diff --git a/dace/jupyter.py b/dace/jupyter.py
index 0f338908cd..c7ac85d6ee 100755
--- a/dace/jupyter.py
+++ b/dace/jupyter.py
@@ -8,7 +8,7 @@
def _connected():
try:
- urllib.request.urlopen('https://spcl.github.io/dace/webclient2/dist/sdfv.js', timeout=1)
+ urllib.request.urlopen('https://spcl.github.io/dace-webclient/dist/sdfv.js', timeout=1)
return True
except urllib.error.URLError:
return False
@@ -31,31 +31,22 @@ def isnotebook():
def preamble():
# Emit javascript headers for SDFG renderer
sdfv_js_deps = ['sdfv.js']
- sdfv_css_deps = ['sdfv.css']
+ offline_sdfv_js_deps = ['sdfv_jupyter.js']
result = ''
- # Rely on internet connection for Material icons
- result += '"
@@ -834,81 +818,6 @@
"446 ms ± 41.1 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
]
},
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- ":4: NumbaWarning: \u001b[1m\n",
- "Compilation is falling back to object mode WITH looplifting enabled because Function \"someforloop\" failed type inference due to: \u001b[1mUntyped global name 'element_update':\u001b[0m \u001b[1m\u001b[1mCannot determine Numba type of \u001b[0m\n",
- "\u001b[1m\n",
- "File \"\", line 7:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- " \n",
- " for j in range(A.shape[1]):\n",
- "\u001b[1m A[i, j] = element_update(A[i, j])\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\u001b[0m\n",
- " def someforloop(A):\n",
- ":4: NumbaWarning: \u001b[1m\n",
- "Compilation is falling back to object mode WITHOUT looplifting enabled because Function \"someforloop\" failed type inference due to: \u001b[1m\u001b[1mCannot determine Numba type of \u001b[0m\n",
- "\u001b[1m\n",
- "File \"\", line 5:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- "\u001b[1m for i in range(A.shape[0]):\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\u001b[0m\n",
- " def someforloop(A):\n",
- "/home/user/anaconda3/envs/py38/lib/python3.8/site-packages/numba/core/object_mode_passes.py:151: NumbaWarning: \u001b[1mFunction \"someforloop\" was compiled in object mode without forceobj=True, but has lifted loops.\n",
- "\u001b[1m\n",
- "File \"\", line 5:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- "\u001b[1m for i in range(A.shape[0]):\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\n",
- " warnings.warn(errors.NumbaWarning(warn_msg,\n",
- "/home/user/anaconda3/envs/py38/lib/python3.8/site-packages/numba/core/object_mode_passes.py:161: NumbaDeprecationWarning: \u001b[1m\n",
- "Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.\n",
- "\n",
- "For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit\n",
- "\u001b[1m\n",
- "File \"\", line 5:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- "\u001b[1m for i in range(A.shape[0]):\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\n",
- " warnings.warn(errors.NumbaDeprecationWarning(msg,\n",
- ":4: NumbaWarning: \u001b[1m\n",
- "Compilation is falling back to object mode WITHOUT looplifting enabled because Function \"someforloop\" failed type inference due to: \u001b[1mUntyped global name 'element_update':\u001b[0m \u001b[1m\u001b[1mCannot determine Numba type of \u001b[0m\n",
- "\u001b[1m\n",
- "File \"\", line 7:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- " \n",
- " for j in range(A.shape[1]):\n",
- "\u001b[1m A[i, j] = element_update(A[i, j])\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\u001b[0m\n",
- " def someforloop(A):\n",
- "/home/user/anaconda3/envs/py38/lib/python3.8/site-packages/numba/core/object_mode_passes.py:151: NumbaWarning: \u001b[1mFunction \"someforloop\" was compiled in object mode without forceobj=True.\n",
- "\u001b[1m\n",
- "File \"\", line 5:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- "\u001b[1m for i in range(A.shape[0]):\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\n",
- " warnings.warn(errors.NumbaWarning(warn_msg,\n",
- "/home/user/anaconda3/envs/py38/lib/python3.8/site-packages/numba/core/object_mode_passes.py:161: NumbaDeprecationWarning: \u001b[1m\n",
