opengl:vfpbenchlog
差分
このページの2つのバージョン間の差分を表示します。
両方とも前のリビジョン前のリビジョン次のリビジョン | 前のリビジョン次のリビジョン両方とも次のリビジョン | ||
opengl:vfpbenchlog [2019/02/17 01:02] – [結果一覧] oga | opengl:vfpbenchlog [2019/06/16 01:04] – [Qualcomm Kryo 385 (Cortex-A55) (ARMv8.2A AArch64 arm64) FPU+ASIMD+HALFFP] oga | ||
---|---|---|---|
行 9218: | 行 9218: | ||
2019/01/05 16: | 2019/01/05 16: | ||
- | </ | ||
- | |||
- | ++++ | ||
- | |||
- | |||
- | ==== Qualcomm Kryo 385 (Cortex-A55) (ARMv8.2A AArch64 arm64) FPU+ASIMD+HALFFP ==== | ||
- | |||
- | ++++Pixel 3 Snapdragon 845 little core Kryo 385 1.76GHz x4 ARM64 (AArch64) Android 9.0| | ||
- | |||
- | < | ||
- | ARCH: ARMv8A 3 | ||
- | FPU: AArch64 NEON | ||
- | SingleT SP max: 13.701 GFLOPS | ||
- | SingleT DP max: 6.859 GFLOPS | ||
- | MultiT | ||
- | MultiT | ||
- | CPU core: 4 | ||
- | FPHP : yes | ||
- | SIMDHP: yes | ||
- | |||
- | * FPU/NEON (single fp) | ||
- | TIME(s) | ||
- | FPU fmul (32bit x1) n8 : 0.396 | ||
- | FPU fadd (32bit x1) n8 : 0.362 | ||
- | FPU fmadd (32bit x1) n8 : | ||
- | NEON fmul.2s (32bit x2) n8 : 0.378 | ||
- | NEON fadd.2s (32bit x2) n8 : 0.361 | ||
- | NEON fmla.2s (32bit x2) n8 : 0.378 12691.6 | ||
- | NEON fmul.4s (32bit x4) n8 : 0.705 | ||
- | NEON fadd.4s (32bit x4) n8 : 0.705 | ||
- | NEON fmla.4s (32bit x4) n8 : 0.705 13619.2 | ||
- | FPU fmul (32bit x1) ns4 : | ||
- | FPU fadd (32bit x1) ns4 : | ||
- | FPU fmadd (32bit x1) ns4 : 0.688 | ||
- | NEON fmul.2s (32bit x2) ns4 : | ||
- | NEON fadd.2s (32bit x2) ns4 : | ||
- | NEON fmla.2s (32bit x2) ns4 : | ||
- | NEON fmul.4s (32bit x4) ns4 : | ||
- | NEON fadd.4s (32bit x4) ns4 : | ||
- | NEON fmla.4s (32bit x4) ns4 : | ||
- | FPU fmul (32bit x1) n1 : 0.688 | ||
- | FPU fadd (32bit x1) n1 : 0.690 | ||
- | FPU fmadd (32bit x1) n1 : | ||
- | NEON fmul.2s (32bit x2) n1 : 0.688 | ||
- | NEON fadd.2s (32bit x2) n1 : 0.688 | ||
- | NEON fmla.2s (32bit x2) n1 : 2.754 | ||
- | NEON fmul.4s (32bit x4) n1 : 0.706 | ||
- | NEON fadd.4s (32bit x4) n1 : 0.706 | ||
- | NEON fmla.4s (32bit x4) n1 : 2.757 | ||
- | NEON fmul.4s (32bit x4) n12 : | ||
- | NEON fadd.4s (32bit x4) n12 : | ||
- | NEON fmla.4s (32bit x4) n12 : | ||
- | Average | ||
- | Highest | ||
- | |||
- | |||
- | * FPU/NEON (double fp) | ||
- | TIME(s) | ||
- | FPU fmul (64bit x1) n8 : 0.377 | ||
- | FPU fadd (64bit x1) n8 : 0.381 | ||
- | FPU fmadd (64bit x1) n8 : | ||
- | NEON fmul.2d (64bit x2) n8 : 0.706 | ||
- | NEON fadd.2d (64bit x2) n8 : 0.706 | ||
- | NEON fmla.2d (64bit x2) n8 : 0.706 | ||
- | FPU fmul (64bit x1) ns4 : | ||
- | FPU fadd (64bit x1) ns4 : | ||
- | FPU fmadd (64bit x1) ns4 : 0.689 | ||
- | NEON fmul.2d (64bit x2) ns4 : | ||
- | NEON fadd.2d (64bit x2) ns4 : | ||
- | NEON fmla.2d (64bit x2) ns4 : | ||
- | FPU fmul (64bit x1) n1 : 0.689 | ||
- | FPU fadd (64bit x1) n1 : 0.689 | ||
- | FPU fmadd (64bit x1) n1 : | ||
- | NEON fmul.2d (64bit x2) n1 : 0.706 | ||
- | NEON fadd.2d (64bit x2) n1 : 0.709 | ||
- | NEON fmla.2d (64bit x2) n1 : 2.754 | ||
- | NEON fmul.2d (64bit x2) n12 : | ||
- | NEON fadd.2d (64bit x2) n12 : | ||
- | NEON fmla.2d (64bit x2) n12 : | ||
- | Average | ||
- | Highest | ||
- | |||
- | |||
- | * Matrix 4x4 | ||
- | TIME(s) | ||
