|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-65.91% |
84157.781 |
28686.573 |
15604.905 |
-68.45% |
15604.905 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-61.81% |
8684.623 |
3316.931 |
1644.014 |
-63.60% |
1644.014 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.45% |
19155.181 |
7959.835 |
108.778 |
-4.53% |
108.778 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-56.10% |
13124.316 |
5761.432 |
2712.720 |
-59.01% |
2712.720 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-50.07% |
35423.616 |
17685.507 |
629.568 |
-49.92% |
629.568 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-49.72% |
35921.735 |
18062.768 |
542.130 |
-49.38% |
542.130 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.84% |
37115.122 |
18987.905 |
26.289 |
-48.77% |
26.289 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-46.87% |
8.823 |
4.688 |
0.149 |
-48.99% |
0.149 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.90% |
24474.762 |
13485.538 |
312.890 |
-41.63% |
312.890 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.28% |
18747.386 |
10445.952 |
0.634 |
-44.06% |
0.634 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-43.50% |
23883.897 |
13493.241 |
322.986 |
-42.09% |
322.986 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-41.95% |
2636.058 |
1530.267 |
52.597 |
-40.57% |
52.597 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.30% |
2568.130 |
1507.521 |
48.533 |
-39.93% |
48.533 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.29% |
17934.354 |
10529.767 |
5.537 |
-40.84% |
5.537 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.73% |
38184.999 |
22633.241 |
219.360 |
-40.68% |
219.360 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-39.01% |
161.888 |
98.735 |
2.825 |
-31.82% |
2.825 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.171 |
883.823 |
0.123 |
-36.69% |
0.123 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.954 |
3915.234 |
0.316 |
-36.67% |
0.316 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.63% |
279.498 |
177.110 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-36.50% |
22841.301 |
14504.092 |
188.076 |
-36.18% |
188.076 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.16% |
107116.786 |
68382.270 |
79.666 |
-36.18% |
79.666 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.11% |
26261.515 |
16778.763 |
10.859 |
-36.13% |
10.859 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.43% |
30186.933 |
19792.986 |
61.522 |
-34.27% |
61.522 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.26% |
29046.481 |
19096.540 |
35.273 |
-34.03% |
35.273 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.139 |
14104.049 |
0.625 |
-31.24% |
0.625 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-29.55% |
140.238 |
98.794 |
2.043 |
-30.67% |
2.043 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.71% |
25918.018 |
18476.526 |
79.709 |
-28.65% |
79.709 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-28.37% |
1265.422 |
906.441 |
9.993 |
0.19% |
9.993 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-28.08% |
13506.181 |
9713.425 |
22.110 |
-27.88% |
22.110 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.01% |
1292.869 |
930.758 |
4.447 |
-28.01% |
4.447 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-27.95% |
188.035 |
135.472 |
1.578 |
-18.92% |
1.578 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.31% |
653.604 |
475.114 |
1.842 |
-27.31% |
1.842 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.09% |
334.010 |
243.531 |
0.882 |
-27.07% |
0.882 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-26.99% |
11800.992 |
8616.080 |
572.767 |
-21.41% |
572.767 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.71% |
556.331 |
407.727 |
0.054 |
-26.87% |
0.054 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.56% |
173.788 |
127.629 |
0.429 |
-26.56% |
0.429 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.59% |
291.808 |
217.134 |
0.112 |
-25.59% |
0.112 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.98% |
27278.634 |
20464.717 |
95.579 |
-24.83% |
95.579 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16024.219 |
12180.963 |
0.490 |
-23.98% |
0.490 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.947 |
463.767 |
0.027 |
-23.21% |
0.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.20% |
158.880 |
122.016 |
0.065 |
-23.20% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.11% |
603.946 |
464.370 |
0.018 |
-23.11% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-22.66% |
732.867 |
566.791 |
42.413 |
-11.07% |
42.413 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.488 |
243.418 |
0.017 |
-22.36% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-22.28% |
7164.572 |
5568.459 |
2.367 |
-21.58% |
2.367 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-22.25% |
3.112 |
2.420 |
0.001 |
-22.12% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.18% |
615.173 |
478.746 |
0.055 |
-22.18% |
0.055 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.16% |
313.521 |
244.045 |
0.047 |
-22.16% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.161 |
479.996 |
0.033 |
-21.98% |
0.033 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-21.81% |
11138.899 |
8709.211 |
401.612 |
-22.35% |
401.612 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-21.76% |
29796.993 |
23313.882 |
81.958 |
-22.67% |
