warp-lang 1.2.0__py3-none-manylinux2014_x86_64.whl → 1.2.2__py3-none-manylinux2014_x86_64.whl

warp/config.py

@@ -7,7 +7,7 @@
 
 from typing import Optional
 
-version: str = "1.2.0"
+version: str = "1.2.2"
 
 verify_fp: bool = False  # verify inputs and outputs are finite after each launch
 verify_cuda: bool = False  # if true will check CUDA errors after each kernel launch / memory operation

warp/context.py

@@ -1488,8 +1488,9 @@ class Module:
 
                 # functions source
                 for function in module.functions.values():
-                    # include all overloads
-                    for sig, func in function.user_overloads.items():
+                    # include all concrete and generic overloads
+                    overloads = itertools.chain(function.user_overloads.items(), function.user_templates.items())
+                    for sig, func in overloads:
                         # signature
                         ch.update(bytes(sig, "utf-8"))
 
@@ -3632,6 +3633,9 @@ def is_mempool_access_supported(target_device: Devicelike, peer_device: Deviceli
 
     init()
 
+    target_device = runtime.get_device(target_device)
+    peer_device = runtime.get_device(peer_device)
+
     return target_device.is_mempool_supported and is_peer_access_supported(target_device, peer_device)
 
 
@@ -4041,7 +4045,7 @@ def full(
             # a sequence, assume it's a vector or matrix value
             try:
                 # try to convert to a numpy array first
-                na = np.array(value, copy=False)
+                na = np.asarray(value)
             except Exception as e:
                 raise ValueError(f"Failed to interpret the value as a vector or matrix: {e}") from e
 

warp/tests/test_vec_scalar_ops.py

@@ -687,10 +687,22 @@ def test_equality(test, device, dtype, register_kernels=False):
     vec4 = wp.types.vector(length=4, dtype=wptype)
     vec5 = wp.types.vector(length=5, dtype=wptype)
 
-    def check_equality(
+    def check_unsigned_equality(
         v20: wp.array(dtype=vec2),
         v21: wp.array(dtype=vec2),
         v22: wp.array(dtype=vec2),
+        v30: wp.array(dtype=vec3),
+        v40: wp.array(dtype=vec4),
+        v50: wp.array(dtype=vec5),
+    ):
+        wp.expect_eq(v20[0], v20[0])
+        wp.expect_neq(v21[0], v20[0])
+        wp.expect_neq(v22[0], v20[0])
+        wp.expect_eq(v30[0], v30[0])
+        wp.expect_eq(v40[0], v40[0])
+        wp.expect_eq(v50[0], v50[0])
+
+    def check_signed_equality(
         v30: wp.array(dtype=vec3),
         v31: wp.array(dtype=vec3),
         v32: wp.array(dtype=vec3),
@@ -707,29 +719,21 @@ def test_equality(test, device, dtype, register_kernels=False):
         v54: wp.array(dtype=vec5),
         v55: wp.array(dtype=vec5),
     ):
-        wp.expect_eq(v20[0], v20[0])
-        wp.expect_neq(v21[0], v20[0])
-        wp.expect_neq(v22[0], v20[0])
-
-        wp.expect_eq(v30[0], v30[0])
         wp.expect_neq(v31[0], v30[0])
         wp.expect_neq(v32[0], v30[0])
         wp.expect_neq(v33[0], v30[0])
-
-        wp.expect_eq(v40[0], v40[0])
         wp.expect_neq(v41[0], v40[0])
         wp.expect_neq(v42[0], v40[0])
         wp.expect_neq(v43[0], v40[0])
         wp.expect_neq(v44[0], v40[0])
-
-        wp.expect_eq(v50[0], v50[0])
         wp.expect_neq(v51[0], v50[0])
         wp.expect_neq(v52[0], v50[0])
         wp.expect_neq(v53[0], v50[0])
         wp.expect_neq(v54[0], v50[0])
         wp.expect_neq(v55[0], v50[0])
 
-    kernel = getkernel(check_equality, suffix=dtype.__name__)
+    unsigned_kernel = getkernel(check_unsigned_equality, suffix=dtype.__name__)
+    signed_kernel = getkernel(check_signed_equality, suffix=dtype.__name__)
 
     if register_kernels:
         return
@@ -739,49 +743,64 @@ def test_equality(test, device, dtype, register_kernels=False):
     v22 = wp.array([3.0, 2.0], dtype=vec2, requires_grad=True, device=device)
 