- "Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.\n",
- "\n",
- "For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit\n",
- "\u001b[1m\n",
- "File \"\", line 5:\u001b[0m\n",
- "\u001b[1mdef someforloop(A):\n",
- "\u001b[1m for i in range(A.shape[0]):\n",
- "\u001b[0m \u001b[1m^\u001b[0m\u001b[0m\n",
- "\u001b[0m\n",
- " warnings.warn(errors.NumbaDeprecationWarning(msg,\n"
- ]
- },
{
"name": "stdout",
"output_type": "stream",
diff --git a/tutorials/codegen.ipynb b/tutorials/codegen.ipynb
index 0de9fab2d9..a6effd7996 100644
--- a/tutorials/codegen.ipynb
+++ b/tutorials/codegen.ipynb
@@ -32,22 +32,7 @@
{
"data": {
"text/html": [
- ""
@@ -83,15 +68,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (simple)"
]
},
"execution_count": 2,
@@ -822,7 +812,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.6"
+ "version": "3.12.1"
}
},
"nbformat": 4,
diff --git a/tutorials/explicit.ipynb b/tutorials/explicit.ipynb
index 5ecd3fe590..7f9fbbd866 100644
--- a/tutorials/explicit.ipynb
+++ b/tutorials/explicit.ipynb
@@ -17,22 +17,7 @@
{
"data": {
"text/html": [
- ""
@@ -137,15 +122,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (transpose)"
]
},
"execution_count": 5,
@@ -375,9 +365,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.3"
+ "version": "3.12.1"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}
diff --git a/tutorials/getting_started.ipynb b/tutorials/getting_started.ipynb
index 31f3c13b11..4405c28d56 100644
--- a/tutorials/getting_started.ipynb
+++ b/tutorials/getting_started.ipynb
@@ -19,22 +19,7 @@
{
"data": {
"text/html": [
- ""
@@ -81,8 +66,8 @@
{
"data": {
"text/plain": [
- "array([[0.19830156, 0.1679383 , 0.19932212],\n",
- " [0.59336771, 0.20975676, 0.05706468]])"
+ "array([[0.74867876, 0.85403223, 0.16573784],\n",
+ " [0.71994615, 0.29855314, 0.21483992]])"
]
},
"execution_count": 3,
@@ -104,8 +89,8 @@
{
"data": {
"text/plain": [
- "array([[0.39660312, 0.33587661, 0.39864423],\n",
- " [1.18673541, 0.41951352, 0.11412936]])"
+ "array([[1.49735752, 1.70806445, 0.33147568],\n",
+ " [1.4398923 , 0.59710627, 0.42967985]])"
]
},
"execution_count": 4,
@@ -135,15 +120,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (getstarted)"
]
},
"execution_count": 5,
@@ -218,15 +208,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (getstarted_sym)"
]
},
"execution_count": 8,
@@ -253,19 +248,19 @@
{
"data": {
"text/plain": [
- "array([[0.22917578, 0.2371489 , 1.41801157, ..., 0.65790524, 0.95110319,\n",
- " 0.17970065],\n",
- " [0.38880002, 1.76962412, 0.10092406, ..., 0.01563938, 1.59546665,\n",
- " 0.91307168],\n",
- " [0.65812086, 0.41412414, 1.53311494, ..., 0.34473083, 1.71308857,\n",
- " 0.46120345],\n",
+ "array([[1.63216549, 1.26522381, 0.21606686, ..., 0.56988572, 1.12572538,\n",
+ " 1.72701877],\n",
+ " [0.3829452 , 1.52386969, 0.82165197, ..., 1.3105662 , 1.19336786,\n",
+ " 1.43671993],\n",
+ " [1.55277426, 1.50918516, 1.30665626, ..., 1.06562809, 1.53069088,\n",
+ " 1.10071159],\n",
" ...,\n",
- " [1.65819208, 0.38832393, 0.539072 , ..., 1.00576714, 0.84533283,\n",
- " 0.93827821],\n",
- " [1.39887643, 1.50380279, 1.85950996, ..., 0.48506318, 1.51421076,\n",
- " 1.84443427],\n",
- " [1.81472469, 1.50510688, 1.69746795, ..., 0.34524469, 0.63041897,\n",
- " 0.76394633]])"
+ " [0.60629736, 1.73240929, 1.26797782, ..., 1.72034476, 1.56691557,\n",
+ " 0.22283613],\n",
+ " [1.96245486, 1.60559508, 0.02009914, ..., 1.40944583, 1.44560312,\n",
+ " 0.37804927],\n",
+ " [1.17875002, 0.96963921, 0.28278902, ..., 1.56747976, 0.4616313 ,\n",
+ " 0.94999278]])"
]
},
"execution_count": 9,
@@ -288,7 +283,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
@@ -304,7 +299,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@@ -320,7 +315,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
@@ -329,14 +324,14 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "14.2 ms ± 465 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+ "12 ms ± 143 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
