|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/44217
|
-58.47% |
19155.181 |
7954.607 |
112.874 |
-4.59% |
112.874 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint32_t_
|
-52.07% |
35423.616 |
16979.643 |
556.449 |
-51.92% |
556.449 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint16_t_
|
-50.60% |
35921.735 |
17745.837 |
195.821 |
-50.26% |
195.821 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG/miniGMG
Profile
|
-49.04% |
8.823 |
4.496 |
0.067 |
-51.08% |
0.067 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint64_t_To_uint8_t_
|
-48.84% |
37115.122 |
18989.724 |
17.680 |
-48.76% |
17.680 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/44217
|
-47.19% |
84157.781 |
44444.028 |
2737.331 |
-51.12% |
2737.331 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/44217
|
-44.85% |
24474.762 |
13497.079 |
276.201 |
-41.58% |
276.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint64_t_
|
-44.28% |
18747.386 |
10446.081 |
1.591 |
-44.06% |
1.591 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/44217
|
-43.57% |
23883.897 |
13478.124 |
319.894 |
-42.15% |
319.894 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/5001
|
-42.42% |
2636.058 |
1517.784 |
30.758 |
-41.05% |
30.758 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/5001
|
-42.23% |
8684.623 |
5017.006 |
350.260 |
-44.95% |
350.260 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint64_t_
|
-41.40% |
17934.354 |
10509.004 |
24.430 |
-40.96% |
24.430 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/5001
|
-41.20% |
2568.130 |
1510.013 |
45.419 |
-39.83% |
45.419 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint32_t_
|
-40.77% |
38184.999 |
22616.582 |
21.045 |
-40.73% |
21.045 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
-38.12% |
161.888 |
100.183 |
1.582 |
-30.82% |
1.582 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/32
|
-36.70% |
1396.171 |
883.811 |
0.049 |
-36.70% |
0.049 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
-36.67% |
6181.954 |
3915.115 |
7.763 |
-36.67% |
7.763 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
-36.64% |
279.498 |
177.104 |
0.010 |
-36.63% |
0.010 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/256
|
-36.18% |
107116.786 |
68363.012 |
36.589 |
-36.20% |
36.589 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/128
|
-36.09% |
26261.515 |
16783.317 |
6.527 |
-36.12% |
6.527 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint64_t_
|
-35.61% |
22841.301 |
14706.615 |
209.764 |
-35.28% |
209.764 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint8_t_
|
-34.42% |
30186.933 |
19796.768 |
14.321 |
-34.25% |
14.321 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint64_t_To_uint16_t_
|
-34.22% |
29046.481 |
19107.934 |
30.700 |
-33.99% |
30.700 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/44217
|
-32.66% |
13464.268 |
9067.009 |
955.040 |
-32.66% |
955.040 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, None>
|
-31.24% |
20511.139 |
14103.796 |
0.411 |
-31.24% |
0.411 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_DIFF_RAW/44217
|
-29.45% |
140.238 |
98.935 |
2.117 |
-30.57% |
2.117 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint16_t_
|
-28.94% |
25918.018 |
18417.254 |
55.498 |
-28.88% |
55.498 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/44217
|
-28.38% |
188.035 |
134.668 |
0.839 |
-19.40% |
0.839 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
-28.03% |
1292.869 |
930.448 |
2.682 |
-28.03% |
2.682 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint8_t_
|
-27.97% |
13506.181 |
9728.527 |
19.479 |
-27.77% |
19.479 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/5001
|
-27.69% |
1265.422 |
914.987 |
1.439 |
1.13% |
1.439 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
-27.32% |
653.604 |
475.038 |
1.270 |
-27.32% |
1.270 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
-27.13% |
334.010 |
243.404 |
0.752 |
-27.11% |
0.752 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/44217
|
-26.70% |
11800.992 |
8649.908 |
5.219 |
-21.10% |
5.219 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC128
|
-26.70% |
556.331 |
407.790 |
0.064 |
-26.86% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
-26.49% |
173.788 |
127.757 |
0.466 |
-26.49% |
0.466 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC64
|
-25.58% |
291.808 |
217.162 |
0.023 |
-25.59% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint8_t_
|
-24.77% |
27278.634 |
20522.868 |
61.623 |
-24.61% |
61.623 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, None>
|
-23.98% |
16024.219 |
12181.128 |
0.380 |
-23.98% |
0.380 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/44217
|
-23.78% |
13124.316 |
10002.934 |
31.469 |
-28.83% |
31.469 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC128
|
-23.21% |
603.947 |
463.774 |
0.063 |
-23.21% |
0.063 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC32
|
-23.20% |
158.880 |
122.025 |
0.081 |
-23.19% |
0.081 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC128
|
-23.10% |
603.946 |
464.421 |
0.018 |
-23.10% |
0.018 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/44217
|
-22.62% |
11138.899 |
8619.795 |
937.689 |
-23.15% |
937.689 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC64
|
-22.35% |
313.488 |
243.431 |
0.006 |
-22.35% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
-22.27% |
7164.572 |
5569.103 |
0.643 |
-21.57% |
0.643 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
-22.27% |
3.112 |
2.419 |
0.003 |
-22.14% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC127
|
-22.17% |
615.173 |
478.796 |
0.033 |
-22.17% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC64
|
-22.15% |
313.521 |
244.070 |
0.017 |
-22.15% |
0.017 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
-22.08% |
29796.993 |
23218.915 |
92.280 |
-22.99% |
92.280 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC127
|
-21.97% |
615.161 |
480.031 |
0.032 |
-21.97% |
0.032 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint32_t_
|
-21.55% |
6589.320 |
5169.454 |
4.164 |
-21.46% |
4.164 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
-21.40% |
389.835 |
306.428 |
0.550 |
-21.34% |