     v30 = wp.array([1.0, 2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
-    v31 = wp.array([-1.0, 2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
-    v32 = wp.array([1.0, -2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
-    v33 = wp.array([1.0, 2.0, -3.0], dtype=vec3, requires_grad=True, device=device)
-
     v40 = wp.array([1.0, 2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
-    v41 = wp.array([-1.0, 2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
-    v42 = wp.array([1.0, -2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
-    v43 = wp.array([1.0, 2.0, -3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
-    v44 = wp.array([1.0, 2.0, 3.0, -4.0], dtype=vec4, requires_grad=True, device=device)
-
     v50 = wp.array([1.0, 2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
-    v51 = wp.array([-1.0, 2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
-    v52 = wp.array([1.0, -2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
-    v53 = wp.array([1.0, 2.0, -3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
-    v54 = wp.array([1.0, 2.0, 3.0, -4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
-    v55 = wp.array([1.0, 2.0, 3.0, 4.0, -5.0], dtype=vec5, requires_grad=True, device=device)
+
     wp.launch(
-        kernel,
+        unsigned_kernel,
         dim=1,
         inputs=[
             v20,
             v21,
             v22,
             v30,
-            v31,
-            v32,
-            v33,
             v40,
-            v41,
-            v42,
-            v43,
-            v44,
             v50,
-            v51,
-            v52,
-            v53,
-            v54,
-            v55,
         ],
         outputs=[],
         device=device,
     )
 
+    if dtype not in np_unsigned_int_types:
+        v31 = wp.array([-1.0, 2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
+        v32 = wp.array([1.0, -2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
+        v33 = wp.array([1.0, 2.0, -3.0], dtype=vec3, requires_grad=True, device=device)
+
+        v41 = wp.array([-1.0, 2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
+        v42 = wp.array([1.0, -2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
+        v43 = wp.array([1.0, 2.0, -3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
+        v44 = wp.array([1.0, 2.0, 3.0, -4.0], dtype=vec4, requires_grad=True, device=device)
+
+        v51 = wp.array([-1.0, 2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
+        v52 = wp.array([1.0, -2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
+        v53 = wp.array([1.0, 2.0, -3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
+        v54 = wp.array([1.0, 2.0, 3.0, -4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
+        v55 = wp.array([1.0, 2.0, 3.0, 4.0, -5.0], dtype=vec5, requires_grad=True, device=device)
+
+        wp.launch(
+            signed_kernel,
+            dim=1,
+            inputs=[
+                v30,
+                v31,
+                v32,
+                v33,
+                v40,
+                v41,
+                v42,
+                v43,
+                v44,
+                v50,
+                v51,
+                v52,
+                v53,
+                v54,
+                v55,
+            ],
+            outputs=[],
+            device=device,
+        )
+
 
 def test_scalar_multiplication(test, device, dtype, register_kernels=False):
     rng = np.random.default_rng(123)

warp/types.py

@@ -1650,9 +1650,10 @@ class array(Array):
             try:
                 # Performance note: try first, ask questions later
                 device = warp.context.runtime.get_device(device)
-            except:
-                warp.context.init()
-                raise
+            except Exception:
+                # Fallback to using the public API for retrieving the device,
+                # which takes take of initializing Warp if needed.
+                device = warp.context.get_device(device)
 
             if device.is_cuda:
                 desc = data.__cuda_array_interface__
@@ -1684,7 +1685,7 @@ class array(Array):
         if dtype == Any:
             # infer dtype from data
             try:
-                arr = np.array(data, copy=False, ndmin=1)
+                arr = np.asarray(data)
             except Exception as e:
                 raise RuntimeError(f"Failed to convert input data to an array: {e}") from e
             dtype = np_dtype_to_warp_type.get(arr.dtype)
@@ -1723,7 +1724,7 @@ class array(Array):
                     f"Failed to convert input data to an array with Warp type {warp.context.type_str(dtype)}"
                 )
             try:
-                arr = np.array(data, dtype=npdtype, copy=False, ndmin=1)
+                arr = np.asarray(data, dtype=npdtype)
             except Exception as e:
                 raise RuntimeError(f"Failed to convert input data to an array with type {npdtype}: {e}") from e
 
@@ -1779,9 +1780,10 @@ class array(Array):
         try:
             # Performance note: try first, ask questions later
             device = warp.context.runtime.get_device(device)
-        except:
-            warp.context.init()
-            raise
+        except Exception:
+            # Fallback to using the public API for retrieving the device,
+            # which takes take of initializing Warp if needed.
+            device = warp.context.get_device(device)
 
         if device.is_cpu and not copy and not pinned:
             # reference numpy memory directly
@@ -1805,9 +1807,10 @@ class array(Array):
         try:
             # Performance note: try first, ask questions later
             device = warp.context.runtime.get_device(device)
-        except:
-            warp.context.init()
-            raise
+        except Exception:
+            # Fallback to using the public API for retrieving the device,
+            # which takes take of initializing Warp if needed.
+            device = warp.context.get_device(device)
 