81.958 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.52% |
6589.320 |
5171.070 |
3.632 |
-21.44% |
3.632 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-21.52% |
1124.972 |
882.855 |
44.884 |
-20.14% |
44.884 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.38% |
389.835 |
306.489 |
0.397 |
-21.33% |
0.397 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.38% |
182326.373 |
143352.285 |
64.713 |
-21.39% |
64.713 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.37% |
13179.252 |
10363.269 |
27.365 |
-21.54% |
27.365 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.318 |
133.274 |
0.009 |
-20.82% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.52% |
45.203 |
35.926 |
0.069 |
-20.62% |
0.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.45% |
168.321 |
133.901 |
0.019 |
-20.45% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.42% |
324.749 |
258.439 |
0.020 |
-20.43% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.29% |
275.608 |
219.680 |
0.473 |
-20.25% |
0.473 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.783 |
259.687 |
0.018 |
-20.05% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-19.97% |
273.555 |
218.919 |
1.898 |
-20.32% |
1.898 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.71% |
640.879 |
514.571 |
0.091 |
-19.66% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.29% |
92.264 |
74.471 |
0.024 |
-19.30% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.08% |
3817.544 |
3089.140 |
0.095 |
-19.09% |
0.095 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.81% |
8.758 |
7.110 |
0.001 |
-18.81% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.80% |
8.757 |
7.110 |
0.001 |
-18.80% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.70% |
27135.618 |
22061.129 |
87.511 |
-18.45% |
87.511 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.55% |
13801.497 |
11240.880 |
9.580 |
-18.59% |
9.580 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.46% |
13905.025 |
11337.561 |
8.608 |
-18.44% |
8.608 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-18.43% |
1119.894 |
913.533 |
5.837 |
0.01% |
5.837 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.30% |
95.737 |
78.217 |
0.002 |
-18.30% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.11% |
1.104 |
0.904 |
0.000 |
-18.10% |
0.000 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.07% |
0.124 |
0.101 |
0.001 |
-18.06% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.97% |
746725.425 |
612529.636 |
262.518 |
-17.87% |
262.518 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.743 |
78.844 |
0.001 |
-17.65% |
0.001 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.44% |
0.335 |
0.277 |
0.000 |
-17.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.44% |
17.519 |
14.463 |
0.016 |
-17.45% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.42% |
179.578 |
148.299 |
0.003 |
-17.42% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.41% |
739929.228 |
611140.330 |
1620.206 |
-17.43% |
1620.206 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.34% |
13201.020 |
10912.475 |
3.882 |
-16.48% |
3.882 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.26% |
570.715 |
472.195 |
0.046 |
-17.24% |
0.046 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-17.23% |
1124.819 |
930.958 |
20.370 |
-13.67% |
20.370 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.10% |
297.778 |
246.845 |
0.030 |
-17.09% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-16.85% |
148.851 |
123.767 |
4.027 |
-17.44% |
4.027 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.85% |
93.204 |
77.502 |
0.201 |
-16.78% |
0.201 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-16.80% |
162.253 |
134.994 |
0.875 |
-18.84% |
0.875 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.73% |
179.587 |
149.544 |
0.008 |
-16.73% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-16.59% |
147.968 |
123.422 |
0.717 |
-16.96% |
0.717 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.54% |
160.742 |
134.153 |
0.037 |
-16.88% |
0.037 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.18% |
260.281 |
218.156 |
0.191 |
-16.15% |
0.191 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.15% |
260.287 |
218.257 |
0.153 |
-16.10% |
0.153 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.14% |
0.443 |
0.372 |
0.000 |
-15.83% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.11% |
1266.610 |
1062.524 |
1.147 |
-16.02% |
1.147 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.11% |
0.443 |
0.372 |
0.000 |
-15.87% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.02% |
1262.941 |
1060.657 |
1.520 |
-16.33% |
1.520 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7463.632 |
6293.157 |
0.231 |
-15.67% |
0.231 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.48% |
10641.738 |
8994.563 |
32.210 |
-15.11% |
32.210 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
-15.42% |
58.816 |
49.746 |
0.001 |
-15.35% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, First>
|
-15.39% |
16669.875 |
14103.795 |
0.622 |
-15.40% |
0.622 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.648 |
0.001 |
-15.39% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.38% |
16666.454 |
14103.427 |
1.077 |
-15.38% |
1.077 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.36% |
16667.937 |
14108.089 |
1.219 |
-15.35% |
1.219 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-15.22% |
20.683 |