- | C++ code : 0.412 | ||
- | NEON fmla.4s 128bit A : | ||
- | NEON fmla.4s 128bit B : | ||
- | Average | ||
- | Highest | ||
- | |||
- | |||
- | * FPU/NEON (single fp) multi-thread | ||
- | TIME(s) | ||
- | FPU fmul (32bit x1) n8 : 0.393 12208.3 | ||
- | FPU fadd (32bit x1) n8 : 0.363 13232.9 | ||
- | FPU fmadd (32bit x1) n8 : | ||
- | NEON fmul.2s (32bit x2) n8 : 0.383 25035.2 | ||
- | NEON fadd.2s (32bit x2) n8 : 0.362 26526.6 | ||
- | NEON fmla.2s (32bit x2) n8 : 0.384 50053.8 | ||
- | NEON fmul.4s (32bit x4) n8 : 0.705 27222.9 | ||
- | NEON fadd.4s (32bit x4) n8 : 0.720 26648.3 | ||
- | NEON fmla.4s (32bit x4) n8 : 0.708 54231.1 | ||
- | FPU fmul (32bit x1) ns4 : | ||
- | FPU fadd (32bit x1) ns4 : | ||
- | FPU fmadd (32bit x1) ns4 : 0.688 13949.1 | ||
- | NEON fmul.2s (32bit x2) ns4 : | ||
- | NEON fadd.2s (32bit x2) ns4 : | ||
- | NEON fmla.2s (32bit x2) ns4 : | ||
- | NEON fmul.4s (32bit x4) ns4 : | ||
- | NEON fadd.4s (32bit x4) ns4 : | ||
- | NEON fmla.4s (32bit x4) ns4 : | ||
- | FPU fmul (32bit x1) n1 : 0.688 | ||
- | FPU fadd (32bit x1) n1 : 0.688 | ||
- | FPU fmadd (32bit x1) n1 : | ||
- | NEON fmul.2s (32bit x2) n1 : 0.689 13937.2 | ||
- | NEON fadd.2s (32bit x2) n1 : 0.688 13955.2 | ||
- | NEON fmla.2s (32bit x2) n1 : 2.750 | ||
- | NEON fmul.4s (32bit x4) n1 : 0.704 27255.8 | ||
- | NEON fadd.4s (32bit x4) n1 : 0.706 27191.7 | ||
- | NEON fmla.4s (32bit x4) n1 : 2.764 13891.8 | ||
- | NEON fmul.4s (32bit x4) n12 : | ||
- | NEON fadd.4s (32bit x4) n12 : | ||
- | NEON fmla.4s (32bit x4) n12 : | ||
- | Average | ||
- | Highest | ||
- | |||
- | |||
- | * FPU/NEON (double fp) multi-thread | ||
- | TIME(s) | ||
- | FPU fmul (64bit x1) n8 : 0.377 12737.2 | ||
- | FPU fadd (64bit x1) n8 : 0.379 12652.6 | ||
- | FPU fmadd (64bit x1) n8 : | ||
- | NEON fmul.2d (64bit x2) n8 : 0.707 13571.8 | ||
- | NEON fadd.2d (64bit x2) n8 : 0.707 13570.5 | ||
- | NEON fmla.2d (64bit x2) n8 : 0.709 27085.1 | ||
- | FPU fmul (64bit x1) ns4 : | ||
- | FPU fadd (64bit x1) ns4 : | ||
- | FPU fmadd (64bit x1) ns4 : 0.691 13893.6 | ||
- | NEON fmul.2d (64bit x2) ns4 : | ||
- | NEON fadd.2d (64bit x2) ns4 : | ||
- | NEON fmla.2d (64bit x2) ns4 : | ||
- | FPU fmul (64bit x1) n1 : 0.695 | ||
- | FPU fadd (64bit x1) n1 : 0.687 | ||
- | FPU fmadd (64bit x1) n1 : | ||
- | NEON fmul.2d (64bit x2) n1 : 0.706 13591.6 | ||
- | NEON fadd.2d (64bit x2) n1 : 0.710 13522.7 | ||
- | NEON fmla.2d (64bit x2) n1 : 2.752 | ||
- | NEON fmul.2d (64bit x2) n12 : | ||
- | NEON fadd.2d (64bit x2) n12 : | ||
- | NEON fmla.2d (64bit x2) n12 : | ||
- | Average | ||
- | Highest | ||
- | |||
- | |||
- | * Matrix 4x4 multi-thread | ||
- | TIME(s) | ||
- | C++ code : 0.421 17033.9 | ||
- | NEON fmla.4s 128bit A : | ||
- | NEON fmla.4s 128bit B : | ||
- | Average | ||
- | Highest | ||
- | |||
- | |||
- | cpu0 1766400 300000 | ||
- | cpu1 1766400 300000 | ||
- | cpu2 1766400 300000 | ||
- | cpu3 1766400 300000 | ||
- | cpu4 2803200 825600 | ||
- | cpu5 2803200 825600 | ||
- | cpu6 2803200 825600 | ||
- | cpu7 2803200 825600 | ||
- | |||
- | Processor : AArch64 Processor rev 13 (aarch64) | ||
- | processor : 0 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x7 | ||