]
}
],
@@ -346,14 +341,14 @@
},
{
"cell_type": "code",
- "execution_count": 14,
+ "execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "8.6 ms ± 44.6 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+ "3.86 ms ± 271 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
]
}
],
@@ -372,25 +367,30 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (sse_sigma)"
]
},
- "execution_count": 15,
+ "execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
@@ -436,7 +436,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.7"
+ "version": "3.12.1"
}
},
"nbformat": 4,
diff --git a/tutorials/numpy_frontend.ipynb b/tutorials/numpy_frontend.ipynb
index 8e83f0a204..fafda2f1b1 100644
--- a/tutorials/numpy_frontend.ipynb
+++ b/tutorials/numpy_frontend.ipynb
@@ -24,22 +24,7 @@
{
"data": {
"text/html": [
- ""
@@ -121,15 +106,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (gemm)"
]
},
"execution_count": 5,
@@ -276,15 +266,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (forloop)"
]
},
"execution_count": 10,
@@ -332,15 +327,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (maptest)"
]
},
"execution_count": 11,
@@ -475,9 +475,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.7.7"
+ "version": "3.12.1"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}
diff --git a/tutorials/sdfg_api.ipynb b/tutorials/sdfg_api.ipynb
index 586115d85c..645158ce88 100644
--- a/tutorials/sdfg_api.ipynb
+++ b/tutorials/sdfg_api.ipynb
@@ -19,22 +19,7 @@
{
"data": {
"text/html": [
- ""
@@ -126,15 +111,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (jacobi2d)"
]
},
"execution_count": 5,
@@ -209,15 +199,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (jacobi2d)"
]
},
"execution_count": 7,
@@ -244,15 +239,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (jacobi2d)"
]
},
"execution_count": 8,
@@ -286,15 +286,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (jacobi2d)"
]
},
"execution_count": 9,
@@ -341,15 +346,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (jacobi2d)"
]
},
"execution_count": 11,
@@ -384,15 +394,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (jacobi2d)"
]
},
"execution_count": 12,
@@ -464,16 +479,7 @@
"cell_type": "code",
"execution_count": 14,
"metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "WARNING: Casting scalar argument \"N\" from int to \n",
- "WARNING: Casting scalar argument \"T\" from int to \n"
- ]
- }
- ],
+ "outputs": [],
"source": [
"sdfg(A=inp, N=N, T=T)"
]
@@ -487,7 +493,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Difference: 6.037729e-07\n"
+ "Difference: 1.6358224e-06\n"
]
}
],
@@ -512,9 +518,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.3"
+ "version": "3.12.1"
}
},
"nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
}
diff --git a/tutorials/transformations.ipynb b/tutorials/transformations.ipynb
index 511e8b1be3..d54b294e6e 100644
--- a/tutorials/transformations.ipynb
+++ b/tutorials/transformations.ipynb
@@ -31,22 +31,7 @@
{
"data": {
"text/html": [
- ""
@@ -84,15 +69,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 2,
@@ -121,15 +111,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 3,
@@ -159,15 +154,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 4,
@@ -196,15 +196,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 5,
@@ -237,8 +242,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Match: MapTiling in _Mult__map: ['__i0', '__i1']\n",
- "Match: MapTiling in _Add__map: ['__i0', '__i1']\n"
+ "Match: MapTiling in [MapEntry (_Mult__map[__i0=0:1000, __i1=0:1000])]\n",
+ "Match: MapTiling in [MapEntry (_Add__map[__i0=0:1000, __i1=0:1000])]\n"
]
}
],
@@ -275,7 +280,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Match found in state assign_4_4 . Nodes: [MapExit (_Mult__map[__i0=0:1000, __i1=0:1000]), AccessNode (__tmp1), MapEntry (_Add__map[__i0=0:1000, __i1=0:1000])]\n"