17.536 |
0.327 |
-0.41% |
0.327 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.08% |
113.157 |
96.095 |
0.957 |
-15.03% |
0.957 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.79% |
605.595 |
516.040 |
0.062 |
-14.81% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.74% |
59.443 |
50.682 |
0.005 |
-14.75% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.277 |
942.485 |
0.098 |
-14.58% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.54% |
1095.619 |
936.281 |
0.041 |
-14.52% |
0.041 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-14.45% |
17.751 |
15.186 |
0.450 |
-11.57% |
0.450 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.34% |
562.484 |
481.828 |
0.036 |
-14.31% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-14.23% |
9955.172 |
8538.268 |
94.294 |
-13.80% |
94.294 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.19% |
554.194 |
475.567 |
0.169 |
-14.27% |
0.169 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-14.18% |
11013.237 |
9451.799 |
71.361 |
-15.07% |
71.361 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-14.08% |
85.530 |
73.485 |
1.346 |
-13.88% |
1.346 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.04% |
3756.902 |
3229.415 |
5.219 |
-14.03% |
5.219 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.96% |
22055.605 |
18977.161 |
45.651 |
-13.93% |
45.651 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.90% |
789585.548 |
679848.144 |
1995.745 |
-13.73% |
1995.745 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.86% |
51.936 |
44.737 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.86% |
51.934 |
44.737 |
0.002 |
-13.86% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.936 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.86% |
51.935 |
44.738 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.85% |
51.936 |
44.741 |
0.001 |
-13.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.933 |
44.740 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.445 |
51.312 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.66% |
789552.919 |
681694.117 |
628.208 |
-13.88% |
628.208 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.65% |
284.040 |
245.281 |
0.019 |
-13.66% |
0.019 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.63% |
14104.298 |
12181.867 |
0.591 |
-13.63% |
0.591 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.713 |
12181.564 |
0.603 |
-13.62% |
0.603 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.63% |
14104.388 |
12182.213 |
0.992 |
-13.62% |
0.992 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.55% |
23.153 |
20.016 |
0.003 |
-13.55% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.55% |
290.978 |
251.555 |
0.002 |
-13.85% |
0.002 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.47% |
223.021 |
192.991 |
0.804 |
-13.68% |
0.804 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.40% |
374.347 |
324.195 |
0.018 |
-13.42% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.23% |
12794.310 |
11101.554 |
6.918 |
-13.52% |
6.918 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC8
|
-13.16% |
23.778 |
20.649 |
0.001 |
-13.16% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/128
|
-13.10% |
224.592 |
195.168 |
7.016 |
-14.39% |
7.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.347 |
70.707 |
0.002 |
-13.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.99% |
156.780 |
136.415 |
0.042 |
-13.09% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4542.149 |
3953.884 |
0.142 |
-12.95% |
0.142 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.85% |
106.991 |
93.238 |
0.003 |
-12.86% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.76% |
9136.951 |
7971.268 |
100.253 |
-11.91% |
100.253 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.75% |
2.509 |
2.190 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.67% |
332.876 |
290.691 |
0.014 |
-12.66% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.62% |
148.925 |
130.130 |
0.017 |
-12.55% |
0.017 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-12.54% |
85.959 |
75.178 |
0.549 |
-12.70% |
0.549 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.41% |
4742.886 |
4154.388 |
0.374 |
-12.41% |
0.374 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-12.02% |
7415.982 |
6524.249 |
110.140 |
-8.25% |
110.140 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.87% |
89.461 |
78.841 |
0.005 |
-11.81% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-11.82% |
51.938 |
45.800 |
0.091 |
-11.82% |
0.091 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.772 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.69% |
106.999 |
94.488 |
0.005 |
-11.70% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.45% |
33.163 |
29.365 |
0.021 |
-11.45% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.935 |
45.989 |
0.003 |
-11.46% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-11.16% |
10467.908 |
9300.058 |
171.095 |
-13.39% |
171.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC4
|
-11.11% |
22.527 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
-11.11% |
22.526 |
20.024 |
0.000 |
-11.11% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.023 |
0.001 |
-11.11% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.08% |
123.894 |
110.172 |
0.374 |
19.10% |
0.374 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-11.04% |
45.166 |
40.179 |
1.693 |
-8.63% |