- | CPU part : 0x803 | ||
- | CPU revision : 12 | ||
- | |||
- | processor : 1 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x7 | ||
- | CPU part : 0x803 | ||
- | CPU revision : 12 | ||
- | |||
- | processor : 2 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x7 | ||
- | CPU part : 0x803 | ||
- | CPU revision : 12 | ||
- | |||
- | processor : 3 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x7 | ||
- | CPU part : 0x803 | ||
- | CPU revision : 12 | ||
- | |||
- | processor : 4 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x6 | ||
- | CPU part : 0x802 | ||
- | CPU revision : 13 | ||
- | |||
- | processor : 5 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x6 | ||
- | CPU part : 0x802 | ||
- | CPU revision : 13 | ||
- | |||
- | processor : 6 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x6 | ||
- | CPU part : 0x802 | ||
- | CPU revision : 13 | ||
- | |||
- | processor : 7 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x6 | ||
- | CPU part : 0x802 | ||
- | CPU revision : 13 | ||
- | |||
- | Hardware : Qualcomm Technologies, | ||
- | |||
- | Qualcomm Technologies, | ||
- | |||
- | 2019/01/05 13: | ||
</ | </ | ||
行 9729: | 行 9478: | ||
- | ==== Qualcomm Kryo 385 (Cortex-A75) (ARMv8.2A AArch64 arm64) FPU+ASIMD+HALFFP ==== | + | ==== Qualcomm Kryo 385 (Cortex-A75 |
- | ++++Pixel 3 Snapdragon 845 big core Kryo 385 2.8GHz x4 ARM64 (AArch64) Android 9.0| | + | ++++Pixel 3 Snapdragon 845 Kryo 385 2.8GHz |
< | < | ||
- | ARCH: ARMv8A 3 | + | ARCH: ARMv8.2A |
- | FPU: AArch64 NEON | + | FPU : ASIMD(AArch64 NEON) FPHP ASIMDHP |
- | SingleT SP max: 22.293 GFLOPS | + | Name: Qualcomm Technologies, |
- | SingleT DP max: 11.137 GFLOPS | + | |
- | MultiT | + | CPU Thread: 8 |
- | MultiT | + | CPU Core : |
- | CPU core: 4 | + | CPU Group : 2 |
+ | | ||
+ | Group 1: Thread= | ||
+ | NEON : yes | ||
+ | FMA : yes | ||
FPHP : yes | FPHP : yes | ||
SIMDHP: yes | SIMDHP: yes | ||
- | * FPU/NEON (single | + | Total: |
+ | SingleThread HP max: | ||
+ | SingleThread SP max: | ||
+ | SingleThread DP max: | ||
+ | MultiThread | ||
+ | MultiThread | ||
+ | MultiThread | ||
+ | |||
+ | Group 0: Thread=4 | ||
+ | SingleThread HP max: | ||
+ | SingleThread SP max: | ||
+ | SingleThread DP max: 6.851 GFLOPS | ||
+ | MultiThread | ||
+ | MultiThread | ||
+ | MultiThread | ||
+ | |||
+ | Group 1: Thread=4 | ||
+ | SingleThread HP max: | ||
+ | SingleThread SP max: | ||
+ | SingleThread DP max: | ||
+ | MultiThread | ||
+ | MultiThread | ||
+ | MultiThread | ||
+ | |||
+ | |||
+ | * Group 0: Thread=1 | ||
+ | * FPU/NEON (HP fp) | ||
TIME(s) | TIME(s) | ||
- | FPU fmul (32bit x1) n8 : 0.238 | + | FPU fmul (16bit x1) n8 : 0.320 |
- | FPU fadd (32bit x1) n8 : 0.215 | + | FPU fadd (16bit x1) n8 : 0.320 |
- | FPU fmadd (32bit x1) n8 : | + | FPU fmadd (16bit x1) n8 : |
- | NEON fmul.2s (32bit x2) n8 : 0.215 11156.0 | + | NEON fmul.4h (16bit x4) n8 : 0.319 13282.9 |
- | NEON fadd.2s (32bit x2) n8 : 0.216 11132.2 5566.1 ( | + | NEON fadd.4h (16bit x4) n8 : 0.319 13288.2 3322.0 ( |
- | NEON fmla.2s (32bit x2) n8 : 0.215 22293.3 | + | NEON fmla.4h (16bit x4) n8 : 0.321 26420.5 |