0.550 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint64_t_
|
-21.38% |
13179.252 |
10361.961 |
3.980 |
-21.55% |
3.980 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_uint8_t_
|
-21.35% |
182326.373 |
143400.872 |
3.168 |
-21.36% |
3.168 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
-21.27% |
1.501 |
1.181 |
0.000 |
-21.28% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/5001
|
-20.99% |
1124.972 |
888.867 |
41.991 |
-19.60% |
41.991 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC32
|
-20.82% |
168.318 |
133.282 |
0.003 |
-20.82% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
-20.63% |
45.203 |
35.879 |
0.203 |
-20.72% |
0.203 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC127
|
-20.48% |
275.608 |
219.151 |
0.563 |
-20.44% |
0.563 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC32
|
-20.44% |
168.321 |
133.915 |
0.004 |
-20.45% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC63
|
-20.41% |
324.749 |
258.453 |
0.008 |
-20.42% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC128
|
-20.33% |
273.555 |
217.954 |
0.629 |
-20.67% |
0.629 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC63
|
-20.04% |
324.783 |
259.703 |
0.012 |
-20.04% |
0.012 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DISC_ORD_LAMBDA/5001
|
-19.84% |
732.867 |
587.481 |
41.283 |
-7.82% |
41.283 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC127
|
-19.71% |
640.879 |
514.587 |
0.136 |
-19.66% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC16
|
-19.29% |
92.264 |
74.464 |
0.014 |
-19.31% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
-19.08% |
3817.544 |
3088.982 |
0.317 |
-19.10% |
0.317 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/5001
|
-19.05% |
1119.894 |
906.523 |
9.265 |
-0.76% |
9.265 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint64_t_To_uint32_t_
|
-18.83% |
27135.618 |
22026.090 |
33.564 |
-18.58% |
33.564 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
-18.80% |
8.758 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/2
|
-18.79% |
8.757 |
7.111 |
0.000 |
-18.80% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint32_t_To_uint16_t_
|
-18.57% |
13801.497 |
11237.942 |
11.084 |
-18.61% |
11.084 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC63
|
-18.49% |
148.851 |
121.335 |
2.065 |
-19.06% |
2.065 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC64
|
-18.47% |
147.968 |
120.639 |
0.583 |
-18.83% |
0.583 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/5001
|
-18.40% |
1124.819 |
917.872 |
29.896 |
-14.88% |
29.896 |
|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
-18.38% |
0.124 |
0.101 |
0.000 |
-18.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint8_t_
|
-18.35% |
13905.025 |
11353.560 |
7.598 |
-18.32% |
7.598 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC16
|
-18.29% |
95.737 |
78.223 |
0.001 |
-18.30% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
-18.14% |
1.104 |
0.904 |
0.000 |
-18.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_uint8_t_
|
-17.95% |
746725.425 |
612661.706 |
79.693 |
-17.85% |
79.693 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC16
|
-17.65% |
95.743 |
78.845 |
0.002 |
-17.65% |
0.002 |
|
MultiSource/Benchmarks/MiBench/security-rijndael/security-rijndael
Profile
|
-17.52% |
0.335 |
0.276 |
0.001 |
-17.42% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint64_t_
|
-17.46% |
13201.020 |
10895.795 |
13.026 |
-16.60% |
13.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC31
|
-17.41% |
179.578 |
148.308 |
0.003 |
-17.42% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int32_t_
|
-17.37% |
739929.228 |
611397.814 |
42.104 |
-17.40% |
42.104 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
-17.33% |
570.715 |
471.821 |
0.225 |
-17.31% |
0.225 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC4
|
-17.26% |
17.519 |
14.496 |
0.011 |
-17.26% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIRST_SUM_RAW/44217
|
-17.25% |
162.253 |
134.257 |
0.647 |
-19.29% |
0.647 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC32
|
-17.23% |
85.530 |
70.791 |
1.286 |
-17.03% |
1.286 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
-17.10% |
297.778 |
246.860 |
0.021 |
-17.08% |
0.021 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_SUM_LAMBDA/5001
|
-16.93% |
20.683 |
17.181 |
0.740 |
-2.42% |
0.740 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC31
|
-16.72% |
179.587 |
149.551 |
0.010 |
-16.72% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
-16.51% |
160.742 |
134.197 |
0.022 |
-16.85% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
-16.44% |
93.204 |
77.879 |
0.026 |
-16.37% |
0.026 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/1
|
-16.21% |
260.281 |
218.092 |
0.267 |
-16.17% |
0.267 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/0
|
-16.15% |
1262.941 |
1058.933 |
2.327 |
-16.46% |
2.327 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/171
|
-16.14% |
0.443 |
0.372 |
0.000 |
-15.84% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/1
|
-16.13% |
260.287 |
218.314 |
0.108 |
-16.07% |
0.108 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC31
|
-16.12% |
85.959 |
72.101 |
1.821 |
-16.27% |
1.821 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
-16.11% |
0.443 |
0.372 |
0.000 |
-15.88% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_VOL3D_CALC_RAW/0
|
-16.09% |
1266.610 |
1062.845 |
1.702 |
-15.99% |
1.702 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC4
|
-15.82% |
113.157 |
95.260 |
0.538 |
-15.76% |
0.538 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint32_t_
|
-15.68% |
7463.632 |
6293.362 |
0.459 |
-15.66% |
0.459 |
|
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 |
14104.181 |
0.294 |
-15.40% |
0.294 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
-15.39% |
24.404 |
20.649 |
0.000 |
-15.38% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Mid>
|
-15.37% |
16666.454 |
14104.408 |
0.703 |
-15.37% |
0.703 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, EqZero, Last>
|
-15.35% |
16667.937 |
14109.000 |
0.214 |
-15.35% |
0.214 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint8_t_
|
-15.05% |
10641.738 |