1.693 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint16_t_
|
-11.02% |
19304.443 |
17177.786 |
756.666 |
-9.51% |
756.666 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.78% |
81.353 |
72.584 |
0.007 |
-10.74% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.295 |
36.919 |
0.001 |
-10.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
-10.53% |
23.778 |
21.275 |
0.001 |
-10.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC64
|
-10.46% |
53.810 |
48.180 |
0.002 |
-10.47% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint64_t_
|
-10.25% |
16837.944 |
15112.521 |
550.497 |
-12.12% |
550.497 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.475 |
103.716 |
0.007 |
-10.17% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.13% |
5851.855 |
5259.198 |
7.988 |
-10.10% |
7.988 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.10% |
55.690 |
50.063 |
0.001 |
-10.06% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.08% |
1913.332 |
1720.398 |
0.915 |
-10.08% |
0.915 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.99% |
102.189 |
91.983 |
0.004 |
-9.71% |
0.004 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
472.992 |
425.755 |
0.029 |
-9.99% |
0.029 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-9.96% |
0.519 |
0.467 |
0.000 |
-9.98% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-9.81% |
12.320 |
11.112 |
0.071 |
-7.29% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.002 |
-9.77% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.73% |
31389.140 |
28333.785 |
29.130 |
-9.91% |
29.130 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.61% |
32.540 |
29.411 |
0.000 |
-9.61% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.61% |
7903.080 |
7143.952 |
1.654 |
-9.77% |
1.654 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.778 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-9.49% |
168774.291 |
152749.975 |
5224.053 |
-8.55% |
5224.053 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.49% |
333218.417 |
301605.323 |
22.721 |
-9.50% |
22.721 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-9.43% |
12.885 |
11.670 |
0.229 |
-4.27% |
0.229 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.42% |
53.185 |
48.173 |
0.008 |
-9.44% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.39% |
196.478 |
178.019 |
0.006 |
-9.39% |
0.006 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.26% |
287.242 |
260.649 |
0.084 |
-9.18% |
0.084 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.19% |
287.120 |
260.744 |
0.079 |
-9.19% |
0.079 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC8
|
-9.12% |
26.853 |
24.403 |
0.001 |
-9.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC4
|
-9.09% |
41.298 |
37.545 |
0.002 |
-9.09% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.88% |
28.157 |
25.655 |
0.001 |
-8.89% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-8.83% |
0.359 |
0.328 |
0.000 |
-8.68% |
0.000 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.75% |
16.799 |
15.330 |
0.001 |
-8.25% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.70% |
3.510 |
3.204 |
0.000 |
-8.70% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC16
|
-8.61% |
36.291 |
33.165 |
0.001 |
-8.62% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
-8.51% |
29.409 |
26.906 |
0.000 |
-8.52% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.51% |
6810.941 |
6231.664 |
7.570 |
-8.57% |
7.570 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-8.50% |
352.608 |
322.619 |
3.980 |
-9.05% |
3.980 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.43% |
20335.796 |
18620.528 |
73.438 |
-7.56% |
73.438 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-8.28% |
44.614 |
40.920 |
1.352 |
-7.90% |
1.352 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.24% |
12822.735 |
11765.994 |
19.139 |
-7.93% |
19.139 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.171 |
35.041 |
0.001 |
-8.20% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-8.19% |
88.642 |
81.381 |
0.642 |
-8.21% |
0.642 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.05% |
93.236 |
85.728 |
0.002 |
-8.06% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.90% |
47.561 |
43.801 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
29.409 |
0.002 |
-7.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.84% |
31.909 |
29.408 |
0.002 |
-7.84% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.82% |
40.051 |
36.919 |
0.002 |
-7.82% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.537 |
30.035 |
0.000 |
-7.70% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-7.65% |
88.881 |
82.078 |
0.418 |
-7.39% |
0.418 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.65% |
5.200 |
4.802 |
0.002 |
-7.66% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.61% |
1794.427 |
1657.874 |
0.564 |
-7.94% |
0.564 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.59% |
25041.477 |
23141.695 |
98.943 |
-7.38% |
98.943 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.52% |
3.507 |
3.243 |
0.000 |
-7.49% |
0.000 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.45% |
15.895 |
14.711 |
0.009 |
-7.30% |
0.009 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.41% |
16.895 |
15.643 |
0.000 |
-7.41% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.39% |
1793.121 |
1660.587 |
1.999 |
-7.33% |
1.999 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.23% |