- | NEON fmul.4s (32bit x4) n8 : 0.431 11142.5 | + | NEON fmul.8h (16bit x8) n8 : 0.624 13586.0 |
- | NEON fadd.4s (32bit x4) n8 : 0.432 11111.8 | + | NEON fadd.8h (16bit x8) n8 : 0.625 13575.5 |
- | NEON fmla.4s (32bit x4) n8 : 0.431 22273.6 2784.2 ( | + | NEON fmla.8h (16bit x8) n8 : 0.624 27177.6 1698.6 ( 16 1.0) 27177.6 |
- | FPU fmul (32bit x1) ns4 : | + | FPU fmul (16bit x1) ns4 : |
- | FPU fadd (32bit x1) ns4 : | + | FPU fadd (16bit x1) ns4 : |
- | FPU fmadd (32bit x1) ns4 : 0.342 | + | FPU fmadd (16bit x1) ns4 : 0.609 |
- | NEON fmul.2s (32bit x2) ns4 : | + | NEON fmul.4h (16bit x4) ns4 : |
- | NEON fadd.2s (32bit x2) ns4 : | + | NEON fadd.4h (16bit x4) ns4 : |
- | NEON fmla.2s (32bit x2) ns4 : | + | NEON fmla.4h (16bit x4) ns4 : |
- | NEON fmul.4s (32bit x4) ns4 : | + | NEON fmul.8h (16bit x8) ns4 : |
- | NEON fadd.4s (32bit x4) ns4 : | + | NEON fadd.8h (16bit x8) ns4 : |
- | NEON fmla.4s (32bit x4) ns4 : | + | NEON fmla.8h (16bit x8) ns4 : |
- | FPU fmul (32bit x1) n1 : 0.217 | + | FPU fmul (16bit x1) n1 : 0.608 |
- | FPU fadd (32bit x1) n1 : 0.217 | + | FPU fadd (16bit x1) n1 : 0.608 |
- | FPU fmadd (32bit x1) n1 : | + | FPU fmadd (16bit x1) n1 : |
- | NEON fmul.2s (32bit x2) n1 : 0.215 11153.8 5576.9 ( | + | NEON fmul.4h (16bit x4) n1 : 0.608 6974.8 1743.7 ( |
- | NEON fadd.2s (32bit x2) n1 : 0.215 11149.0 5574.5 ( | + | NEON fadd.4h (16bit x4) n1 : 0.609 6963.0 1740.8 ( |
- | NEON fmla.2s (32bit x2) n1 : | + | NEON fmla.4h (16bit x4) n1 : |
- | NEON fmul.4s (32bit x4) n1 : 0.433 11081.5 | + | NEON fmul.8h (16bit x8) n1 : 0.623 13606.3 |
- | NEON fadd.4s (32bit x4) n1 : 0.434 11050.7 | + | NEON fadd.8h (16bit x8) n1 : 0.623 13609.6 |
- | NEON fmla.4s (32bit x4) n1 : | + | NEON fmla.8h (16bit x8) n1 : |
- | NEON fmul.4s (32bit x4) n12 : | + | NEON fmul.8h (16bit x8) n12 : |
- | NEON fadd.4s (32bit x4) n12 : | + | NEON fadd.8h (16bit x8) n12 : |
- | NEON fmla.4s (32bit x4) n12 : | + | NEON fmla.8h (16bit x8) n12 : |
- | Average | + | Average |
- | Highest | + | Highest |
- | * FPU/NEON (double | + | * Group 0: Thread=1 |
+ | * FPU/NEON (SP fp) | ||
+ | TIME(s) | ||
+ | FPU fmul (32bit x1) n8 : 0.322 | ||
+ | FPU fadd (32bit x1) n8 : 0.320 | ||
+ | FPU fmadd (32bit x1) n8 : | ||
+ | NEON fmul.2s (32bit x2) n8 : 0.320 | ||
+ | NEON fadd.2s (32bit x2) n8 : 0.319 | ||
+ | NEON fmla.2s (32bit x2) n8 : 0.319 13292.4 | ||
+ | NEON fmul.4s (32bit x4) n8 : 0.623 | ||
+ | NEON fadd.4s (32bit x4) n8 : 0.623 | ||
+ | NEON fmla.4s (32bit x4) n8 : 0.623 13611.7 | ||
+ | FPU fmul (32bit x1) ns4 : | ||
+ | FPU fadd (32bit x1) ns4 : | ||
+ | FPU fmadd (32bit x1) ns4 : 0.609 | ||
+ | NEON fmul.2s (32bit x2) ns4 : | ||
+ | NEON fadd.2s (32bit x2) ns4 : | ||
+ | NEON fmla.2s (32bit x2) ns4 : | ||
+ | NEON fmul.4s (32bit x4) ns4 : | ||
+ | NEON fadd.4s (32bit x4) ns4 : | ||
+ | NEON fmla.4s (32bit x4) ns4 : | ||
+ | FPU fmul (32bit x1) n1 : 0.608 | ||
+ | FPU fadd (32bit x1) n1 : 0.618 | ||
+ | FPU fmadd (32bit x1) n1 : | ||
+ | NEON fmul.2s (32bit x2) n1 : 0.608 | ||
+ | NEON fadd.2s (32bit x2) n1 : 0.610 | ||
+ | NEON fmla.2s (32bit x2) n1 : 2.435 | ||
+ | NEON fmul.4s (32bit x4) n1 : 0.625 | ||
+ | NEON fadd.4s (32bit x4) n1 : 0.624 | ||
