Benchmark works again

9577deec · Jan Hönig · a534e81b · 9577deec
Commit 9577deec authored 3 years ago by Jan Hönig
--- a/doc/notebooks/demo_ve.ipynb
+++ b/doc/notebooks/demo_ve.ipynb
@@ -43,7 +43,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 1,
   "id": "5d56a49c-5963-4f86-a8d8-0b753a971e52",
   "metadata": {},
   "outputs": [],
@@ -54,7 +54,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 2,
   "id": "9c204a47-a39b-450b-9026-9bb63cf54e83",
   "metadata": {},
   "outputs": [],
@@ -64,7 +64,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 3,
   "id": "5bbc4118-e1b7-412b-9dc8-7d7d524786df",
   "metadata": {},
   "outputs": [],
@@ -75,19 +75,19 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 4,
   "id": "85641913-f00a-4f95-af69-c7646ad5b3d0",
   "metadata": {},
   "outputs": [],
   "source": [
-    "@ps.kernel(config)\n",
+    "@ps.kernel_config(config)\n",
    "def vadd():\n",
    "    a[0] @= b[0] + c[0]"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 5,
   "id": "33097862-9f60-4624-a1f2-0fdfd82831bc",
   "metadata": {},
   "outputs": [
@@ -115,19 +115,19 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 6,
   "id": "99aee06b-1704-4d06-b261-cc07a6a7f9a3",
   "metadata": {},
   "outputs": [],
   "source": [
-    "@ps.kernel(config)\n",
+    "@ps.kernel_config(config)\n",
    "def daxpy():\n",
    "    b[0] @= alpha * a[0] + b[0]"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 7,
   "id": "e79ab7bb-128e-47ee-9d53-8779c4f55d7e",
   "metadata": {},
   "outputs": [
@@ -155,19 +155,19 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 8,
   "id": "4bb14872-11de-42cc-b5fc-4f995c7a6725",
   "metadata": {},
   "outputs": [],
   "source": [
-    "@ps.kernel(config)\n",
+    "@ps.kernel_config(config)\n",
    "def daxpy_one_off():\n",
    "    b[0] @= alpha * a[0] + b[0]"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 9,
   "id": "457cc1fe-1aef-44bd-9fd1-f914e019c933",
   "metadata": {},
   "outputs": [
@@ -195,87 +195,51 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 12,
-   "id": "fea2f8e4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#from pystencils.kerncraft_coupling import generate_benchmark"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "id": "4fbd5c90",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#print(generate_benchmark(kernel_vadd))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
   "id": "ae05beb9-745f-4885-ad4f-667aae867f05",
   "metadata": {},
   "outputs": [],
   "source": [
-    "from pystencils.benchmark import kernel_header, kernel_source, generate_benchmark\n",
+    "from pystencils_benchmark import kernel_header, kernel_source, generate_benchmark\n",
    "from pathlib import Path"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 13,
   "id": "7dfa86e1-8962-47df-900c-3133883a19c7",
   "metadata": {},
   "outputs": [],
   "source": [
-    "example_path = Path.cwd() / 'example'\n",
+    "example_path = Path.cwd() / 'example'"
-    "example_path.mkdir(parents=True, exist_ok=True)"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 21,
   "id": "dd39502f-d935-4b88-b8c8-896b1a294bf9",
   "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "ename": "ValueError",
-     "evalue": "Unknown dialect='c'",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[0;31mValueError\u001B[0m                                Traceback (most recent call last)",
-      "\u001B[0;32m/tmp/ipykernel_209040/990452426.py\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[0;32m----> 1\u001B[0;31m \u001B[0mgenerate_benchmark\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mkernel_vadd\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mexample_path\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      2\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
-      "\u001B[0;32m~/git/pystencils/pystencils/benchmark/benchmark.py\u001B[0m in \u001B[0;36mgenerate_benchmark\u001B[0;34m(kernel_ast, path, dialect, kernel_name)\u001B[0m\n\u001B[1;32m     13\u001B[0m         \u001B[0mkernel_name\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mkernel_ast\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mfunction_name\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     14\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 15\u001B[0;31m     \u001B[0mheader\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mkernel_header\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mkernel_ast\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdialect\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     16\u001B[0m     \u001B[0;32mwith\u001B[0m \u001B[0mopen\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mpath\u001B[0m \u001B[0;34m/\u001B[0m \u001B[0;34mf'{kernel_name}.h'\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m'w+'\u001B[0m\u001B[0;34m)\u001B[0m \u001B[0;32mas\u001B[0m \u001B[0mf\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     17\u001B[0m         \u001B[0mf\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mwrite\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mheader\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