1.498 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.339 |
160.816 |
0.001 |
-7.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-7.21% |
82.593 |
76.638 |
0.311 |
13.39% |
0.311 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.20% |
138.914 |
128.909 |
0.005 |
-7.20% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.15% |
2403.930 |
2231.965 |
21.557 |
-8.02% |
21.557 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.709 |
65.702 |
0.005 |
-7.09% |
0.005 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.02% |
1.782 |
1.657 |
0.000 |
-7.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.95% |
45.055 |
41.925 |
0.095 |
-6.94% |
0.095 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.89% |
54.434 |
50.684 |
0.002 |
-6.90% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.70% |
74.455 |
69.464 |
0.004 |
-6.71% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.56% |
114.514 |
106.999 |
0.007 |
-6.56% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-6.53% |
17.631 |
16.480 |
0.201 |
-1.23% |
0.201 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.52% |
28.783 |
26.905 |
0.003 |
-6.52% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.905 |
0.001 |
-6.52% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.49% |
1.312 |
1.226 |
0.001 |
-6.55% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.48% |
15.976 |
14.940 |
0.068 |
-6.44% |
0.068 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.47% |
74.260 |
69.456 |
0.002 |
-6.42% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.46% |
180964.907 |
169279.921 |
532.968 |
-6.54% |
532.968 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.43% |
68.831 |
64.405 |
0.024 |
-6.39% |
0.024 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.421 |
36.917 |
0.002 |
-6.35% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.35% |
68.793 |
64.428 |
0.011 |
-5.66% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.33% |
194.598 |
182.277 |
0.256 |
-6.34% |
0.256 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.33% |
0.366 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
-6.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.921 |
130.149 |
0.008 |
-6.31% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.29% |
11.862 |
11.116 |
0.071 |
-6.85% |
0.071 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.26% |
45.343 |
42.505 |
0.061 |
-6.25% |
0.061 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-6.24% |
204.954 |
192.158 |
1.401 |
-4.25% |
1.401 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.17% |
20.006 |
18.771 |
0.003 |
-6.16% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.15% |
40.672 |
38.170 |
0.001 |
-6.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-6.06% |
88.672 |
83.297 |
0.831 |
-6.39% |
0.831 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.95% |
0.663 |
0.623 |
0.000 |
-6.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.119 |
89.482 |
0.003 |
-5.92% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.88% |
138.289 |
130.151 |
0.006 |
-5.88% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.66% |
33.162 |
31.286 |
0.001 |
-5.66% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.426 |
41.924 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.422 |
41.922 |
0.002 |
-5.64% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.55% |
45.052 |
42.550 |
0.001 |
-5.58% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.049 |
42.549 |
0.001 |
-5.56% |
0.001 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.52% |
290.706 |
274.665 |
0.526 |
-5.96% |
0.526 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.50% |
107.655 |
101.736 |
0.032 |
-5.48% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.48% |
21468.256 |
20291.798 |
4.610 |
-5.40% |
4.610 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.42% |
61.321 |
57.999 |
0.083 |
-5.42% |
0.083 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.39% |
3630.131 |
3434.398 |
9.888 |
-5.48% |
9.888 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.485 |
658.958 |
0.019 |
-5.39% |
0.019 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.33% |
389.327 |
368.579 |
0.327 |
-5.39% |
0.327 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.32% |
13.532 |
12.812 |
0.062 |
-5.37% |
0.062 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.30% |
70.708 |
66.960 |
0.003 |
-5.32% |
0.003 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.27% |
0.241 |
0.229 |
0.000 |
-5.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC1
|
-5.26% |
11.889 |
11.263 |
0.000 |
-5.26% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/999
|
-5.23% |
1365.065 |
1293.698 |
0.012 |
-5.23% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-5.15% |
503.786 |
477.845 |
4.787 |
-4.15% |
4.787 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.14% |
24.405 |
23.151 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.13% |
24.402 |
23.150 |
0.001 |
-5.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.13% |
24.403 |
23.152 |
0.000 |
-5.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.12% |
24.403 |
23.152 |
0.001 |
-5.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.12% |
128.267 |
121.705 |
0.002 |
-5.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.09% |
241.300 |
229.026 |
0.008 |
-5.06% |
0.008 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.08% |
13.482 |
12.797 |
0.048 |
-5.19% |
