Update GCOVR annotations now that jenkins agent has avx512

CMakeLists.txt

@@ -276,9 +276,15 @@ if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR AND BUILD_TESTING)
 
   find_program(VALGRIND_EXE valgrind)
   if(VALGRIND_EXE AND NOT CMAKE_CROSSCOMPILING)
-    add_test(NAME conflict_set_blackbox_valgrind
-             COMMAND ${VALGRIND_EXE} --error-exitcode=99 --
-                     $<TARGET_FILE:driver> ${CORPUS_TESTS})
+    list(LENGTH CORPUS_TESTS len)
+    math(EXPR last "${len} - 1")
+    set(partition_size 100)
+    foreach(i RANGE 0 ${last} ${partition_size})
+      list(SUBLIST CORPUS_TESTS ${i} ${partition_size} partition)
+      add_test(NAME conflict_set_blackbox_valgrind_${i}
+               COMMAND ${VALGRIND_EXE} --error-exitcode=99 --
+                       $<TARGET_FILE:driver> ${partition})
+    endforeach()
   endif()
 
   # api smoke tests

ConflictSet.cpp

@@ -1544,8 +1544,6 @@ void maybeDecreaseCapacity(Node *&self, WriteContext *tls,
 }
 
 #if defined(HAS_AVX) && !defined(__SANITIZE_THREAD__)
-// This gets covered in local development
-// GCOVR_EXCL_START
 __attribute__((target("avx512f"))) void rezero16(InternalVersionT *vs,
                                                  InternalVersionT zero) {
   uint32_t z;
@@ -1555,7 +1553,6 @@ __attribute__((target("avx512f"))) void rezero16(InternalVersionT *vs,
       _mm512_sub_epi32(_mm512_loadu_epi32(vs), zvec), _mm512_setzero_epi32());
   _mm512_mask_storeu_epi32(vs, m, zvec);
 }
-// GCOVR_EXCL_STOP
 
 __attribute__((target("default")))
 #endif
@@ -1992,9 +1989,9 @@ downLeftSpine:
 #ifdef HAS_AVX
 uint32_t compare16_32bit(const InternalVersionT *vs, InternalVersionT rv) {
   uint32_t compared = 0;
-  __m128i w[4];
+  __m128i w[4]; // GCOVR_EXCL_LINE
   memcpy(w, vs, sizeof(w));
-  uint32_t r;
+  uint32_t r; // GCOVR_EXCL_LINE
   memcpy(&r, &rv, sizeof(r));
   const auto rvVec = _mm_set1_epi32(r);
   const auto zero = _mm_setzero_si128();
@@ -2006,8 +2003,6 @@ uint32_t compare16_32bit(const InternalVersionT *vs, InternalVersionT rv) {
   return compared;
 }
 
-// This gets covered in local development
-// GCOVR_EXCL_START
 __attribute__((target("avx512f"))) uint32_t
 compare16_32bit_avx512(const InternalVersionT *vs, InternalVersionT rv) {
   uint32_t r;
@@ -2017,7 +2012,6 @@ compare16_32bit_avx512(const InternalVersionT *vs, InternalVersionT rv) {
       _mm512_setzero_epi32());
 }
 #endif
-// GCOVR_EXCL_STOP
 
 // Returns true if v[i] <= readVersion for all i such that begin <= is[i] < end
 // Preconditions: begin <= end, end - begin < 256
@@ -2400,14 +2394,11 @@ bool checkMaxBetweenExclusiveImpl(Node *n, int begin, int end,
 }
 
 #if defined(HAS_AVX) && !defined(__SANITIZE_THREAD__)
-// This gets covered in local development
-// GCOVR_EXCL_START
 __attribute__((target("avx512f"))) bool
 checkMaxBetweenExclusive(Node *n, int begin, int end,
                          InternalVersionT readVersion, ReadContext *tls) {
   return checkMaxBetweenExclusiveImpl<true>(n, begin, end, readVersion, tls);
 }
-// GCOVR_EXCL_STOP
 __attribute__((target("default")))
 #endif
 bool checkMaxBetweenExclusive(Node *n, int begin, int end,