+ "Match found in state BinOp_5 . Nodes: [MapExit (_Mult__map[__i0=0:1000, __i1=0:1000]), AccessNode (__tmp0), MapEntry (_Add__map[__i0=0:1000, __i1=0:1000])]\n"
]
}
],
@@ -310,7 +315,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "_Mult__map[__i0=0:1000, __i1=0:1000] -> __tmp1 -> _Add__map[__i0=0:1000, __i1=0:1000]\n"
+ "_Mult__map[__i0=0:1000, __i1=0:1000] -> __tmp0 -> _Add__map[__i0=0:1000, __i1=0:1000]\n"
]
}
],
@@ -342,15 +347,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
"\n",
+ ""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 9,
@@ -388,15 +398,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 10,
@@ -434,59 +449,132 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "0. Transformation FPGATransformSDFG in dbladd\n",
- "1. Transformation FPGATransformState in assign_4_4\n",
- "2. Transformation GPUTransformLocalStorage in outer_fused[__i0=0:1000, __i1=0:1000]\n",
- "3. Transformation GPUTransformMap in outer_fused[__i0=0:1000, __i1=0:1000]\n",
- "4. Transformation GPUTransformSDFG in dbladd\n",
- "5. Transformation MapExpansion in outer_fused: ['__i0', '__i1']\n",
- "6. Transformation MapFission in outer_fused\n",
- "7. Transformation MapTiling in outer_fused: ['__i0', '__i1']\n",
- "8. Transformation NestSDFG in dbladd\n",
- "9. Transformation StripMining in outer_fused: ['__i0', '__i1']\n",
- "10. Transformation Vectorization in 6 -> 3 -> 7\n",
- "Select the pattern to apply (0 - 10 or name$id): 7(tile_sizes=(128,))\n",
- "You selected (7) pattern MapTiling in outer_fused: ['__i0', '__i1'] with parameters {'tile_sizes': (128,)}\n",
- "0. Transformation FPGATransformSDFG in dbladd\n",
- "1. Transformation FPGATransformState in assign_4_4\n",
- "2. Transformation GPUTransformLocalStorage in outer_fused[__i0=128*tile___i0:Min(1000, 128*tile___i0 + 128), __i1=128*tile___i1:Min(1000, 128*tile___i1 + 128)]\n",
- "3. Transformation GPUTransformLocalStorage in merged_tile___i0_outer_fused[tile___i0=0:int_ceil(1000, 128), tile___i1=0:int_ceil(1000, 128)]\n",
- "4. Transformation GPUTransformMap in outer_fused[__i0=128*tile___i0:Min(1000, 128*tile___i0 + 128), __i1=128*tile___i1:Min(1000, 128*tile___i1 + 128)]\n",
- "5. Transformation GPUTransformMap in merged_tile___i0_outer_fused[tile___i0=0:int_ceil(1000, 128), tile___i1=0:int_ceil(1000, 128)]\n",
- "6. Transformation GPUTransformSDFG in dbladd\n",
- "7. Transformation InLocalStorage in 8 -> 6\n",
- "8. Transformation MapExpansion in outer_fused: ['__i0', '__i1']\n",
- "9. Transformation MapExpansion in merged_tile___i0_outer_fused: ['tile___i0', 'tile___i1']\n",
- "10. Transformation MapFission in outer_fused\n",
- "11. Transformation MapTiling in outer_fused: ['__i0', '__i1']\n",
- "12. Transformation MapTiling in merged_tile___i0_outer_fused: ['tile___i0', 'tile___i1']\n",
- "13. Transformation NestSDFG in dbladd\n",
- "14. Transformation OutLocalStorage in 7 -> 9\n",
+ "0. Transformation ElementWiseArrayOperation in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "1. Transformation ElementWiseArrayOperation2D in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "2. Transformation FPGATransformSDFG in []\n",
+ "3. Transformation FPGATransformState in [SDFGState (BinOp_5)]\n",
+ "4. Transformation GPUTransformLocalStorage in outer_fused[__i0=0:1000, __i1=0:1000]\n",
+ "5. Transformation GPUTransformMap in outer_fused[__i0=0:1000, __i1=0:1000]\n",
+ "6. Transformation GPUTransformSDFG in []\n",
+ "7. Transformation MapDimShuffle in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "8. Transformation MapExpansion in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "9. Transformation MapFission in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "10. Transformation MapTiling in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "11. Transformation MapTilingWithOverlap in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "12. Transformation MapUnroll in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
+ "13. Transformation NestSDFG in []\n",