0.048 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-4.89% |
1.759 |
1.673 |
0.010 |
-8.31% |
0.010 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-4.85% |
31.985 |
30.434 |
0.125 |
-5.55% |
0.125 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.176 |
346.648 |
0.023 |
-4.81% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-4.76% |
907.399 |
864.197 |
8.590 |
-5.76% |
8.590 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.69% |
0.641 |
0.611 |
0.000 |
-4.68% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-4.69% |
437.008 |
416.516 |
7.476 |
-2.85% |
7.476 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.115 |
90.730 |
0.007 |
-4.61% |
0.007 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<16, int>
|
-4.60% |
54.437 |
51.934 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<16, int>
|
-4.60% |
54.435 |
51.932 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.53% |
13.766 |
13.142 |
0.007 |
-4.53% |
0.007 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.49% |
43.548 |
41.590 |
0.085 |
-3.94% |
0.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.47% |
70.080 |
66.951 |
0.004 |
-4.47% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.39% |
23528.576 |
22495.173 |
14.972 |
-4.21% |
14.972 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.392 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.391 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.35% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.391 |
13.766 |
0.002 |
-4.34% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.34% |
14.390 |
13.765 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.34% |
14.390 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.34% |
14.390 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.34% |
14.393 |
13.769 |
0.001 |
-4.34% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.33% |
14.390 |
13.767 |
0.003 |
-4.35% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.27% |
650043.949 |
622260.239 |
157.419 |
-3.55% |
157.419 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.27% |
14.210 |
13.603 |
0.012 |
-4.48% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-4.27% |
3121.916 |
2988.627 |
33.801 |
-4.48% |
33.801 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.25% |
1811.098 |
1734.103 |
0.147 |
-4.26% |
0.147 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-4.25% |
1062.880 |
1017.718 |
6.117 |
-4.64% |
6.117 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-4.25% |
2968.548 |
2842.517 |
32.335 |
-4.43% |
32.335 |
|
SingleSource/Benchmarks/Misc/flops-5
Profile
|
-4.16% |
2.021 |
1.937 |
0.000 |
-4.15% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/171
|
-4.16% |
14.196 |
13.605 |
0.013 |
-4.51% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.253 |
3445.767 |
0.120 |
-4.14% |
0.120 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-4.10% |
500.096 |
479.611 |
3.841 |
-4.50% |
3.841 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.577 |
897.365 |
0.043 |
-4.08% |
0.043 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.947 |
59.444 |
0.001 |
-4.04% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.02% |
31.295 |
30.036 |
0.084 |
-4.01% |
0.084 |
|
SingleSource/Benchmarks/CoyoteBench/lpbench
Profile
|
-4.02% |
13.357 |
12.820 |
0.074 |
-0.77% |
0.074 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.98% |
96170.007 |
92342.749 |
13.251 |
-3.97% |
13.251 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.478 |
90.729 |
0.006 |
-3.98% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.96% |
221.510 |
212.742 |
0.006 |
-3.96% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.96% |
63.196 |
60.697 |
0.001 |
-3.96% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.93% |
15.957 |
15.329 |
0.001 |
-3.64% |
0.001 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.86% |
6.126 |
5.889 |
0.001 |
-3.88% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.85% |
16.269 |
15.643 |
0.000 |
-3.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-3.79% |
19367.741 |
18632.938 |
132.099 |
-3.42% |
132.099 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-3.76% |
15.021 |
14.455 |
0.036 |
-4.23% |
0.036 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-3.74% |
21.205 |
20.412 |
0.000 |
-1.85% |
0.000 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-3.68% |
2.000 |
1.926 |
0.006 |
-5.38% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.66% |
514.390 |
495.571 |
0.026 |
-3.66% |
0.026 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.63% |
3344.151 |
3222.774 |
0.187 |
-3.69% |
0.187 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.456 |
66.954 |
0.003 |
-3.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.453 |
66.954 |
0.002 |
-3.61% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.58% |
70.090 |
67.581 |
0.002 |
-3.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.081 |
67.580 |
0.001 |
-3.57% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.55% |
9836.810 |
9487.125 |
19.502 |
-3.97% |
19.502 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.52% |
477.136 |
460.356 |
0.094 |
-3.67% |
0.094 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-3.51% |
0.587 |
0.566 |
0.002 |
-1.28% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.51% |
2873.097 |
2772.182 |
0.704 |
-3.68% |
0.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-3.43% |
1640.658 |