-      "\u001B[0;32m~/git/pystencils/pystencils/benchmark/benchmark.py\u001B[0m in \u001B[0;36mkernel_header\u001B[0;34m(kernel_ast, dialect)\u001B[0m\n\u001B[1;32m     23\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     24\u001B[0m \u001B[0;32mdef\u001B[0m \u001B[0mkernel_header\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mkernel_ast\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdialect\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;34m'c'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 25\u001B[0;31m     \u001B[0mfunction_signature\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mgenerate_c\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mkernel_ast\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mdialect\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0mdialect\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0msignature_only\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0;32mTrue\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     26\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     27\u001B[0m     jinja_context = {\n",
-      "\u001B[0;32m~/git/pystencils/pystencils/backends/cbackend.py\u001B[0m in \u001B[0;36mgenerate_c\u001B[0;34m(ast_node, signature_only, dialect, custom_backend, with_globals)\u001B[0m\n\u001B[1;32m     76\u001B[0m         \u001B[0mprinter\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mOpenClBackend\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0msignature_only\u001B[0m\u001B[0;34m=\u001B[0m\u001B[0msignature_only\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     77\u001B[0m     \u001B[0;32melse\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m---> 78\u001B[0;31m         \u001B[0;32mraise\u001B[0m \u001B[0mValueError\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34mf'Unknown {dialect=}'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m     79\u001B[0m     \u001B[0mcode\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mprinter\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mast_node\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m     80\u001B[0m     \u001B[0;32mif\u001B[0m \u001B[0;32mnot\u001B[0m \u001B[0msignature_only\u001B[0m \u001B[0;32mand\u001B[0m \u001B[0misinstance\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mast_node\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0mKernelFunction\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
-      "\u001B[0;31mValueError\u001B[0m: Unknown dialect='c'"
-     ]
-    }
-   ],
   "source": [
-    "generate_benchmark(kernel_vadd, example_path)"
+    "generate_benchmark([kernel_vadd, kernel_daxpy, kernel_daxpy_one_off], example_path)"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
   "id": "f084548f-3a8e-4d45-8c7e-5845013b222e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Examples:\n",
-    "generate_benchmark(kernel_daxpy, example_path)\n",
+    "# generate_benchmark(kernel_daxpy, example_path)\n",
-    "generate_benchmark(kernel_vadd, example_path)\n",
+    "# generate_benchmark(kernel_vadd, example_path)\n",
-    "generate_benchmark(kernel_daxpy_one_off, example_path)"
+    "# generate_benchmark(kernel_daxpy_one_off, example_path)"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
   "id": "954b5ec7-a88a-4723-bd7f-227a3919b32d",
   "metadata": {},
   "outputs": [],
@@ -283,7 +247,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
   "id": "f51f2aff-f232-4de9-a0c4-94d3682eff86",
   "metadata": {},
   "outputs": [],

 %% Cell type:markdown id:b79814e5-9a10-4b20-a886-c16db785bc48 tags:
 # LLVM-VE Vector Intrinsics
 - [Tutorial](https://sx-aurora-dev.github.io/ve-intrinsics-tutorial/)
 - [List of intrinsics](https://sx-aurora-dev.github.io/velintrin.html)
 - [Assembly manual](https://www.hpc.nec/documents/sdk/pdfs/VectorEngine-as-manual-v1.3.pdf)
 ## Vector Register
 - `__vr`: 256 x 64 bit values
 -  64 registers available (**beware of spilling**)
 ## Intrinsic Functions
 - format: `_vel_<asm>_<suffix>`
 - `<asm>`: instruction mnemonic in the [assembly manual](https://www.hpc.nec/documents/sdk/pdfs/VectorEngine-as-manual-v1.3.pdf)
    - has one suffix which handles the type: `d`: double
 - `<suffix>`: list of return value and arguments
    - `v`: vector
    - `s`: scalar
    - `m` and `M`: mask for 256 and 512 elements
    - `l`: vector length
 ## Vector Load/Store
 - 64 bit: `_vel_vld_vssl`
 - 32 bit: upper, lower or "packed"
 - 2 `s` arguments: stride; base adress
 ## Vector Length and Pass Through Argument
 - `l` defines how many elements are updated
 - all instructions with additional `v` available, which is passed to the non-updated elements (pass-through: `pt`)
 ## NT-Stores
 - `nc` variants of memory access intrinsics (e.g. `_vel_vldnc_vssl`)
 ## Vector Mask
 - `__vm256`: 256 bit
 - 8 registers
 - 0 bit -> no update
 - instructions with `m` suffix
 ## Packed Instructions
 - operations on 512 elements of `fp32` or `int32`.
 - `p` prefix (e.g. `_vel_pvfadd_vl`)
 - TBD...