+ | NEON fmla.4s (32bit x4) n1 : 2.435 | ||
+ | NEON fmul.4s (32bit x4) n12 : | ||
+ | NEON fadd.4s (32bit x4) n12 : | ||
+ | NEON fmla.4s (32bit x4) n12 : | ||
+ | Average | ||
+ | Highest | ||
+ | |||
+ | |||
+ | * Group 0: Thread=1 | ||
+ | * FPU/NEON (DP fp) | ||
TIME(s) | TIME(s) | ||
- | FPU fmul (64bit x1) n8 : 0.232 | + | FPU fmul (64bit x1) n8 : 0.335 |
- | FPU fadd (64bit x1) n8 : 0.216 | + | FPU fadd (64bit x1) n8 : 0.338 |
- | FPU fmadd (64bit x1) n8 : | + | FPU fmadd (64bit x1) n8 : |
- | NEON fmul.2d (64bit x2) n8 : 0.431 | + | NEON fmul.2d (64bit x2) n8 : 0.623 |
- | NEON fadd.2d (64bit x2) n8 : 0.431 | + | NEON fadd.2d (64bit x2) n8 : 0.624 |
- | NEON fmla.2d (64bit x2) n8 : 0.431 11136.7 | + | NEON fmla.2d (64bit x2) n8 : 0.623 6802.3 |
- | FPU fmul (64bit x1) ns4 : | + | FPU fmul (64bit x1) ns4 : |
- | FPU fadd (64bit x1) ns4 : | + | FPU fadd (64bit x1) ns4 : |
- | FPU fmadd (64bit x1) ns4 : 0.332 | + | FPU fmadd (64bit x1) ns4 : 0.609 |
- | NEON fmul.2d (64bit x2) ns4 : | + | NEON fmul.2d (64bit x2) ns4 : |
- | NEON fadd.2d (64bit x2) ns4 : | + | NEON fadd.2d (64bit x2) ns4 : |
- | NEON fmla.2d (64bit x2) ns4 : | + | NEON fmla.2d (64bit x2) ns4 : |
- | FPU fmul (64bit x1) n1 : 0.216 | + | FPU fmul (64bit x1) n1 : 0.616 |
- | FPU fadd (64bit x1) n1 : 0.218 | + | FPU fadd (64bit x1) n1 : 0.609 |
- | FPU fmadd (64bit x1) n1 : | + | FPU fmadd (64bit x1) n1 : |
- | NEON fmul.2d (64bit x2) n1 : 0.431 | + | NEON fmul.2d (64bit x2) n1 : 0.626 |
- | NEON fadd.2d (64bit x2) n1 : 0.431 | + | NEON fadd.2d (64bit x2) n1 : 0.626 |
- | NEON fmla.2d (64bit x2) n1 : | + | NEON fmla.2d (64bit x2) n1 : |
- | NEON fmul.2d (64bit x2) n12 : | + | NEON fmul.2d (64bit x2) n12 : |
- | NEON fadd.2d (64bit x2) n12 : | + | NEON fadd.2d (64bit x2) n12 : |
- | NEON fmla.2d (64bit x2) n12 : | + | NEON fmla.2d (64bit x2) n12 : |
- | Average | + | Average |
- | Highest | + | Highest |
+ | * Group 0: Thread=1 | ||
* Matrix 4x4 | * Matrix 4x4 | ||
TIME(s) | TIME(s) | ||
- | C++ code : 0.207 | + | C++ code : 0.371 |
- | NEON fmla.4s 128bit A : | + | NEON fmla.4s 128bit A : |
- | NEON fmla.4s 128bit B : | + | NEON fmla.4s 128bit B : |
- | Average | + | Average |
- | Highest | + | Highest |
- | * FPU/NEON (single | + | * Group 0: Thread=4 |
+ | * FPU/NEON (HP fp) multi-thread | ||
TIME(s) | TIME(s) | ||
- | FPU fmul (32bit x1) n8 : 0.245 19559.4 | + | FPU fmul (16bit x1) n8 : 0.321 13201.8 |
- | FPU fadd (32bit x1) n8 : 0.228 21088.1 5272.0 ( 4 1.9) 21088.1 | + | FPU fadd (16bit x1) n8 : 0.322 13146.1 3286.5 ( 4 1.9) 13146.1 |
- | FPU fmadd (32bit x1) n8 : | + | FPU fmadd (16bit x1) n8 : |
- | NEON fmul.2s (32bit x2) n8 : 0.228 42187.4 | + | NEON fmul.4h (16bit x4) n8 : 0.321 52891.3 |
- | NEON fadd.2s (32bit x2) n8 : 0.228 42183.3 5272.9 ( | + | NEON fadd.4h (16bit x4) n8 : 0.320 52954.3 3309.6 ( 16 1.9) 52954.3 |
- | NEON fmla.2s (32bit x2) n8 : 0.228 84357.8 | + | NEON fmla.4h (16bit x4) n8 : 0.323 |
- | NEON fmul.4s (32bit x4) n8 : 0.455 42182.2 2636.4 ( 16 0.9) 42182.2 | + | NEON fmul.8h (16bit x8) n8 : 0.624 54394.2 1699.8 ( 32 1.0) 54394.2 |
- | NEON fadd.4s (32bit x4) n8 : 0.455 42184.0 | + | NEON fadd.8h (16bit x8) n8 : 0.626 54212.1 |