9040.487 |
30.296 |
-14.67% |
30.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
-14.79% |
605.595 |
516.048 |
0.019 |
-14.81% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC8
|
-14.73% |
59.443 |
50.685 |
0.002 |
-14.74% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC128
|
-14.57% |
1103.277 |
942.563 |
0.058 |
-14.57% |
0.058 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC127
|
-14.54% |
1095.619 |
936.356 |
0.047 |
-14.51% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC64
|
-14.33% |
562.484 |
481.863 |
0.020 |
-14.31% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC63
|
-14.18% |
554.194 |
475.609 |
2.714 |
-14.26% |
2.714 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/1024
|
-14.17% |
7415.982 |
6365.202 |
185.138 |
-10.48% |
185.138 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
-14.14% |
15.387 |
13.211 |
0.001 |
-14.13% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint8_t_To_uint16_t_
|
-14.12% |
3756.902 |
3226.556 |
8.900 |
-14.11% |
8.900 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint64_t_To_uint8_t_
|
-13.88% |
22055.605 |
18995.184 |
17.509 |
-13.84% |
17.509 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC2
|
-13.86% |
51.936 |
44.739 |
0.004 |
-13.85% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC8
|
-13.86% |
51.936 |
44.740 |
0.003 |
-13.86% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC7
|
-13.85% |
51.936 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC1
|
-13.85% |
51.934 |
44.740 |
0.002 |
-13.85% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC3
|
-13.85% |
51.935 |
44.741 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC4
|
-13.85% |
51.933 |
44.741 |
0.001 |
-13.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_novec_int64_t_
|
-13.85% |
789585.548 |
680242.809 |
1823.691 |
-13.68% |
1823.691 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_with_cond_arith_autovec_int64_t_
|
-13.76% |
789552.919 |
680882.532 |
1300.665 |
-13.99% |
1300.665 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC8
|
-13.68% |
59.445 |
51.314 |
0.001 |
-13.69% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC31
|
-13.64% |
284.040 |
245.308 |
0.017 |
-13.65% |
0.017 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Last>
|
-13.63% |
14104.298 |
12181.525 |
0.303 |
-13.64% |
0.303 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
-13.63% |
14104.388 |
12181.983 |
0.622 |
-13.62% |
0.622 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, First>
|
-13.63% |
14103.713 |
12181.453 |
0.508 |
-13.63% |
0.508 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint8_t_
|
-13.56% |
11013.237 |
9520.110 |
63.770 |
-14.46% |
63.770 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC32
|
-13.55% |
290.978 |
251.548 |
0.018 |
-13.85% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC8
|
-13.52% |
23.153 |
20.022 |
0.001 |
-13.52% |
0.001 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
-13.43% |
223.021 |
193.068 |
0.194 |
-13.65% |
0.194 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC63
|
-13.39% |
374.347 |
324.205 |
0.028 |
-13.41% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint16_t_
|
-13.18% |
12794.310 |
11107.472 |
5.879 |
-13.47% |
5.879 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DISC_ORD_RAW/5001
|
-13.16% |
640.201 |
555.938 |
30.820 |
-16.37% |
30.820 |
|
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
|
-13.12% |
224.592 |
195.124 |
10.487 |
-14.41% |
10.487 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
-13.08% |
81.347 |
70.707 |
0.012 |
-13.08% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC16
|
-12.99% |
156.780 |
136.413 |
0.006 |
-13.09% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint16_t_
|
-12.95% |
4542.149 |
3953.812 |
0.643 |
-12.95% |
0.643 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC15
|
-12.85% |
106.991 |
93.243 |
0.001 |
-12.86% |
0.001 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
-12.75% |
2.509 |
2.189 |
0.000 |
-12.71% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC16
|
-12.73% |
51.938 |
45.324 |
0.296 |
-12.74% |
0.296 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
-12.67% |
332.876 |
290.699 |
0.018 |
-12.66% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC15
|
-12.60% |
148.925 |
130.157 |
0.003 |
-12.53% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/44217
|
-12.42% |
9136.951 |
8001.698 |
84.757 |
-11.58% |
84.757 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
-12.42% |
4742.886 |
4153.903 |
0.515 |
-12.42% |
0.515 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint32_t_To_uint16_t_
|
-12.08% |
9955.172 |
8752.246 |
90.317 |
-11.64% |
90.317 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/5001
|
-11.96% |
17.751 |
15.628 |
0.401 |
-9.00% |
0.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC8
|
-11.87% |
89.461 |
78.843 |
0.003 |
-11.81% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC2
|
-11.77% |
21.275 |
18.771 |
0.001 |
-11.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC15
|
-11.70% |
106.999 |
94.485 |
0.002 |
-11.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForBigLoopWithReductionAutoVecTC15
|
-11.45% |
51.935 |
45.991 |
0.001 |
-11.45% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint32_t_To_uint16_t_
|
-11.37% |
10467.908 |
9277.828 |
228.144 |
-13.59% |
228.144 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC16
|
-11.33% |
33.163 |
29.405 |
0.001 |
-11.33% |
0.001 |
|
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 |
20.023 |
0.003 |
-11.12% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC3
|
-11.11% |
22.525 |
20.023 |
0.002 |
-11.11% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/51
|
-11.11% |
123.894 |
110.134 |
0.436 |
19.06% |
0.436 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_1D_RAW/5001
|
-10.78% |
17.631 |
15.731 |
0.459 |
-5.72% |
0.459 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC7
|
-10.78% |
81.353 |
72.586 |
0.004 |
-10.73% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC4
|
-10.60% |
41.295 |
36.918 |
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 |
48.182 |
0.001 |
-10.47% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/16