1584.384 |
18.053 |
-3.61% |
18.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.42% |
43.181 |
41.706 |
0.015 |
-3.40% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-3.36% |
1730.820 |
1672.608 |
16.685 |
-3.71% |
16.685 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.32% |
60.194 |
58.194 |
0.001 |
-3.45% |
0.001 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
-3.32% |
3.667 |
3.545 |
0.023 |
0.01% |
0.023 |
|
SingleSource/Benchmarks/Polybench/stencils/fdtd-2d/fdtd-2d
Profile
|
-3.19% |
20.043 |
19.403 |
0.142 |
-0.52% |
0.142 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.17% |
3590.013 |
3476.163 |
16.101 |
-3.01% |
16.101 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.997 |
498.710 |
0.021 |
-3.17% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.14% |
4512.901 |
4371.297 |
3.076 |
-3.23% |
3.076 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.13% |
11.316 |
10.962 |
0.016 |
-3.10% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.12% |
20.022 |
19.398 |
0.000 |
-3.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-3.11% |
59.868 |
58.004 |
0.457 |
7.78% |
0.457 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-3.10% |
1488.996 |
1442.856 |
16.278 |
-3.20% |
16.278 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020119.583 |
4865342.278 |
82.295 |
-3.08% |
82.295 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-3.04% |
1788.144 |
1733.771 |
6.095 |
0.01% |
6.095 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-3.01% |
37631.714 |
36499.822 |
35.315 |
-2.86% |
35.315 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/5001
|
-2.88% |
20.692 |
20.097 |
0.033 |
-2.55% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-2.87% |
31.232 |
30.335 |
0.081 |
-2.74% |
0.081 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.86% |
4366.616 |
4241.767 |
5.856 |
-1.91% |
5.856 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.787 |
984.968 |
0.042 |
-2.85% |
0.042 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-2.82% |
277.570 |
269.743 |
2.617 |
-2.34% |
2.617 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.82% |
111.387 |
108.250 |
0.005 |
-2.81% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-2.81% |
20.746 |
20.162 |
0.025 |
-3.06% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.78% |
22.526 |
21.900 |
0.002 |
-2.78% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.524 |
21.900 |
0.001 |
-2.78% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.77% |
31.282 |
30.417 |
0.025 |
-2.78% |
0.025 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.68% |
0.553 |
0.538 |
0.000 |
-2.68% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-2.67% |
93.290 |
90.801 |
0.068 |
-3.25% |
0.068 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-ary3
Profile
|
-2.63% |
3.648 |
3.552 |
0.030 |
-0.03% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.61% |
120.141 |
117.009 |
0.011 |
-2.61% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-2.58% |
7080.229 |
6897.769 |
9.925 |
-2.20% |
9.925 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.57% |
0.651 |
0.635 |
0.001 |
-2.46% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.808 |
47.558 |
0.030 |
2.47% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.54% |
7077.932 |
6898.188 |
1.044 |
-2.53% |
1.044 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.50% |
9.699 |
9.457 |
0.015 |
-2.52% |
0.015 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.46% |
1.253 |
1.222 |
0.009 |
-2.85% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166195.324 |
162117.962 |
6.277 |
-2.46% |
6.277 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-2.45% |
27.144 |
26.480 |
0.023 |
0.24% |
0.023 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-2.44% |
2754.320 |
2687.152 |
13.518 |
-2.08% |
13.518 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.42% |
19742.555 |
19264.348 |
30.179 |
-2.91% |
30.179 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.39% |
8297.219 |
8099.290 |
21.102 |
-2.37% |
21.102 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-2.38% |
6651.880 |
6493.365 |
19.841 |
-2.28% |
19.841 |
|
SingleSource/Benchmarks/Shootout/Shootout-heapsort
Profile
|
-2.36% |
22.690 |
22.153 |
0.097 |
0.03% |
0.097 |
|
MultiSource/Benchmarks/Olden/voronoi/voronoi
Profile
|
-2.36% |
1.408 |
1.375 |
0.011 |
-0.76% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.33% |
106.998 |
104.501 |
0.002 |
-2.34% |
0.002 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.33% |
5.762 |
5.628 |
0.000 |
-2.32% |
0.000 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.32% |
9.852 |
9.623 |
0.003 |
-2.79% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.32% |
108.253 |
105.743 |
0.005 |
-2.31% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.27% |
1446782.685 |
1413920.966 |
1113.818 |
-2.28% |
1113.818 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-2.26% |
86.422 |
84.469 |
0.003 |
11.81% |
0.003 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.23% |
32.323 |
31.601 |
0.023 |
-2.89% |
0.023 |
|
SingleSource/Benchmarks/BenchmarkGame/puzzle
Profile
|
-2.23% |
0.872 |
0.853 |
0.001 |
-1.82% |
0.001 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MultiSource/Benchmarks/TSVC/InductionVariable-dbl/InductionVariable-dbl
Profile
|
-2.17% |
17.804 |
17.418 |
0.104 |
-1.78% |
0.104 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.11% |