- | NEON fmla.4s (32bit x4) n8 : 0.455 84367.8 | + | NEON fmla.8h (16bit x8) n8 : 0.672 |
- | FPU fmul (32bit x1) ns4 : | + | FPU fmul (16bit x1) ns4 : |
- | FPU fadd (32bit x1) ns4 : | + | FPU fadd (16bit x1) ns4 : |
- | FPU fmadd (32bit x1) ns4 : 0.365 26334.8 | + | FPU fmadd (16bit x1) ns4 : 0.646 13120.3 |
- | NEON fmul.2s (32bit x2) ns4 : | + | NEON fmul.4h (16bit x4) ns4 : |
- | NEON fadd.2s (32bit x2) ns4 : | + | NEON fadd.4h (16bit x4) ns4 : |
- | NEON fmla.2s (32bit x2) ns4 : | + | NEON fmla.4h (16bit x4) ns4 : |
- | NEON fmul.4s (32bit x4) ns4 : | + | NEON fmul.8h (16bit x8) ns4 : |
- | NEON fadd.4s (32bit x4) ns4 : | + | NEON fadd.8h (16bit x8) ns4 : |
- | NEON fmla.4s (32bit x4) ns4 : | + | NEON fmla.8h (16bit x8) ns4 : |
- | FPU fmul (32bit x1) n1 : 0.228 21087.6 | + | FPU fmul (16bit x1) n1 : 0.624 6789.1 |
- | FPU fadd (32bit x1) n1 : 0.228 21092.9 | + | FPU fadd (16bit x1) n1 : 0.621 6822.1 |
- | FPU fmadd (32bit x1) n1 : | + | FPU fmadd (16bit x1) n1 : |
- | NEON fmul.2s (32bit x2) n1 : 0.228 42187.2 | + | NEON fmul.4h (16bit x4) n1 : 0.618 27451.7 |
- | NEON fadd.2s (32bit x2) n1 : 0.228 42192.6 | + | NEON fadd.4h (16bit x4) n1 : 0.612 27697.2 |
- | NEON fmla.2s (32bit x2) n1 : | + | NEON fmla.4h (16bit x4) n1 : |
- | NEON fmul.4s (32bit x4) n1 : 0.455 42182.2 2636.4 ( 16 0.9) 42182.2 | + | NEON fmul.8h (16bit x8) n1 : 0.643 52731.2 1647.9 ( 32 0.9) 52731.2 |
- | NEON fadd.4s (32bit x4) n1 : 0.455 42180.2 | + | NEON fadd.8h (16bit x8) n1 : 0.644 52629.8 |
- | NEON fmla.4s (32bit x4) n1 : | + | NEON fmla.8h (16bit x8) n1 : |
- | NEON fmul.4s (32bit x4) n12 : | + | NEON fmul.8h (16bit x8) n12 : |
- | NEON fadd.4s (32bit x4) n12 : | + | NEON fadd.8h (16bit x8) n12 : |
- | NEON fmla.4s (32bit x4) n12 : | + | NEON fmla.8h (16bit x8) n12 : |
- | Average | + | Average |
- | Highest | + | Highest |
- | * FPU/NEON (double | + | * Group 0: Thread=4 |
+ | * FPU/NEON (SP fp) multi-thread | ||
TIME(s) | TIME(s) | ||
- | FPU fmul (64bit x1) n8 : 0.248 19330.2 | + | FPU fmul (32bit x1) n8 : 0.321 13217.0 |
- | FPU fadd (64bit x1) n8 : 0.228 21086.2 | + | FPU fadd (32bit x1) n8 : 0.329 12886.4 |
- | FPU fmadd (64bit x1) n8 : | + | FPU fmadd (32bit x1) n8 : |
- | NEON fmul.2d (64bit x2) n8 : 0.455 21087.8 | + | NEON fmul.2s (32bit x2) n8 : 0.326 26045.3 |
- | NEON fadd.2d (64bit x2) n8 : 0.455 21090.8 2636.4 ( 8 0.9) 21090.8 | + | NEON fadd.2s (32bit x2) n8 : 0.326 25979.8 3247.5 ( 8 1.8) 25979.8 |
- | NEON fmla.2d (64bit x2) n8 : 0.455 42183.3 2636.5 ( 16 0.9) 42183.3 | + | NEON fmla.2s (32bit x2) n8 : 0.327 51831.0 |
- | FPU fmul (64bit x1) ns4 : | + | NEON fmul.4s (32bit x4) n8 : 0.649 26135.3 1633.5 ( 16 0.9) 26135.3 |
- | FPU fadd (64bit x1) ns4 : | + | NEON fadd.4s (32bit x4) n8 : 0.641 26468.0 |
- | FPU fmadd (64bit x1) ns4 : 0.350 27445.9 | + | NEON fmla.4s (32bit x4) n8 : 0.643 52712.0 |
- | NEON fmul.2d (64bit x2) ns4 : | + | FPU fmul (32bit x1) ns4 : |
- | NEON fadd.2d (64bit x2) ns4 : | + | FPU fadd (32bit x1) ns4 : |
- | NEON fmla.2d (64bit x2) ns4 : | + | FPU fmadd (32bit x1) ns4 : 0.614 13814.8 |
- | FPU fmul (64bit x1) n1 : 0.228 21091.8 | + | NEON fmul.2s (32bit x2) ns4 : |