|
-10.18% |
115.475 |
103.722 |
0.036 |
-10.17% |
0.036 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint16_t_
|
-10.14% |
5851.855 |
5258.757 |
4.888 |
-10.11% |
4.888 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC4
|
-10.11% |
55.690 |
50.060 |
0.001 |
-10.07% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/64
|
-10.00% |
1913.332 |
1721.910 |
9.474 |
-10.00% |
9.474 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC127
|
-9.99% |
102.189 |
91.982 |
0.005 |
-9.71% |
0.005 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/32
|
-9.99% |
472.992 |
425.749 |
0.006 |
-9.99% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/oopack_v1p8
Profile
|
-9.99% |
0.519 |
0.467 |
0.000 |
-10.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_DIFF_PREDICT_LAMBDA/171
|
-9.81% |
12.320 |
11.111 |
0.086 |
-7.30% |
0.086 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/256
|
-9.80% |
31389.140 |
28313.382 |
27.450 |
-9.97% |
27.450 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BILINEAR_INTERPOLATION/128
|
-9.78% |
7903.080 |
7130.330 |
5.066 |
-9.94% |
5.066 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
-9.76% |
25.655 |
23.151 |
0.001 |
-9.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
-9.76% |
25.655 |
23.152 |
0.001 |
-9.76% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
-9.62% |
333218.417 |
301161.269 |
173.489 |
-9.64% |
173.489 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC7
|
-9.62% |
32.540 |
29.410 |
0.001 |
-9.61% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
-9.52% |
26.280 |
23.777 |
0.001 |
-9.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC7
|
-9.52% |
26.279 |
23.777 |
0.002 |
-9.53% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC7
|
-9.51% |
352.608 |
319.087 |
2.213 |
-10.04% |
2.213 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC32
|
-9.42% |
53.185 |
48.174 |
0.006 |
-9.44% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
-9.39% |
196.478 |
178.031 |
0.002 |
-9.39% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
-9.24% |
287.120 |
260.602 |
0.189 |
-9.24% |
0.189 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
-9.23% |
287.242 |
260.737 |
0.075 |
-9.15% |
0.075 |
|
MultiSource/Benchmarks/FreeBench/pifft/pifft
Profile
|
-9.15% |
0.359 |
0.326 |
0.001 |
-8.99% |
0.001 |
|
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 |
37.543 |
0.001 |
-9.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC7
|
-8.89% |
28.157 |
25.655 |
0.001 |
-8.90% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
-8.76% |
12.885 |
11.756 |
0.366 |
-3.56% |
0.366 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_pass<4, int>
|
-8.74% |
16.799 |
15.330 |
0.000 |
-8.25% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
-8.72% |
3.510 |
3.204 |
0.000 |
-8.71% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/2
|
-8.71% |
3.510 |
3.204 |
0.000 |
-8.71% |
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 |
26.907 |
0.003 |
-8.51% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint8_t_
|
-8.44% |
6810.941 |
6235.828 |
7.201 |
-8.51% |
7.201 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/28
|
-8.25% |
82.593 |
75.782 |
0.216 |
12.12% |
0.216 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint64_t_
|
-8.21% |
20335.796 |
18666.825 |
18.085 |
-7.33% |
18.085 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC2
|
-8.20% |
38.171 |
35.042 |
0.002 |
-8.20% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint8_t_To_uint32_t_
|
-8.17% |
12822.735 |
11774.640 |
16.680 |
-7.86% |
16.680 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC64
|
-8.07% |
93.236 |
85.715 |
0.002 |
-8.07% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_HYDRO_2D_RAW/171
|
-8.00% |
88.881 |
81.774 |
0.622 |
-7.73% |
0.622 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC3
|
-7.91% |
47.561 |
43.800 |
0.001 |
-7.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC16
|
-7.84% |
31.911 |
29.408 |
0.001 |
-7.85% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC16
|
-7.83% |
31.909 |
29.410 |
0.000 |
-7.84% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC32
|
-7.83% |
40.051 |
36.917 |
0.001 |
-7.82% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
-7.69% |
32.538 |
30.034 |
0.002 |
-7.70% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
-7.69% |
32.537 |
30.036 |
0.002 |
-7.69% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
-7.62% |
2403.930 |
2220.789 |
5.427 |
-8.48% |
5.427 |
|
MultiSource/Benchmarks/VersaBench/beamformer/beamformer
Profile
|
-7.56% |
5.200 |
4.807 |
0.001 |
-7.56% |
0.001 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
-7.52% |
3.507 |
3.243 |
0.000 |
-7.48% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
-7.51% |
1794.427 |
1659.717 |
3.867 |
-7.84% |
3.867 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/0
|
-7.47% |
1793.121 |
1659.238 |
3.205 |
-7.41% |
3.205 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
-7.42% |
16.895 |
15.643 |
0.001 |
-7.42% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_2D_LAMBDA/171
|
-7.36% |
88.642 |
82.122 |
0.131 |
-7.37% |
0.131 |
|
MultiSource/Applications/lambda-0.1.3/lambda
Profile
|
-7.34% |
15.895 |
14.728 |
0.011 |
-7.19% |
0.011 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
-7.24% |
1.498 |
1.389 |
0.000 |
-7.19% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC128
|
-7.22% |
173.339 |
160.817 |
0.003 |
-7.22% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
-7.21% |
138.914 |
128.904 |
0.008 |
-7.21% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
-7.09% |
88.672 |
82.382 |
0.383 |
-7.42% |
0.383 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
-7.08% |
25041.477 |
23268.565 |
23.945 |
-6.87% |
23.945 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC7
|
-7.08% |
70.709 |
65.706 |
0.005 |
-7.08% |
0.005 |
|
SingleSource/Benchmarks/Misc/pi
Profile
|
-7.03% |
1.782 |
1.657 |
0.000 |
-7.03% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC15
|
-6.94% |
45.055 |
41.927 |
0.053 |
-6.94% |
0.053 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC15
|
-6.88% |
54.434 |
50.686 |
0.001 |
-6.90% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC31