         check_array_shape(shape)
         ndim = len(shape)
@@ -1852,9 +1855,10 @@ class array(Array):
         try:
             # Performance note: try first, ask questions later
             device = warp.context.runtime.get_device(device)
-        except:
-            warp.context.init()
-            raise
+        except Exception:
+            # Fallback to using the public API for retrieving the device,
+            # which takes take of initializing Warp if needed.
+            device = warp.context.get_device(device)
 
         check_array_shape(shape)
         ndim = len(shape)
@@ -2329,7 +2333,7 @@ class array(Array):
                 a = self.to("cpu", requires_grad=False)
             # convert through __array_interface__
             # Note: this handles arrays of structs using `descr`, so the result will be a structured NumPy array
-            return np.array(a, copy=False)
+            return np.asarray(a)
         else:
             # return an empty numpy array with the correct dtype and shape
             if isinstance(self.dtype, warp.codegen.Struct):

{warp_lang-1.2.0.dist-info → warp_lang-1.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: warp-lang
-Version: 1.2.0
+Version: 1.2.2
 Summary: A Python framework for high-performance simulation and graphics programming
 Author-email: NVIDIA <mmacklin@nvidia.com>
 License: NVIDIA Software License
@@ -108,7 +108,10 @@ print(lengths)
 
 ## Running Examples
 
-The `examples` directory contains a number of scripts that show how to implement different simulation methods using the Warp API. Most examples will generate USD files containing time-sampled animations (stored in the current working directory). Before running examples, users should ensure that the ``usd-core``, ``matplotlib``, and ``pyglet`` packages are installed using:
+The [warp/examples](./warp/examples/) directory contains a number of scripts categorized under different subdirectories
+that show how to implement different simulation methods using the Warp API.
+Most examples will generate USD files containing time-sampled animations (stored in the current working directory).
+Before running examples, users should ensure that the ``usd-core``, ``matplotlib``, and ``pyglet`` packages are installed using:
 