- | FPU fadd (64bit x1) n1 : 0.228 21087.8 | + | NEON fadd.2s (32bit x2) ns4 : |
- | FPU fmadd (64bit x1) n1 : | + | NEON fmla.2s (32bit x2) ns4 : |
- | NEON fmul.2d (64bit x2) n1 : 0.455 21090.0 | + | NEON fmul.4s (32bit x4) ns4 : |
- | NEON fadd.2d (64bit x2) n1 : 0.455 21085.6 | + | NEON fadd.4s (32bit x4) ns4 |
- | NEON fmla.2d (64bit x2) n1 : | + | NEON fmla.4s (32bit x4) ns4 : |
- | NEON fmul.2d (64bit x2) n12 : | + | FPU fmul (32bit x1) n1 : 0.615 6888.6 |
- | NEON fadd.2d (64bit x2) n12 : | + | FPU fadd (32bit x1) n1 : 0.619 6848.6 |
- | NEON fmla.2d (64bit x2) n12 : | + | FPU fmadd (32bit x1) n1 : |
- | Average | + | NEON fmul.2s (32bit x2) n1 : 0.614 13801.4 |
- | Highest | + | NEON fadd.2s (32bit x2) n1 : 0.619 13707.1 |
+ | NEON fmla.2s (32bit x2) n1 : 2.510 | ||
+ | NEON fmul.4s (32bit x4) n1 : 0.647 26189.5 | ||
+ | NEON fadd.4s (32bit x4) n1 : 0.660 25699.9 | ||
+ | NEON fmla.4s (32bit x4) n1 : | ||
+ | NEON fmul.4s (32bit x4) n12 : | ||
+ | NEON fadd.4s (32bit x4) n12 : | ||
+ | NEON fmla.4s (32bit x4) n12 : | ||
+ | Average | ||
+ | Highest | ||
+ | * Group 0: Thread=4 | ||
+ | * FPU/NEON (DP fp) multi-thread | ||
+ | TIME(s) | ||
+ | FPU fmul (64bit x1) n8 : 0.354 11990.3 | ||
+ | FPU fadd (64bit x1) n8 : 0.358 11843.1 | ||
+ | FPU fmadd (64bit x1) n8 : | ||
+ | NEON fmul.2d (64bit x2) n8 : 0.649 13059.9 | ||
+ | NEON fadd.2d (64bit x2) n8 : 0.663 12789.1 | ||
+ | NEON fmla.2d (64bit x2) n8 : 0.651 26052.7 | ||
+ | FPU fmul (64bit x1) ns4 : | ||
+ | FPU fadd (64bit x1) ns4 : | ||
+ | FPU fmadd (64bit x1) ns4 : 0.645 13152.3 | ||
+ | NEON fmul.2d (64bit x2) ns4 : | ||
+ | NEON fadd.2d (64bit x2) ns4 : | ||
+ | NEON fmla.2d (64bit x2) ns4 : | ||
+ | FPU fmul (64bit x1) n1 : 0.642 | ||
+ | FPU fadd (64bit x1) n1 : 0.656 | ||
+ | FPU fmadd (64bit x1) n1 : | ||
+ | NEON fmul.2d (64bit x2) n1 : 0.661 12823.2 | ||
+ | NEON fadd.2d (64bit x2) n1 : 0.655 12936.4 | ||
+ | NEON fmla.2d (64bit x2) n1 : 2.529 | ||
+ | NEON fmul.2d (64bit x2) n12 : | ||
+ | NEON fadd.2d (64bit x2) n12 : | ||
+ | NEON fmla.2d (64bit x2) n12 : | ||
+ | Average | ||
+ | Highest | ||
+ | |||
+ | |||
+ | * Group 0: Thread=4 | ||
* Matrix 4x4 multi-thread | * Matrix 4x4 multi-thread | ||
TIME(s) | TIME(s) | ||
- | C++ code : 0.220 32563.2 | + | C++ code : 0.385 16451.8 |
- | NEON fmla.4s 128bit A : | + | NEON fmla.4s 128bit A : |
- | NEON fmla.4s 128bit B : | + | NEON fmla.4s 128bit B : |
- | Average | + | Average |
- | Highest | + | Highest |
- | cpu0 1766400 300000 | + | * Group 1: Thread=1 |
- | cpu1 1766400 300000 | + | * FPU/NEON (HP fp) |
- | cpu2 1766400 300000 | + | |
- | cpu3 1766400 300000 | + | FPU fmul (16bit x1) n8 : 0.304 |
- | cpu4 2803200 825600 | + | FPU fadd (16bit x1) n8 : 0.307 |
- | cpu5 2803200 825600 | + | FPU fmadd (16bit x1) n8 : |
- | cpu6 2803200 825600 | + | NEON fmul.4h (16bit x4) n8 : 0.304 22113.0 |
- | cpu7 2803200 825600 | + | NEON fadd.4h (16bit x4) n8 : 0.307 21906.8 |
+ | NEON fmla.4h (16bit x4) n8 : 0.304 44248.4 | ||
+ | NEON fmul.8h (16bit x8) n8 : 0.609 22087.1 | ||
+ | NEON fadd.8h (16bit x8) n8 : 0.611 22008.4 | ||
+ | NEON fmla.8h (16bit x8) n8 : 0.610 44087.5 | ||