|
-6.72% |
74.455 |
69.455 |
0.005 |
-6.73% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC128
|
-6.59% |
68.831 |
64.295 |
0.052 |
-6.55% |
0.052 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC63
|
-6.55% |
114.514 |
107.015 |
0.204 |
-6.55% |
0.204 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
-6.54% |
45.343 |
42.376 |
0.214 |
-6.54% |
0.214 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_pass<16, int>
|
-6.52% |
28.782 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_runtime_checks_fail<16, int>
|
-6.51% |
28.783 |
26.907 |
0.001 |
-6.52% |
0.001 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
-6.48% |
15.976 |
14.940 |
0.102 |
-6.44% |
0.102 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC63
|
-6.47% |
74.260 |
69.455 |
0.010 |
-6.42% |
0.010 |
|
SingleSource/Benchmarks/Misc/flops-6
Profile
|
-6.42% |
1.312 |
1.228 |
0.000 |
-6.47% |
0.000 |
|
MicroBenchmarks/harris/harris.test:BENCHMARK_HARRIS/2048/2048
|
-6.39% |
168774.291 |
157992.614 |
3412.129 |
-5.41% |
3412.129 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC127
|
-6.38% |
194.598 |
182.180 |
0.205 |
-6.39% |
0.205 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
-6.35% |
39.421 |
36.919 |
0.002 |
-6.35% |
0.002 |
|
SingleSource/Benchmarks/Polybench/stencils/jacobi-2d/jacobi-2d
Profile
|
-6.34% |
31.985 |
29.958 |
0.277 |
-7.03% |
0.277 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_DIFF_PREDICT_RAW/171
|
-6.34% |
11.862 |
11.110 |
0.090 |
-6.89% |
0.090 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC127
|
-6.33% |
68.793 |
64.440 |
0.007 |
-5.64% |
0.007 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_BAND_LIN_EQ_RAW/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int32_t_
|
-6.32% |
180964.907 |
169530.770 |
129.924 |
-6.40% |
129.924 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/171
|
-6.32% |
0.366 |
0.343 |
0.000 |
-6.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/127
|
-6.31% |
138.921 |
130.149 |
0.006 |
-6.31% |
0.006 |
|
SingleSource/Benchmarks/Misc-C++/Large/sphereflake
Profile
|
-6.19% |
20.006 |
18.768 |
0.003 |
-6.17% |
0.003 |
|
External/SPEC/CFP2017rate/519.lbm_r/519.lbm_r
Profile
|
-6.17% |
204.954 |
192.316 |
1.312 |
-4.17% |
1.312 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC16
|
-6.16% |
40.672 |
38.169 |
0.001 |
-6.16% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/65
|
-5.93% |
95.119 |
89.481 |
0.004 |
-5.92% |
0.004 |
|
SingleSource/Benchmarks/Shootout/Shootout-ary3
Profile
|
-5.90% |
3.667 |
3.450 |
0.064 |
-1.95% |
0.064 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/127
|
-5.89% |
138.289 |
130.148 |
0.004 |
-5.88% |
0.004 |
|
MultiSource/Benchmarks/MiBench/telecomm-gsm/telecomm-gsm
Profile
|
-5.86% |
0.663 |
0.624 |
0.000 |
-5.92% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
-5.75% |
907.399 |
855.199 |
4.586 |
-6.74% |
4.586 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC16
|
-5.65% |
33.162 |
31.287 |
0.005 |
-5.66% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC32
|
-5.63% |
44.426 |
41.924 |
0.001 |
-5.64% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC32
|
-5.63% |
44.422 |
41.922 |
0.001 |
-5.64% |
0.001 |
|
SingleSource/Benchmarks/Stanford/Puzzle
Profile
|
-5.59% |
0.241 |
0.228 |
0.001 |
-5.53% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC31
|
-5.56% |
45.052 |
42.549 |
0.003 |
-5.58% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC31
|
-5.55% |
45.049 |
42.550 |
0.001 |
-5.56% |
0.001 |
|
MultiSource/Benchmarks/SciMark2-C/scimark2
Profile
|
-5.52% |
107.655 |
101.713 |
0.034 |
-5.51% |
0.034 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
-5.43% |
3121.916 |
2952.333 |
17.037 |
-5.64% |
17.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint64_t_To_uint32_t_
|
-5.41% |
15878.490 |
15018.704 |
98.297 |
-0.61% |
98.297 |
|
External/SPEC/CFP2017rate/538.imagick_r/538.imagick_r
Profile
|
-5.40% |
290.706 |
275.012 |
0.217 |
-5.84% |
0.217 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/999
|
-5.39% |
696.485 |
658.937 |
0.021 |
-5.40% |
0.021 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
-5.38% |
2968.548 |
2808.698 |
15.953 |
-5.57% |
15.953 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_2D_LAMBDA/171
|
-5.37% |
13.482 |
12.757 |
0.060 |
-5.49% |
0.060 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
-5.36% |
389.327 |
368.442 |
0.077 |
-5.43% |
0.077 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint8_t_To_uint16_t_
|
-5.34% |
3630.131 |
3436.230 |
0.823 |
-5.43% |
0.823 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint64_t_
|
-5.33% |
21468.256 |
20324.693 |
30.866 |
-5.25% |
30.866 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1BigLoopWithReductionTC7
|
-5.31% |
70.708 |
66.954 |
0.005 |
-5.32% |
0.005 |
|
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
|
-5.22% |
1365.065 |
1293.742 |
0.015 |
-5.22% |
0.015 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC32
|
-5.13% |
24.405 |
23.152 |
0.004 |
-5.12% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC31
|
-5.13% |
24.403 |
23.151 |
0.010 |
-5.13% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC31
|
-5.12% |
24.403 |
23.153 |
0.000 |
-5.13% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC32
|
-5.12% |
24.402 |
23.152 |
0.000 |
-5.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
-5.11% |
128.267 |
121.706 |
0.004 |
-5.11% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC32
|
-5.10% |
61.321 |
58.194 |
0.001 |
-5.10% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopWithReductionTC31
|
-5.08% |
241.300 |
229.039 |
0.041 |
-5.05% |
0.041 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_PIC_1D_LAMBDA/5001
|
-5.05% |
349.522 |
331.857 |
4.820 |
-5.98% |
4.820 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_PIC_2D_RAW/171
|
-5.04% |
13.532 |
12.851 |
0.051 |
-5.09% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint32_t>/256
|
-4.81% |
364.176 |
346.668 |
0.014 |
-4.81% |
0.014 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
-4.70% |
0.641 |
0.611 |
0.000 |
-4.69% |
0.000 |
|
MultiSource/Benchmarks/McCat/12-IOtest/iotest
Profile
|
-4.61% |
1.759 |
1.678 |
0.016 |