+ "14. Transformation ReductionNOperation in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])]\n",
"15. Transformation StripMining in outer_fused: ['__i0', '__i1']\n",
- "16. Transformation StripMining in merged_tile___i0_outer_fused: ['tile___i0', 'tile___i1']\n",
- "17. Transformation Vectorization in 6 -> 3 -> 7\n",
- "Select the pattern to apply (0 - 17 or name$id): \n",
- "You did not select a valid option. Quitting optimization ...\n"
+ "16. Transformation TaskletFusion in [Tasklet (_Mult_), AccessNode (__tmp0), Tasklet (_Add_)]\n"
]
},
{
- "data": {
- "text/html": [
- "\n",
- "
\n",
- ""
- ],
- "text/plain": [
- ""
- ]
- },
- "execution_count": 11,
- "metadata": {},
- "output_type": "execute_result"
+ "name": "stdin",
+ "output_type": "stream",
+ "text": [
+ "Select the pattern to apply (0 - 16 or name$id): MapExpansion$0\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "You selected (MapExpansion$0) pattern MapExpansion in [MapEntry (outer_fused[__i0=0:1000, __i1=0:1000])] with parameters {}\n",
+ "0. Transformation ElementWiseArrayOperation in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "1. Transformation FPGATransformSDFG in []\n",
+ "2. Transformation FPGATransformState in [SDFGState (BinOp_5)]\n",
+ "3. Transformation GPUGridStridedTiling in [MapEntry (outer_fused[__i0=0:1000]), MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "4. Transformation GPUTransformLocalStorage in outer_fused[__i0=0:1000]\n",
+ "5. Transformation GPUTransformMap in outer_fused[__i0=0:1000]\n",
+ "6. Transformation GPUTransformMap in outer_fused___i1[__i1=0:1000]\n",
+ "7. Transformation GPUTransformSDFG in []\n",
+ "8. Transformation InLocalStorage in outer_fused[__i0=0:1000] -> outer_fused___i1[__i1=0:1000]\n",
+ "9. Transformation MPITransformMap in [MapEntry (outer_fused[__i0=0:1000])]\n",
+ "10. Transformation MPITransformMap in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "11. Transformation MapDimShuffle in [MapEntry (outer_fused[__i0=0:1000])]\n",
+ "12. Transformation MapDimShuffle in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "13. Transformation MapFission in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "14. Transformation MapInterchange in [MapEntry (outer_fused[__i0=0:1000]), MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "15. Transformation MapTiling in [MapEntry (outer_fused[__i0=0:1000])]\n",
+ "16. Transformation MapTiling in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "17. Transformation MapTilingWithOverlap in [MapEntry (outer_fused[__i0=0:1000])]\n",
+ "18. Transformation MapTilingWithOverlap in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "19. Transformation MapToForLoop in [MapEntry (outer_fused[__i0=0:1000])]\n",
+ "20. Transformation MapToForLoop in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "21. Transformation MapUnroll in [MapEntry (outer_fused[__i0=0:1000])]\n",
+ "22. Transformation NestSDFG in []\n",
+ "23. Transformation OutLocalStorage in outer_fused___i1[__i1=0:1000] -> outer_fused[__i0=0:1000]\n",
+ "24. Transformation ReductionNOperation in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "25. Transformation StripMining in outer_fused: ['__i0']\n",
+ "26. Transformation StripMining in outer_fused___i1: ['__i1']\n",
+ "27. Transformation TaskletFusion in [Tasklet (_Mult_), AccessNode (__tmp0), Tasklet (_Add_)]\n"
+ ]
+ },
+ {
+ "name": "stdin",
+ "output_type": "stream",
+ "text": [
+ "Select the pattern to apply (0 - 27 or name$id): MapTiling$0(tile_sizes=(128,))\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "You selected (MapTiling$0) pattern MapTiling in [MapEntry (outer_fused[__i0=0:1000])] with parameters {'tile_sizes': (128,)}\n",
+ "0. Transformation ElementWiseArrayOperation in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "1. Transformation FPGATransformSDFG in []\n",
+ "2. Transformation FPGATransformState in [SDFGState (BinOp_5)]\n",
