write(nrows=1)
nop(sig=’load tmu0’)
fmul(r0, r4, 2.0)
fadd(vpm, r0, 1.0)
setup_dma_store(nrows=1)
mov(vpm_st_addr, rb0)
wait_dma_store()
mutex_release()
isub(ra0, ra0, rb1, set_flags=True)
jzc(L.loop)
iadd(rb0, rb0, ra1); nop(); nop()
exit()

27. Flow of execution
・allocate GPU memory
・build uniforms
・for each thread
・run driver
with Driver () as drv :
n_threads = 12
r = drv.alloc((n_threads, 128),
’float32’)
a = drv.alloc((n_threads, 128),
’float32’)
………
code = drv.program(mul2)
uniforms = drv.alloc((n_threads, 3),
‘uint32’)
uniforms[:, 0] = r.address()[:, 0]
uniforms[:, 1] = 128
uniforms[:, 2] = a.address()[0][0]
drv.execute(n_threads=n_threads,
program=code, uniforms=uniforms)

28. performance example: qmkl
$ sudo ./qmkl/test/sgemm 224 224 224
GPU: 6.17614e+09 [flop/s]
CPU: 9.78483e+08 [flop/s]
NEON: 1.06783e+09 [flop/s]
https://github.com/idein/qmkl
・mathematical kernels using VC4 cation: no-trans, no-trans

29. Performance issue
・low memory band-width:
・4.48 GBPS v.s. 98 GBPS in my computer...
・TMU Latecy (cycle):
・TMU cache hit: 9
・L2 cache hit: 12
・Memory: 20 (if v3d_freq=250 [MHz])
・cache incoherency

30. Cache incoherency 1
②
③
④
⑤
①

31. Cache incoherency

32. Cache incoherency

33. VC4C: OpenCL compiler for VC4

34. ・Parallel programming framework for
heterogene computing (GPU, DSP, FPGA, etc...)
・Support data paralle computing model
Recap: OpenCL
kernel void mul2(global float * a)
{
int id = get_global_id(0);
a[id] = a[id] * 2 + 1;
}
clCreateContext
clCreateProgramWithSource
clCreateBuffer
clEnqueueWriteBuffer
global_item_size = { 4, 8, 12 };
clEnqueueNDRangeKernel
compile at runtime
enqueue kernel
Host program

35. Recap: OpenCL

36. VC4C Overview
OpenCL runtime
offline compiler

37. Asm structure kernel void mul2(global float * a) {
int id = get_global_id(0);
a[id] = a[id] * 2 + 1;
}
・make implicit loop
・OpenCL parameters are
passed via uniform
・Loop exit are passed via
uniform

38. VC4C demo
Let’s check the output….

39. Current status: works if registers are enough
・Works fine if register-allocation is successful
・Lack of register-spilling
・Performance issue
・better instruction scheduling
・adjust clang loop-optimizations for VC4
・innermost loop unrolling
・improve DMA transportation
・auto-vectorization
Implementatio
Issue

40. VC4 specific optimization

41. ・To load 32bit constants, ldi is required
・Dealing with constants are costy
・moveConstantload removes ldi from loops
・But increase register-pressure…
immediate
ldi(r0, 0)
ldi(r2, 10)
L.loop
ldi(r1, 256)
iadd(r0, r0, r1)
isub(r2, r2, 1, set_flag=True)
bgt(L.loop)
nop(); nop(); nop()
ldi(r0, 0)
ldi(r2, 10)
ldi(r1, 256)
L.loop
iadd(r0, r0, r1)
isub(r2, r2, 1, set_flag=True)
bgt(L.loop)
nop(); nop(); nop()

42. Instead of rb regfile fields, limited imm can be encoded
・-16~15, 1.0, 2.0, 4.0, …
・by combining them, some imm can be ALU instruction
small immediate
ldi(r0, 0)
ldi(r2, 10)
L.loop
ldi(r1, 256)
iadd(r0, r0, r1)
isub(r2, r2, 1, set_flag=True)
bgt(L.loop)
nop(); nop(); nop()
mov(r0, 0)
mov(r2, 10)
imul24(r1, -16, -16)
L.loop
iadd(r0, r0, r1)
isub(r2, r2, 1, set_flag=True)
bgt(L.loop)
nop(); nop(); nop()

43. Fusion of writing VPM(WIP)
mov(r0, 0)
L.loop
setup_vpm_write(nrows=1)
mutex_acquire()
fadd(r1, uniform, 1.0)
iadd(r0, r0, 1).mov(vpm, r1)
mov(vpm_st_addr, rb0)
wait_dma_store()
mutex_release()
isub(None, r0, 3,
set_flag=True)
bne(L.loop)
nop(); nop(); nop()
setup_vpm_write(nrows=3)
fadd(ra0, uniform, 1.0)
fadd(ra1, uniform, 1.0)
fadd(ra2, uniform, 1.0)
mutex_acquire()
mov(vpm, ra0)
mov(vpm, ra1)
mov(vpm, ra2)
mov(vpm_st_addr, rb0)
wait_dma_store()
mutex_release()
Full unrolling

44. Hardware limitation
・Cache incoherency is huge problem
・Register-spill
・problematic in other GPU
・Effective TMU load
・If the same region is read/write, it makes wrong
・Use DMA discard parallelism at all

45. Insufficient use of DMA
kernel void mul2(global float * a)
{
int id = get_global_id(0);
a[id] = a[id] * 2 + 1;
}
・region a is read/write
・a is just read once
・Acutually, Load via TMU is safe
・required complex analysis…???

46. Complex iteration via OpenCL IDs
・implicit loops (by ids) are hard to convert to natural loops
・global_id + worker_id + local_id ……
・want to remove such parameters by offline-compilation

47. Fusion of kernels(WIP)
・Fusion of some kernels (GEMM + ReLu + bias, etc…)
・For reducing memory transfer
・Diesel (NVIDIA Compiler project)
reported the impact
from Diesel: DSL for linear algebra and neural net computations on GPUs

48. Software pipelining(WIP)?
・Probably, it is not effect…
・Due to instruction cache limitation
・We rerolled some kernels…..

49. Conclusion?
・Introduce VC4
・Dual-issue in-order processor
・You can write its assembly freely
・Introduce VC4C
・heavily under development
・compiler-lovers, here is a unmatured compiler!!!!

50. Reference
・VideoCore® IV 3D Architecture Reference Guide
・Raspberry PiのGPUで行列乗算(その1)
・Raspberry PiのGPUで行列乗算(その2)
・Hacking the Raspberry Pi's VideoCore IV GPU
・GPU_FFT
・blog@ysugi