-8.04% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
-4.61% |
95.115 |
90.731 |
0.006 |
-4.61% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
-4.60% |
1640.658 |
1565.193 |
9.102 |
-4.78% |
9.102 |
|
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>
|
-4.59% |
54.435 |
51.934 |
0.003 |
-4.60% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopWithReductionTC2
|
-4.52% |
13.766 |
13.144 |
0.002 |
-4.52% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC31
|
-4.46% |
70.080 |
66.951 |
0.002 |
-4.47% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/44217
|
-4.44% |
503.786 |
481.411 |
2.836 |
-3.44% |
2.836 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/5001
|
-4.40% |
437.008 |
417.783 |
5.368 |
-2.56% |
5.368 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_int32_t_
|
-4.39% |
650043.949 |
621525.071 |
201.332 |
-3.66% |
201.332 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint64_t_
|
-4.36% |
23528.576 |
22502.471 |
27.854 |
-4.18% |
27.854 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
-4.36% |
1730.820 |
1655.404 |
7.430 |
-4.70% |
7.430 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC8
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC4
|
-4.35% |
14.392 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC15
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC16
|
-4.35% |
14.391 |
13.766 |
0.001 |
-4.35% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
-4.34% |
14.392 |
13.766 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC3
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC15
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
-4.34% |
14.393 |
13.768 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC7
|
-4.34% |
14.391 |
13.767 |
0.000 |
-4.34% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC7
|
-4.34% |
14.390 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC3
|
-4.34% |
14.391 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC8
|
-4.34% |
14.390 |
13.766 |
0.001 |
-4.36% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC16
|
-4.34% |
14.390 |
13.766 |
0.000 |
-4.36% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
-4.34% |
14.390 |
13.766 |
0.000 |
-4.35% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC63
|
-4.26% |
43.548 |
41.691 |
0.005 |
-3.70% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/999
|
-4.26% |
1811.098 |
1733.943 |
0.106 |
-4.27% |
0.106 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/16
|
-4.17% |
59.868 |
57.374 |
0.180 |
6.61% |
0.180 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
-4.17% |
1488.996 |
1426.956 |
7.597 |
-4.27% |
7.597 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/999
|
-4.16% |
3595.253 |
3445.600 |
0.284 |
-4.15% |
0.284 |
|
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
|
-4.15% |
14.196 |
13.607 |
0.009 |
-4.50% |
0.009 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/5001
|
-4.12% |
433.261 |
415.428 |
2.934 |
-5.16% |
2.934 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/256
|
-4.08% |
935.577 |
897.372 |
0.037 |
-4.08% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint32_t_
|
-4.05% |
19367.741 |
18582.995 |
43.703 |
-3.68% |
43.703 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC31
|
-4.04% |
61.947 |
59.446 |
0.002 |
-4.04% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC16
|
-4.03% |
31.295 |
30.035 |
0.230 |
-4.01% |
0.230 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/171
|
-4.02% |
14.210 |
13.638 |
0.011 |
-4.23% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint32_t_To_uint16_t_
|
-3.99% |
9836.810 |
9444.043 |
53.959 |
-4.41% |
53.959 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_uint8_t_
|
-3.99% |
96170.007 |
92333.778 |
2.791 |
-3.98% |
2.791 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
-3.99% |
1510.525 |
1450.321 |
5.614 |
-4.27% |
5.614 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint32_t>/65
|
-3.97% |
94.478 |
90.728 |
0.004 |
-3.98% |
0.004 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
-3.96% |
6.126 |
5.883 |
0.001 |
-3.98% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_PRESSURE_CALC_LAMBDA/5001
|
-3.96% |
45.166 |
43.379 |
0.451 |
-1.35% |
0.451 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC32
|
-3.95% |
63.196 |
60.697 |
0.004 |
-3.96% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint32_t>/256
|
-3.95% |
221.510 |
212.750 |
0.009 |
-3.95% |
0.009 |
|
SingleSource/Benchmarks/Misc/oourafft
Profile
|
-3.94% |
15.021 |
14.428 |
0.108 |
-4.41% |
0.108 |
|
SingleSource/Benchmarks/CoyoteBench/lpbench
Profile
|
-3.94% |
13.357 |
12.831 |
0.091 |
-0.69% |
0.091 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_runtime_checks_fail<4, int>
|
-3.93% |
15.957 |
15.330 |
0.001 |
-3.64% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/256
|
-3.91% |
1062.880 |
1021.348 |
5.195 |
-4.30% |
5.195 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
-3.88% |
745.450 |
716.490 |
4.150 |
-4.55% |
4.150 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC3
|
-3.84% |
16.269 |
15.643 |
0.001 |
-3.84% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, Mid>
|
-3.75% |
2754.320 |
2651.044 |
35.942 |
-3.40% |
35.942 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
-3.74% |
21.205 |
20.412 |
0.000 |
-1.85% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Dilate/Dilate.test:BENCHMARK_DILATE/512
|
-3.73% |
3590.013 |
3456.046 |
28.191 |
-3.57% |
28.191 |
|
SingleSource/Benchmarks/Shootout/Shootout-matrix
Profile
|
-3.70% |
3.864 |
3.721 |
0.000 |
-3.68% |
0.000 |
|
MultiSource/Benchmarks/Rodinia/hotspot/hotspot
Profile
|
-3.66% |
2.000 |
1.927 |
0.011 |
-5.36% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/256
|
-3.65% |
514.390 |
495.604 |
0.022 |
-3.65% |
0.022 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
-3.65% |
31.232 |
30.093 |
0.181 |
-3.51% |
0.181 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, EqZero, First>
|
-3.62% |
3344.151 |
3223.055 |
0.057 |
-3.68% |
0.057 |
|
MultiSource/Benchmarks/TSVC/NodeSplitting-dbl/NodeSplitting-dbl
Profile
|
-3.61% |
27.144 |
26.165 |
0.235 |
-0.95% |
0.235 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC64
|
-3.60% |
69.456 |
66.954 |
