Merge pull request #11263 from chris-b1/tslib-gil

jreback · jreback · commit 7e5b223d417c · 2015-10-17T10:48:10.000-04:00
PERF: Release GIL on some datetime ops
diff --git a/asv_bench/benchmarks/gil.py b/asv_bench/benchmarks/gil.py
@@ -320,3 +320,49 @@ def time_nogil_kth_smallest(self):
         def run(arr):
             algos.kth_smallest(arr, self.k)
         run()
+
+class nogil_datetime_fields(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 100000000
+        self.dti = pd.date_range('1900-01-01', periods=self.N, freq='D')
+        self.period = self.dti.to_period('D')
+        if (not have_real_test_parallel):
+            raise NotImplementedError
+
+    def time_datetime_field_year(self):
+        @test_parallel(num_threads=2)
+        def run(dti):
+            dti.year
+        run(self.dti)
+
+    def time_datetime_field_day(self):
+        @test_parallel(num_threads=2)
+        def run(dti):
+            dti.day
+        run(self.dti)
+
+    def time_datetime_field_daysinmonth(self):
+        @test_parallel(num_threads=2)
+        def run(dti):
+            dti.days_in_month
+        run(self.dti)
+
+    def time_datetime_field_normalize(self):
+        @test_parallel(num_threads=2)
+        def run(dti):
+            dti.normalize()
+        run(self.dti)
+
+    def time_datetime_to_period(self):
+        @test_parallel(num_threads=2)
+        def run(dti):
+            dti.to_period('S')
+        run(self.dti)
+
+    def time_period_to_datetime(self):
+        @test_parallel(num_threads=2)
+        def run(period):
+            period.to_timestamp()
+        run(self.period)
diff --git a/doc/source/whatsnew/v0.17.1.txt b/doc/source/whatsnew/v0.17.1.txt
@@ -58,6 +58,10 @@ Performance Improvements
 
 - Checking monotonic-ness before sorting on an index (:issue:`11080`)
 
+
+- Release the GIL on most datetime field operations (e.g. ``DatetimeIndex.year``, ``Series.dt.year``), normalization, and conversion to and from ``Period``, ``DatetimeIndex.to_period`` and ``PeriodIndex.to_timestamp`` (:issue:`11263`)
+
+
 .. _whatsnew_0171.bug_fixes:
 
 Bug Fixes
diff --git a/pandas/src/datetime.pxd b/pandas/src/datetime.pxd
@@ -95,14 +95,14 @@ cdef extern from "datetime/np_datetime.h":
                                              int apply_tzinfo)
 
     npy_datetime pandas_datetimestruct_to_datetime(PANDAS_DATETIMEUNIT fr,
-                                                   pandas_datetimestruct *d)
+                                                   pandas_datetimestruct *d) nogil
     void pandas_datetime_to_datetimestruct(npy_datetime val,
                                            PANDAS_DATETIMEUNIT fr,
-                                           pandas_datetimestruct *result)
+                                           pandas_datetimestruct *result) nogil
     int days_per_month_table[2][12]
 
-    int dayofweek(int y, int m, int d)
-    int is_leapyear(int64_t year)
+    int dayofweek(int y, int m, int d) nogil
+    int is_leapyear(int64_t year) nogil
     PANDAS_DATETIMEUNIT get_datetime64_unit(object o)
 
 cdef extern from "datetime/np_datetime_strings.h":
diff --git a/pandas/src/period.pyx b/pandas/src/period.pyx
@@ -76,11 +76,11 @@ cdef extern from "period_helper.h":
 
     int64_t get_period_ordinal(int year, int month, int day,
                           int hour, int minute, int second, int microseconds, int picoseconds,
-                          int freq) except INT32_MIN
+                          int freq) nogil except INT32_MIN
 
     int64_t get_python_ordinal(int64_t period_ordinal, int freq) except INT32_MIN
 
-    int get_date_info(int64_t ordinal, int freq, date_info *dinfo) except INT32_MIN
+    int get_date_info(int64_t ordinal, int freq, date_info *dinfo) nogil except INT32_MIN
     double getAbsTime(int, int64_t, int64_t)
 
     int pyear(int64_t ordinal, int freq) except INT32_MIN
@@ -139,13 +139,14 @@ def dt64arr_to_periodarr(ndarray[int64_t] dtarr, int freq, tz=None):
     out = np.empty(l, dtype='i8')
 