     pip install usd-core matplotlib pyglet
 

{warp_lang-1.2.0.dist-info → warp_lang-1.2.2.dist-info}/RECORD

@@ -4,9 +4,9 @@ warp/build.py,sha256=LmRSU00pdlN1P31XS1_FhXgu_k7GzKkAzPd0LacZClo,3690
 warp/build_dll.py,sha256=p9eTXMhKbI0uTkpqeY5DxOmVhupfaykM-a-re6fXBXg,15896
 warp/builtins.py,sha256=AlHPF8WTvTOF2DGo8nQJ_OmZ5nzkoTi_qPLDlc6fPg0,122322
 warp/codegen.py,sha256=MJC5a63p-eXelMivb0Tyg6hU_ZCuqx8nMDSE7Om0BV0,103205
-warp/config.py,sha256=Spi7LsenwhcJubEYYMAmlzYEoVdGQ1qPNJjeqEICsv8,1879
+warp/config.py,sha256=gRyon6yrUl16-XDLbTYV7PfuXBMWTLOiAnx129lWIzs,1879
 warp/constants.py,sha256=ckfEqwbg109RJDW98SILe_yfOBEFolOATVjt0mU2py4,1321
-warp/context.py,sha256=J0w1vzGBh1r0JXz-A0bf1rytV5E5WtZEv2gPGxt4yzg,213400
+warp/context.py,sha256=QEGden9SZLlWFUhEwHJEXSNOLOMaFTxMA79DQzzOXaA,213608
 warp/dlpack.py,sha256=z242iSS70YF-5IP-GVE83R7HbHB5aRMmiYiQlAbyNis,16568
 warp/fabric.py,sha256=__Dbd9TmF5bqxUh411dpiAGxrlsfDAwZ8benjXN3Jco,11316
 warp/jax.py,sha256=QKJXfpz1jjaRD-Yp4C4wC4jUv8jHj0en3MW0VXKq0ZA,5280
@@ -15,9 +15,9 @@ warp/sparse.py,sha256=57Ar8OknSZ5P0apLLm_hnhxWlj0bh6U-mbu2qfYDcis,42356
 warp/stubs.py,sha256=wS3_3Joiutw9cecEzae5GyYHIOUH6wl8CdLeozueqks,57977
 warp/tape.py,sha256=hH3Qb9CiKHmq5OUIHRTZjZdYDXR2noHFNiB9HrIl5ZU,47864
 warp/torch.py,sha256=5hRCNL5jJzrh3hAcn1DdYfTvdOA5fvBy0VQnHviZpkE,11760
-warp/types.py,sha256=1OlIRSbwHFDbOPcnCxOi5lQcGCY6kn2Iwp-5kuntML8,169680
+warp/types.py,sha256=xKBWVRektFwU4r5FPL8ePR-ZR6_ue30wzVMfz2iHaK0,170236
 warp/utils.py,sha256=UoTCl9kGlPJBlsgvhM726VsnMkUsQSamxLQ0vgR1h5s,34148
-warp/bin/warp-clang.so,sha256=xb3cMPnm75SkqEdGNRasxJPSD-WjSJfekR5jmpsCJ9E,66204032
+warp/bin/warp-clang.so,sha256=mKEvTDt6X2fkaD0XJUdTHcwUI-_18rtTls9z5nTYdKA,66199872
 warp/bin/warp.so,sha256=riEf32U_pt1CNMMOdnlYXlew7_olGsPxwB8XObD89sM,110600160
 warp/examples/__init__.py,sha256=ul3vRFtQ17_zIZIWJaCnCY28KZTGOUHQA4wA_IW_qaw,606
 warp/examples/browse.py,sha256=6v7F0vpZz5ZtYGkg8hIpxhbIZ2ECv46cIKAmKVtV1S4,848
@@ -329,7 +329,7 @@ warp/tests/test_types.py,sha256=gQcQXTFK41QkfMKGP9fXd_WTtdlFNiPotAY6TpdvEsM,2211
 warp/tests/test_utils.py,sha256=_LixxYRl-7sj4YbcdSZNjaTrh72MRiadLr8iElvW0v4,18801
 warp/tests/test_vec.py,sha256=50B7gKFzMTNGmp0amBndlfLIF6yOk4GKMRPEu-mxmdg,42423
 warp/tests/test_vec_lite.py,sha256=zcTogrKDqYJsJXlAvR8zsSYiVsCB-mqphark6ULehcA,2343
-warp/tests/test_vec_scalar_ops.py,sha256=lRnkyH-MCeoCKpnp_x03mfx4BIjBrUvWkdNFva2Ot6o,84906
+warp/tests/test_vec_scalar_ops.py,sha256=A7B5gDXpyEExHahORUkHaErO9NB5Zt6mHwxT1iStvTk,85526
 warp/tests/test_verify_fp.py,sha256=KQuFVhAfjQ8YQHWWHP6vj7SX8zatGRJmfMDTotc7JBQ,2343
 warp/tests/test_volume.py,sha256=QlvrJUpZ8Wq1PAd5a0o-YqTJEMbFf3qNkhikXjmRHhI,33909
 warp/tests/test_volume_write.py,sha256=VMy40l3ioInNovw-ooz7-o1vdVPK-kMkEXd1-cb309E,11531
@@ -352,8 +352,8 @@ warp/thirdparty/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 warp/thirdparty/appdirs.py,sha256=2UXPK-AkDGoN5APeqAMMYkkfgf3Q_aUEZxcfkIxlQn0,24254
 warp/thirdparty/dlpack.py,sha256=OzMyVi5uQU01n0yEquDotgYvEAmfXT93QaIV4p4QqB4,4273
 warp/thirdparty/unittest_parallel.py,sha256=5z6oi9tsk2fOxhP4fx8hXRGveDTLM9fcESfzMWxJLFs,20998
-warp_lang-1.2.0.dist-info/LICENSE.md,sha256=Gq_TN0Xfat8Ftq2Rlvc31NgxdpLGVB-34kp-4eoeDV0,19265
-warp_lang-1.2.0.dist-info/METADATA,sha256=JEx5lbyT9BHlLuQzlBUxBXLSE79bcDchLWtHJi6c15I,20549
-warp_lang-1.2.0.dist-info/WHEEL,sha256=tlJxHuB9B338XjSv8YGiDebYqhyHpN1cFwihGfSw9Hw,110
-warp_lang-1.2.0.dist-info/top_level.txt,sha256=8pupHORyKoiN_BYWlTmv5OFBWdhqpppiBYQV5KxgEvg,5
-warp_lang-1.2.0.dist-info/RECORD,,
+warp_lang-1.2.2.dist-info/LICENSE.md,sha256=Gq_TN0Xfat8Ftq2Rlvc31NgxdpLGVB-34kp-4eoeDV0,19265
+warp_lang-1.2.2.dist-info/METADATA,sha256=pFezgRswKflUhG_fCs5O56jEEZvH_MHJ92tIXXlKQso,20615
+warp_lang-1.2.2.dist-info/WHEEL,sha256=tlJxHuB9B338XjSv8YGiDebYqhyHpN1cFwihGfSw9Hw,110
+warp_lang-1.2.2.dist-info/top_level.txt,sha256=8pupHORyKoiN_BYWlTmv5OFBWdhqpppiBYQV5KxgEvg,5
+warp_lang-1.2.2.dist-info/RECORD,,