0.001 |
-3.60% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
-3.60% |
277.570 |
267.580 |
1.088 |
-3.13% |
1.088 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC64
|
-3.60% |
69.453 |
66.953 |
0.005 |
-3.61% |
0.005 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
-3.59% |
500.096 |
482.161 |
1.680 |
-3.99% |
1.680 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC63
|
-3.58% |
70.090 |
67.579 |
0.002 |
-3.58% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC63
|
-3.57% |
70.081 |
67.577 |
0.004 |
-3.58% |
0.004 |
|
MultiSource/Applications/sgefa/sgefa
Profile
|
-3.56% |
0.587 |
0.566 |
0.002 |
-1.32% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint8_t_
|
-3.54% |
2873.097 |
2771.383 |
4.424 |
-3.71% |
4.424 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
-3.50% |
477.136 |
460.423 |
0.020 |
-3.65% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC64
|
-3.44% |
43.181 |
41.695 |
0.016 |
-3.43% |
0.016 |
|
SingleSource/Benchmarks/Shootout/Shootout-heapsort
Profile
|
-3.40% |
22.690 |
21.918 |
0.106 |
-0.56% |
0.106 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Last>
|
-3.39% |
7080.229 |
6840.365 |
56.206 |
-3.01% |
56.206 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC31
|
-3.32% |
60.194 |
58.194 |
0.003 |
-3.45% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW16From_uint16_t_To_uint8_t_
|
-3.19% |
4512.901 |
4369.016 |
2.861 |
-3.28% |
2.861 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-ary3
Profile
|
-3.17% |
3.648 |
3.532 |
0.023 |
-0.50% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/999
|
-3.16% |
514.997 |
498.706 |
0.033 |
-3.17% |
0.033 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
-3.14% |
37631.714 |
36448.303 |
33.310 |
-3.00% |
33.310 |
|
SingleSource/Benchmarks/Polybench/stencils/fdtd-2d/fdtd-2d
Profile
|
-3.12% |
20.043 |
19.417 |
0.162 |
-0.45% |
0.162 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC1
|
-3.12% |
20.022 |
19.397 |
0.001 |
-3.14% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/1000
|
-3.08% |
5020119.583 |
4865536.160 |
350.347 |
-3.07% |
350.347 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
-3.05% |
11.316 |
10.971 |
0.002 |
-3.02% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_BAND_LIN_EQ_LAMBDA/5001
|
-2.93% |
20.746 |
20.138 |
0.084 |
-3.18% |
0.084 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/999
|
-2.84% |
1013.787 |
984.962 |
0.126 |
-2.85% |
0.126 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
-2.82% |
44.614 |
43.354 |
0.185 |
-2.42% |
0.185 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC64
|
-2.81% |
111.387 |
108.256 |
0.004 |
-2.81% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1BigLoopWithReductionTC1
|
-2.77% |
22.526 |
21.902 |
0.000 |
-2.77% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopWithReductionTC1
|
-2.77% |
22.524 |
21.900 |
0.001 |
-2.77% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC32
|
-2.74% |
31.282 |
30.425 |
0.023 |
-2.75% |
0.023 |
|
MultiSource/Benchmarks/FreeBench/fourinarow/fourinarow
Profile
|
-2.73% |
0.651 |
0.634 |
0.001 |
-2.63% |
0.001 |
|
MultiSource/Benchmarks/FreeBench/mason/mason
Profile
|
-2.72% |
0.553 |
0.538 |
0.000 |
-2.72% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC31
|
-2.66% |
93.290 |
90.811 |
0.051 |
-3.24% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC63
|
-2.60% |
120.141 |
117.013 |
0.003 |
-2.61% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint8_t>/10
|
-2.56% |
48.808 |
47.560 |
0.202 |
2.47% |
0.202 |
|
MultiSource/Benchmarks/Olden/voronoi/voronoi
Profile
|
-2.52% |
1.408 |
1.372 |
0.013 |
-0.93% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint8_t_To_uint32_t_
|
-2.52% |
7077.932 |
6899.896 |
0.925 |
-2.51% |
0.925 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_ENERGY_CALC_LAMBDA/44217
|
-2.47% |
4366.616 |
4258.669 |
9.349 |
-1.52% |
9.349 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint64_t_To_uint8_t_
|
-2.46% |
19742.555 |
19255.985 |
45.926 |
-2.95% |
45.926 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchVecWithRuntimeChecks4PointersDBeforeA/32
|
-2.45% |
166195.324 |
162129.286 |
14.830 |
-2.45% |
14.830 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
-2.40% |
9.699 |
9.466 |
0.018 |
-2.41% |
0.018 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Last>
|
-2.39% |
8297.219 |
8099.275 |
10.258 |
-2.37% |
10.258 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC63
|
-2.34% |
106.998 |
104.498 |
0.004 |
-2.34% |
0.004 |
|
SingleSource/Benchmarks/Misc/fbench
Profile
|
-2.33% |
5.762 |
5.627 |
0.000 |
-2.32% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, EqZero, None>
|
-2.33% |
2960.811 |
2891.906 |
13.562 |
-1.28% |
13.562 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint32_t_To_uint64_t_
|
-2.33% |
26378.093 |
25764.347 |
50.154 |
-1.96% |
50.154 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-dbl/ControlLoops-dbl
Profile
|
-2.32% |
10.935 |
10.681 |
0.082 |
-3.06% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
-2.31% |
108.253 |
105.751 |
0.002 |
-2.31% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
-2.30% |
736.351 |
719.417 |
4.831 |
-2.59% |
4.831 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_multi_csa_only_autovec_int64_t_
|
-2.28% |
1446782.685 |
1413760.796 |
393.696 |
-2.30% |
393.696 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/CoMD/CoMD
Profile
|
-2.28% |
9.852 |
9.627 |
0.002 |
-2.75% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
-2.25% |
86.422 |
84.474 |
0.002 |
11.81% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
-2.24% |
1788.144 |
1748.083 |
2.696 |
0.84% |
2.696 |
|
SingleSource/Benchmarks/Misc/flops-1
Profile
|
-2.17% |
9.002 |
8.806 |
0.000 |
-2.15% |
0.000 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
-2.12% |
93.488 |
91.502 |
0.414 |
-2.72% |
0.414 |
|
SingleSource/Benchmarks/Misc-C++/Large/ray
Profile
|
-2.10% |
12.104 |
11.850 |
0.000 |
-2.07% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC128
|
-2.09% |
119.512 |
117.016 |
0.003 |
-2.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
-2.09% |
119.511 |
117.015 |
0.002 |
-2.10% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC127