     if tz is None:
-        for i in range(l):
-            if dtarr[i] == iNaT:
-                out[i] = iNaT
-                continue
-            pandas_datetime_to_datetimestruct(dtarr[i], PANDAS_FR_ns, &dts)
-            out[i] = get_period_ordinal(dts.year, dts.month, dts.day,
-                                        dts.hour, dts.min, dts.sec, dts.us, dts.ps, freq)
+        with nogil:
+            for i in range(l):
+                if dtarr[i] == NPY_NAT:
+                    out[i] = NPY_NAT
+                    continue
+                pandas_datetime_to_datetimestruct(dtarr[i], PANDAS_FR_ns, &dts)
+                out[i] = get_period_ordinal(dts.year, dts.month, dts.day,
+                                            dts.hour, dts.min, dts.sec, dts.us, dts.ps, freq)
     else:
         out = localize_dt64arr_to_period(dtarr, freq, tz)
     return out
@@ -163,11 +164,12 @@ def periodarr_to_dt64arr(ndarray[int64_t] periodarr, int freq):
 
     out = np.empty(l, dtype='i8')
 
-    for i in range(l):
-        if periodarr[i] == iNaT:
-            out[i] = iNaT
-            continue
-        out[i] = period_ordinal_to_dt64(periodarr[i], freq)
+    with nogil:
+        for i in range(l):
+            if periodarr[i] == NPY_NAT:
+                out[i] = NPY_NAT
+                continue
+            out[i] = period_ordinal_to_dt64(periodarr[i], freq)
 
     return out
 
@@ -245,13 +247,13 @@ def period_ordinal(int y, int m, int d, int h, int min, int s, int us, int ps, i
     return get_period_ordinal(y, m, d, h, min, s, us, ps, freq)
 
 
-cpdef int64_t period_ordinal_to_dt64(int64_t ordinal, int freq):
+cpdef int64_t period_ordinal_to_dt64(int64_t ordinal, int freq) nogil:
     cdef:
         pandas_datetimestruct dts
         date_info dinfo
         float subsecond_fraction
 
-    if ordinal == iNaT:
+    if ordinal == NPY_NAT:
         return NPY_NAT
 
     get_date_info(ordinal, freq, &dinfo)
diff --git a/pandas/src/period_helper.c b/pandas/src/period_helper.c
@@ -113,7 +113,7 @@ static int dInfoCalc_SetFromDateAndTime(struct date_info *dinfo,
         int yearoffset;
 
         /* Range check */
-        Py_AssertWithArg(year > -(INT_MAX / 366) && year < (INT_MAX / 366),
+         Py_AssertWithArg(year > -(INT_MAX / 366) && year < (INT_MAX / 366),
                  PyExc_ValueError,
                  "year out of range: %i",
                  year);
@@ -136,7 +136,7 @@ static int dInfoCalc_SetFromDateAndTime(struct date_info *dinfo,
                  day);
 
         yearoffset = dInfoCalc_YearOffset(year, calendar);
-        if (PyErr_Occurred()) goto onError;
+        if (yearoffset == INT_ERR_CODE) goto onError;
 
         absdate = day + month_offset[leap][month - 1] + yearoffset;
 
@@ -155,7 +155,7 @@ static int dInfoCalc_SetFromDateAndTime(struct date_info *dinfo,
 
     /* Calculate the absolute time */
     {
-        Py_AssertWithArg(hour >= 0 && hour <= 23,
+       Py_AssertWithArg(hour >= 0 && hour <= 23,
                 PyExc_ValueError,
                 "hour out of range (0-23): %i",
                 hour);
@@ -212,8 +212,7 @@ int dInfoCalc_SetFromAbsDate(register struct date_info *dinfo,
     while (1) {
         /* Calculate the year offset */
         yearoffset = dInfoCalc_YearOffset(year, calendar);
-        if (PyErr_Occurred())
-            goto onError;
+        if (yearoffset == INT_ERR_CODE) goto onError;
 
         /* Backward correction: absdate must be greater than the
            yearoffset */
@@ -310,7 +309,7 @@ static int calc_conversion_factors_matrix_size() {
         }
         matrix_size = max_value(matrix_size, period_value);
     }
-    return matrix_size + 1; 
+    return matrix_size + 1;
 }
 
 static void alloc_conversion_factors_matrix(int matrix_size) {
diff --git a/pandas/tslib.pyx b/pandas/tslib.pyx