12.104 |
11.848 |
0.002 |
-2.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.511 |
117.010 |
0.005 |
-2.10% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.512 |
117.012 |
0.002 |
-2.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.09% |
120.144 |
117.634 |
0.006 |
-2.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.131 |
117.636 |
0.001 |
-2.08% |
0.001 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.00% |
93.488 |
91.614 |
0.383 |
-2.60% |
0.383 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.00% |
26378.093 |
25850.951 |
7.464 |
-1.64% |
7.464 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-1.98% |
1532.092 |
1501.727 |
4.181 |
-0.19% |
4.181 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-1.96% |
2960.811 |
2902.807 |
12.336 |
-0.91% |
12.336 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.95% |
0.872 |
0.855 |
0.001 |
-1.78% |
0.001 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-1.93% |
260.421 |
255.389 |
0.258 |
-1.82% |
0.258 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.88% |
0.872 |
0.856 |
0.002 |
-1.74% |
0.002 |
|
MultiSource/Benchmarks/Bullet/bullet
Profile
|
-1.88% |
30.466 |
29.893 |
0.148 |
-1.77% |
0.148 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.86% |
11255.914 |
11046.138 |
57.170 |
-2.61% |
57.170 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.836 |
267.826 |
0.009 |
-1.84% |
0.009 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.80% |
10.399 |
10.212 |
0.026 |
-1.85% |
0.026 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-1.72% |
434.210 |
426.737 |
1.894 |
-2.90% |
1.894 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.298 |
145.792 |
0.001 |
-1.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.64% |
211.495 |
208.034 |
0.082 |
-1.65% |
0.082 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.62% |
5.141 |
5.058 |
0.001 |
-1.59% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.61% |
6.918 |
6.807 |
0.011 |
-1.71% |
0.011 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.59% |
15.575 |
15.328 |
0.001 |
-1.57% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.58% |
5.426 |
5.340 |
0.031 |
-1.96% |
0.031 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.58% |
6.919 |
6.810 |
0.019 |
-1.65% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.56% |
504562.587 |
496696.297 |
26.159 |
-1.59% |
26.159 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.55% |
2.535 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, GreaterThanZero, Mid>
|
-1.51% |
2729.784 |
2688.445 |
3.526 |
-2.09% |
3.526 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.45% |
57.854 |
57.017 |
0.031 |
-0.06% |
0.031 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.42% |
1028347.299 |
1013791.721 |
165.718 |
-1.40% |
165.718 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.39% |
220.280 |
217.214 |
0.026 |
-1.39% |
0.026 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.39% |
33.267 |
32.804 |
0.037 |
-0.77% |
0.037 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.38% |
6609.603 |
6518.329 |
19.477 |
-1.44% |
19.477 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.017 |
225.887 |
0.011 |
-1.36% |
0.011 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.29% |
4570.511 |
4511.652 |
9.069 |
-1.30% |
9.069 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.26% |
197.091 |
194.598 |
0.005 |
-1.27% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.26% |
198.361 |
195.860 |
0.002 |
-1.26% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-1.25% |
49.429 |
48.809 |
0.057 |
-2.48% |
0.057 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.20% |
19472.606 |
19239.797 |
3.593 |
-1.00% |
3.593 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.18% |
12065.301 |
11922.932 |
24.255 |
-1.65% |
24.255 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, LessThanZero, Last>
|
-1.18% |
13140.535 |
12985.695 |
2.707 |
-1.19% |
2.707 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.18% |
2243.067 |
2216.640 |
0.887 |
-1.12% |
0.887 |
|
MultiSource/Applications/obsequi/Obsequi
Profile
|
-1.15% |
7.657 |
7.569 |
0.020 |
-1.20% |
0.020 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.15% |
228.337 |
225.720 |
0.708 |
-1.60% |
0.708 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.14% |
8660.401 |
8561.353 |
31.182 |
-1.11% |
31.182 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.14% |
37597.206 |
37167.372 |
7.063 |
-1.15% |
7.063 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.14% |
2.779 |
2.747 |
0.000 |
-1.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.13% |
2242.072 |
2216.732 |
1.162 |
-1.16% |
1.162 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.044 |
29.706 |
0.004 |
-1.07% |
0.004 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-1.12% |
891.068 |
881.090 |
1.803 |
-0.46% |
1.803 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.11% |
4555.912 |
4505.147 |
6.325 |
-1.10% |
6.325 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, None>
|
-1.09% |
7981.553 |
7894.553 |
32.191 |
-1.26% |
32.191 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.06% |
56353.872 |
55756.229 |
15.508 |
-0.52% |
15.508 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.05% |
4179.209 |
4135.330 |
2.804 |
-0.85% |
2.804 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.03% |
745474.518 |
737811.377 |
444.750 |
-0.96% |
444.750 |