|
-2.08% |
120.144 |
117.639 |
0.001 |
-2.09% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC127
|
-2.08% |
120.131 |
117.636 |
0.004 |
-2.08% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
-2.07% |
520.970 |
510.192 |
3.057 |
-2.89% |
3.057 |
|
MultiSource/Benchmarks/tramp3d-v4/tramp3d-v4
Profile
|
-2.06% |
1.079 |
1.057 |
0.002 |
-1.77% |
0.002 |
|
MultiSource/Benchmarks/Rodinia/pathfinder/pathfinder
Profile
|
-2.05% |
1.253 |
1.227 |
0.008 |
-2.44% |
0.008 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
-2.01% |
260.421 |
255.187 |
0.344 |
-1.89% |
0.344 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
-2.00% |
32.323 |
31.676 |
0.019 |
-2.65% |
0.019 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
-1.99% |
6651.880 |
6519.743 |
8.956 |
-1.89% |
8.956 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/44217
|
-1.97% |
273.022 |
267.656 |
1.121 |
-0.69% |
1.121 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/171
|
-1.95% |
0.872 |
0.855 |
0.000 |
-1.81% |
0.000 |
|
MicroBenchmarks/LoopInterchange/LoopInterchange.test:BENCHMARK_LI1
|
-1.95% |
1532.092 |
1502.200 |
6.255 |
-0.16% |
6.255 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_EOS_LAMBDA/171
|
-1.94% |
0.872 |
0.855 |
0.001 |
-1.77% |
0.001 |
|
MultiSource/Benchmarks/TSVC/ControlLoops-flt/ControlLoops-flt
Profile
|
-1.93% |
5.426 |
5.321 |
0.030 |
-2.31% |
0.030 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC4
|
-1.92% |
346.327 |
339.692 |
2.254 |
-2.77% |
2.254 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
-1.87% |
11255.914 |
11045.207 |
26.097 |
-2.62% |
26.097 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/256
|
-1.84% |
272.836 |
267.829 |
0.007 |
-1.84% |
0.007 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<16, EqZero, Mid>
|
-1.71% |
8660.401 |
8511.965 |
49.642 |
-1.68% |
49.642 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
-1.71% |
6.919 |
6.801 |
0.011 |
-1.79% |
0.011 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_autovec_int64_t_
|
-1.70% |
745474.518 |
732820.129 |
1657.740 |
-1.63% |
1657.740 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C/SimpleMOC/SimpleMOC
Profile
|
-1.69% |
10.399 |
10.223 |
0.066 |
-1.75% |
0.066 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint64_t>/51
|
-1.69% |
148.298 |
145.798 |
0.014 |
-1.69% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_nested_cond_load_novec_uint8_t_
|
-1.68% |
504562.587 |
496101.240 |
149.396 |
-1.71% |
149.396 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
-1.66% |
5.141 |
5.056 |
0.000 |
-1.62% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_in_loop_arith_novec_int64_t_
|
-1.61% |
1028347.299 |
1011834.599 |
985.872 |
-1.59% |
985.872 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, LessThanZero, Mid>
|
-1.60% |
4570.511 |
4497.589 |
2.398 |
-1.61% |
2.398 |
|
MultiSource/Benchmarks/ASC_Sequoia/CrystalMk/CrystalMk
Profile
|
-1.59% |
15.575 |
15.327 |
0.000 |
-1.57% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, GreaterThanZero, None>
|
-1.57% |
44994.464 |
44288.703 |
223.237 |
-1.89% |
223.237 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_INT_PREDICT_LAMBDA/171
|
-1.57% |
6.918 |
6.810 |
0.006 |
-1.67% |
0.006 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
-1.55% |
6609.603 |
6507.060 |
27.942 |
-1.61% |
27.942 |
|
SingleSource/Benchmarks/Misc/mandel-2
Profile
|
-1.55% |
2.535 |
2.496 |
0.000 |
-1.54% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC128
|
-1.48% |
211.495 |
208.358 |
0.021 |
-1.49% |
0.021 |
|
MultiSource/Benchmarks/ASC_Sequoia/AMGmk/AMGmk
Profile
|
-1.47% |
33.267 |
32.776 |
0.044 |
-0.85% |
0.044 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_EOS_RAW/44217
|
-1.43% |
274.101 |
270.189 |
0.840 |
-1.06% |
0.840 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC127
|
-1.42% |
220.280 |
217.157 |
0.025 |
-1.42% |
0.025 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
-1.38% |
434.210 |
428.217 |
0.392 |
-2.56% |
0.392 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, GreaterThanZero, Mid>
|
-1.37% |
4555.912 |
4493.539 |
9.433 |
-1.36% |
9.433 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/51
|
-1.37% |
229.017 |
225.886 |
0.020 |
-1.36% |
0.020 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
-1.33% |
57.854 |
57.087 |
0.023 |
0.07% |
0.023 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
-1.27% |
198.361 |
195.845 |
0.008 |
-1.27% |
0.008 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC127
|
-1.26% |
197.091 |
194.603 |
0.028 |
-1.27% |
0.028 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Mid>
|
-1.23% |
19472.606 |
19232.755 |
5.502 |
-1.04% |
5.502 |
|
MultiSource/Benchmarks/MallocBench/cfrac/cfrac
Profile
|
-1.20% |
2.779 |
2.745 |
0.001 |
-1.25% |
0.001 |
|
External/SPEC/CFP2017rate/526.blender_r/526.blender_r
Profile
|
-1.20% |
891.068 |
880.394 |
2.465 |
-0.54% |
2.465 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC32
|
-1.15% |
49.429 |
48.859 |
0.100 |
-2.38% |
0.100 |
|
External/SPEC/CFP2017rate/511.povray_r/511.povray_r
Profile
|
-1.14% |
33.804 |
33.420 |
0.028 |
-1.08% |
0.028 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_autovec_float_
|
-1.13% |
2242.072 |
2216.662 |
0.882 |
-1.16% |
0.882 |
|
SingleSource/Benchmarks/SmallPT/smallpt
Profile
|
-1.12% |
30.044 |
29.706 |
0.003 |
-1.07% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopTC63
|
-1.11% |
129.793 |
128.347 |
0.104 |
-1.40% |
0.104 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_sinhf_novec_float_
|
-1.11% |
2243.067 |
2218.128 |
0.516 |
-1.06% |
0.516 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Mid>
|
-1.08% |
37597.206 |
37191.080 |
52.731 |
-1.08% |
52.731 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint8_t_To_uint32_t_
|
-1.06% |
12065.301 |
11937.204 |
23.949 |
-1.53% |
23.949 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
-1.06% |
56353.872 |
55759.203 |
89.790 |
-0.51% |
89.790 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<64, LessThanZero, Last>
|
-1.05% |
4179.209 |
4135.423 |
2.688 |
-0.85% |
2.688 |
|
External/SPEC/CINT2017rate/541.leela_r/541.leela_r
Profile
|
-1.03% |
228.337 |
225.988 |
0.613 |
-1.48% |
0.613 |