+ "3. Transformation GPUGridStridedTiling in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1]), MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "4. Transformation GPUGridStridedTiling in [MapEntry (outer_fused[tile___i0=0:1000:128]), MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1])]\n",
+ "5. Transformation GPUTransformLocalStorage in outer_fused[tile___i0=0:1000:128]\n",
+ "6. Transformation GPUTransformMap in outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1]\n",
+ "7. Transformation GPUTransformMap in outer_fused___i1[__i1=0:1000]\n",
+ "8. Transformation GPUTransformMap in outer_fused[tile___i0=0:1000:128]\n",
+ "9. Transformation GPUTransformSDFG in []\n",
+ "10. Transformation InLocalStorage in outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1] -> outer_fused___i1[__i1=0:1000]\n",
+ "11. Transformation InLocalStorage in outer_fused[tile___i0=0:1000:128] -> outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1]\n",
+ "12. Transformation MPITransformMap in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1])]\n",
+ "13. Transformation MPITransformMap in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "14. Transformation MPITransformMap in [MapEntry (outer_fused[tile___i0=0:1000:128])]\n",
+ "15. Transformation MapDimShuffle in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1])]\n",
+ "16. Transformation MapDimShuffle in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "17. Transformation MapDimShuffle in [MapEntry (outer_fused[tile___i0=0:1000:128])]\n",
+ "18. Transformation MapFission in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "19. Transformation MapInterchange in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1]), MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "20. Transformation MapTiling in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1])]\n",
+ "21. Transformation MapTiling in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "22. Transformation MapTiling in [MapEntry (outer_fused[tile___i0=0:1000:128])]\n",
+ "23. Transformation MapTilingWithOverlap in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1])]\n",
+ "24. Transformation MapTilingWithOverlap in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "25. Transformation MapTilingWithOverlap in [MapEntry (outer_fused[tile___i0=0:1000:128])]\n",
+ "26. Transformation MapToForLoop in [MapEntry (outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1])]\n",
+ "27. Transformation MapToForLoop in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "28. Transformation MapToForLoop in [MapEntry (outer_fused[tile___i0=0:1000:128])]\n",
+ "29. Transformation MapUnroll in [MapEntry (outer_fused[tile___i0=0:1000:128])]\n",
+ "30. Transformation NestSDFG in []\n",
+ "31. Transformation OutLocalStorage in outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1] -> outer_fused[tile___i0=0:1000:128]\n",
+ "32. Transformation OutLocalStorage in outer_fused___i1[__i1=0:1000] -> outer_fused[__i0=tile___i0:Min(999, tile___i0 + 127) + 1]\n",
+ "33. Transformation ReductionNOperation in [MapEntry (outer_fused___i1[__i1=0:1000])]\n",
+ "34. Transformation StripMining in outer_fused: ['__i0']\n",
+ "35. Transformation StripMining in outer_fused___i1: ['__i1']\n",
+ "36. Transformation StripMining in outer_fused: ['tile___i0']\n",
+ "37. Transformation TaskletFusion in [Tasklet (_Mult_), AccessNode (__tmp0), Tasklet (_Add_)]\n"
+ ]
+ },
+ {
+ "name": "stdin",
+ "output_type": "stream",
+ "text": [
+ "Select the pattern to apply (0 - 37 or name$id): \n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "You did not select a valid option. Quitting optimization ...\n"
+ ]
}
],
"source": [
@@ -565,15 +653,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 12,
@@ -721,15 +814,20 @@
"data": {
"text/html": [
"\n",
- "
\n",
+ "\n",
+ "\n",
""
],
"text/plain": [
- ""
+ "SDFG (dbladd)"
]
},
"execution_count": 15,
@@ -780,7 +878,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.8.5"
+ "version": "3.12.1"
}
},
"nbformat": 4,