README.md

@@ -24,15 +24,15 @@ Hardware for all benchmarks is an AMD Ryzen 9 7900 with (2x32GB) 5600MT/s CL28-3
 
 |               ns/op |                op/s |    err% |          ins/op |          cyc/op |    IPC |         bra/op |   miss% |     total | benchmark
 |--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
-|               11.04 |       90,614,308.12 |    0.8% |          180.38 |           55.13 |  3.272 |          41.51 |    0.4% |      0.01 | `point reads`
-|               14.96 |       66,843,629.12 |    0.4% |          274.41 |           74.73 |  3.672 |          55.05 |    0.3% |      0.01 | `prefix reads`
-|               37.06 |       26,982,847.61 |    0.2% |          791.04 |          185.28 |  4.269 |         142.67 |    0.2% |      0.01 | `range reads`
-|               17.89 |       55,887,365.73 |    0.6% |          335.54 |           89.79 |  3.737 |          43.84 |    0.4% |      0.01 | `point writes`
-|               31.85 |       31,394,336.65 |    0.3% |          615.32 |          159.63 |  3.855 |          87.69 |    0.2% |      0.01 | `prefix writes`
-|               36.17 |       27,647,221.45 |    0.6% |          705.11 |          182.80 |  3.857 |         100.62 |    0.1% |      0.01 | `range writes`
-|               79.01 |       12,656,457.78 |    0.7% |        1,498.35 |          402.46 |  3.723 |         270.50 |    0.1% |      0.01 | `monotonic increasing point writes`
-|          303,667.50 |            3,293.08 |    1.1% |    3,931,273.00 |    1,612,702.50 |  2.438 |     806,223.33 |    0.0% |      0.01 | `worst case for radix tree`
-|               83.70 |       11,947,443.83 |    0.7% |        1,738.03 |          429.06 |  4.051 |         270.01 |    0.0% |      0.01 | `create and destroy`
+|               11.18 |       89,455,125.34 |    0.6% |          185.37 |           57.08 |  3.248 |          41.51 |    0.4% |      0.01 | `point reads`
+|               14.53 |       68,800,688.89 |    0.4% |          282.41 |           74.80 |  3.776 |          55.06 |    0.3% |      0.01 | `prefix reads`
+|               36.54 |       27,367,576.87 |    0.2% |          798.06 |          188.90 |  4.225 |         141.69 |    0.2% |      0.01 | `range reads`
+|               16.69 |       59,912,106.02 |    0.6% |          314.57 |           86.29 |  3.645 |          39.84 |    0.4% |      0.01 | `point writes`
+|               30.09 |       33,235,744.07 |    0.5% |          591.33 |          155.92 |  3.793 |          82.69 |    0.2% |      0.01 | `prefix writes`
+|               35.77 |       27,956,388.03 |    1.4% |          682.25 |          187.63 |  3.636 |          96.12 |    0.1% |      0.01 | `range writes`
+|               74.04 |       13,505,408.41 |    2.7% |        1,448.95 |          392.10 |  3.695 |         260.53 |    0.1% |      0.01 | `monotonic increasing point writes`
+|          330,984.50 |            3,021.29 |    1.9% |    3,994,153.50 |    1,667,309.00 |  2.396 |     806,019.50 |    0.0% |      0.01 | `worst case for radix tree`
+|               92.46 |       10,814,961.65 |    0.5% |        1,800.00 |          463.41 |  3.884 |         297.00 |    0.0% |      0.01 | `create and destroy`
 
 # "Real data" test
 
@@ -47,7 +47,7 @@ Check: 4.47891 seconds, 364.05 MB/s, Add: 4.55599 seconds, 123.058 MB/s, Gc rati
 ## radix tree
 
 ```
-Check: 0.958985 seconds, 1700.28 MB/s, Add: 1.35083 seconds, 415.044 MB/s, Gc ratio: 44.4768%, Peak idle memory: 2.33588e+06
+Check: 0.953012 seconds, 1710.94 MB/s, Add: 1.30025 seconds, 431.188 MB/s, Gc ratio: 43.9816%, Peak idle memory: 2.28375e+06
 ```
 
 ## hash table