 %% Cell type:code id:5d56a49c-5963-4f86-a8d8-0b753a971e52 tags:
 ``` python
 from pystencils.session import *
 import pystencils as ps
 ```
 %% Cell type:code id:9c204a47-a39b-450b-9026-9bb63cf54e83 tags:
 ``` python
 config = ps.CreateKernelConfig(cpu_vectorize_info={'instruction_set': 've'})
 ```
 %% Cell type:code id:5bbc4118-e1b7-412b-9dc8-7d7d524786df tags:
 ``` python
 a, b, c = ps.fields(a=np.ones(4000000), b=np.ones(4000000), c=np.ones(4000000))
 alpha = sp.symbols('alpha')
 ```
 %% Cell type:code id:85641913-f00a-4f95-af69-c7646ad5b3d0 tags:
 ``` python
-@ps.kernel(config)
+@ps.kernel_config(config)
 def vadd():
    a[0] @= b[0] + c[0]
 ```
 %% Cell type:code id:33097862-9f60-4624-a1f2-0fdfd82831bc tags:
 ``` python
 kernel_vadd = ps.create_kernel(**vadd)
 ps.show_code(kernel_vadd)
 ```
 %% Output
 %% Cell type:code id:99aee06b-1704-4d06-b261-cc07a6a7f9a3 tags:
 ``` python
-@ps.kernel(config)
+@ps.kernel_config(config)
 def daxpy():
    b[0] @= alpha * a[0] + b[0]
 ```
 %% Cell type:code id:e79ab7bb-128e-47ee-9d53-8779c4f55d7e tags:
 ``` python
 kernel_daxpy = ps.create_kernel(**daxpy)
 ps.show_code(kernel_daxpy)
 ```
 %% Output
 %% Cell type:code id:4bb14872-11de-42cc-b5fc-4f995c7a6725 tags:
 ``` python
-@ps.kernel(config)
+@ps.kernel_config(config)
 def daxpy_one_off():
    b[0] @= alpha * a[0] + b[0]
 ```
 %% Cell type:code id:457cc1fe-1aef-44bd-9fd1-f914e019c933 tags:
 ``` python
 kernel_daxpy_one_off = ps.create_kernel(**daxpy_one_off)
 ps.show_code(kernel_daxpy_one_off)
 ```
 %% Output
-%% Cell type:code id:fea2f8e4 tags:
-``` python
-#from pystencils.kerncraft_coupling import generate_benchmark
-```
-%% Cell type:code id:4fbd5c90 tags:
-``` python
-#print(generate_benchmark(kernel_vadd))
-```
 %% Cell type:code id:ae05beb9-745f-4885-ad4f-667aae867f05 tags:
 ``` python
-from pystencils.benchmark import kernel_header, kernel_source, generate_benchmark
+from pystencils_benchmark import kernel_header, kernel_source, generate_benchmark
 from pathlib import Path
 ```
 %% Cell type:code id:7dfa86e1-8962-47df-900c-3133883a19c7 tags:
 ``` python
 example_path = Path.cwd() / 'example'
-example_path.mkdir(parents=True, exist_ok=True)
 ```
 %% Cell type:code id:dd39502f-d935-4b88-b8c8-896b1a294bf9 tags:
 ``` python
-generate_benchmark(kernel_vadd, example_path)
+generate_benchmark([kernel_vadd, kernel_daxpy, kernel_daxpy_one_off], example_path)
 ```
-%% Output
-    ---------------------------------------------------------------------------
-    ValueError                                Traceback (most recent call last)
-    /tmp/ipykernel_209040/990452426.py in <module>
-    ----> 1 generate_benchmark(kernel_vadd, example_path)
-          2
-    ~/git/pystencils/pystencils/benchmark/benchmark.py in generate_benchmark(kernel_ast, path, dialect, kernel_name)
-         13         kernel_name = kernel_ast.function_name
-         14
-    ---> 15     header = kernel_header(kernel_ast, dialect)
-         16     with open(path / f'{kernel_name}.h', 'w+') as f:
-         17         f.write(header)
-    ~/git/pystencils/pystencils/benchmark/benchmark.py in kernel_header(kernel_ast, dialect)
-         23
-         24 def kernel_header(kernel_ast, dialect='c'):
-    ---> 25     function_signature = generate_c(kernel_ast, dialect=dialect, signature_only=True)
-         26
-         27     jinja_context = {
-    ~/git/pystencils/pystencils/backends/cbackend.py in generate_c(ast_node, signature_only, dialect, custom_backend, with_globals)
-         76         printer = OpenClBackend(signature_only=signature_only)
-         77     else:
-    ---> 78         raise ValueError(f'Unknown {dialect=}')
-         79     code = printer(ast_node)
-         80     if not signature_only and isinstance(ast_node, KernelFunction):
-    ValueError: Unknown dialect='c'
 %% Cell type:code id:f084548f-3a8e-4d45-8c7e-5845013b222e tags:
 ``` python
 # Examples:
-generate_benchmark(kernel_daxpy, example_path)
+# generate_benchmark(kernel_daxpy, example_path)
-generate_benchmark(kernel_vadd, example_path)
+# generate_benchmark(kernel_vadd, example_path)
-generate_benchmark(kernel_daxpy_one_off, example_path)
+# generate_benchmark(kernel_daxpy_one_off, example_path)
 ```
 %% Cell type:code id:954b5ec7-a88a-4723-bd7f-227a3919b32d tags:
 ``` python
 ```
 %% Cell type:code id:f51f2aff-f232-4de9-a0c4-94d3682eff86 tags:
 ``` python
 ```