+ | FPU fmul (16bit x1) ns4 : | ||
+ | FPU fadd (16bit x1) ns4 : | ||
+ | FPU fmadd (16bit x1) ns4 : 0.491 | ||
+ | NEON fmul.4h (16bit x4) ns4 : | ||
+ | NEON fadd.4h (16bit x4) ns4 : | ||
+ | NEON fmla.4h (16bit x4) ns4 : | ||
+ | NEON fmul.8h (16bit x8) ns4 : | ||
+ | NEON fadd.8h (16bit x8) ns4 : | ||
+ | NEON fmla.8h (16bit x8) ns4 : | ||
+ | FPU fmul (16bit x1) n1 : 0.306 | ||
+ | FPU fadd (16bit x1) n1 : 0.309 | ||
+ | FPU fmadd (16bit x1) n1 : | ||
+ | NEON fmul.4h (16bit x4) n1 : 0.308 21808.3 | ||
+ | NEON fadd.4h (16bit x4) n1 : 0.308 21847.4 | ||
+ | NEON fmla.4h (16bit x4) n1 : 1.828 | ||
+ | NEON fmul.8h (16bit x8) n1 : 0.610 22069.8 | ||
+ | NEON fadd.8h (16bit x8) n1 : 0.618 21756.4 | ||
+ | NEON fmla.8h (16bit x8) n1 : 1.825 14748.5 | ||
+ | NEON fmul.8h (16bit x8) n12 : | ||
+ | NEON fadd.8h (16bit x8) n12 : | ||
+ | NEON fmla.8h (16bit x8) n12 : | ||
+ | Average | ||
+ | Highest | ||
- | Processor : AArch64 Processor rev 13 (aarch64) | ||
- | processor : 0 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x7 | ||
- | CPU part : 0x803 | ||
- | CPU revision : 12 | ||
- | processor : 1 | + | * Group 1: |
- | BogoMIPS : 38.00 | + | * FPU/NEON (SP fp) |
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | + | TIME(s) |
- | CPU implementer : 0x51 | + | FPU fmul (32bit x1) n8 |
- | CPU architecture: 8 | + | FPU fadd (32bit x1) n8 |
- | CPU variant : 0x7 | + | FPU fmadd (32bit x1) n8 : |
- | CPU part : 0x803 | + | NEON fmul.2s (32bit x2) n8 |
- | CPU revision : 12 | + | NEON fadd.2s (32bit x2) n8 : 0.306 10988.1 |
+ | NEON fmla.2s (32bit x2) n8 : 0.305 22037.4 | ||
+ | NEON fmul.4s (32bit x4) n8 : 0.609 11055.3 | ||
+ | NEON fadd.4s (32bit x4) n8 | ||
+ | NEON fmla.4s (32bit x4) n8 | ||
+ | FPU fmul (32bit x1) ns4 : | ||
+ | FPU fadd (32bit x1) ns4 : | ||
+ | FPU fmadd (32bit x1) ns4 : 0.485 | ||
+ | NEON fmul.2s (32bit x2) ns4 : | ||
+ | NEON fadd.2s (32bit x2) ns4 : | ||
+ | NEON fmla.2s (32bit x2) ns4 : | ||
+ | NEON fmul.4s (32bit x4) ns4 : | ||
+ | NEON fadd.4s (32bit x4) ns4 : | ||
+ | NEON fmla.4s (32bit x4) ns4 : | ||
+ | FPU fmul (32bit x1) n1 : 0.308 | ||
+ | FPU fadd (32bit x1) n1 : 0.303 | ||
+ | FPU fmadd (32bit x1) n1 : | ||
+ | NEON fmul.2s (32bit x2) n1 : 0.304 11075.5 | ||
+ | NEON fadd.2s (32bit x2) n1 : 0.306 10996.9 | ||
+ | NEON fmla.2s (32bit x2) n1 : 1.827 | ||
+ | NEON fmul.4s (32bit x4) n1 : 0.616 10919.4 | ||
+ | NEON fadd.4s (32bit x4) n1 : 0.610 11034.1 | ||
+ | NEON fmla.4s (32bit x4) n1 : 1.823 | ||
+ | NEON fmul.4s (32bit x4) n12 : | ||
+ | NEON fadd.4s (32bit x4) n12 : | ||
+ | NEON fmla.4s (32bit x4) n12 : | ||
+ | Average | ||
+ | Highest | ||
- | processor : 2 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x7 | ||
- | CPU part : 0x803 | ||
- | CPU revision : 12 | ||
- | processor : 3 | + | * Group 1: |
- | BogoMIPS : 38.00 | + | * FPU/NEON (DP fp) |
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | + | TIME(s) |
- | CPU implementer : 0x51 | + | FPU fmul (64bit x1) n8 : 0.302 |
- | CPU architecture: 8 | + | FPU fadd (64bit x1) n8 : 0.305 |
- | CPU variant : 0x7 | + | FPU fmadd (64bit x1) n8 : 0.384 |
- | CPU part : 0x803 | + | NEON fmul.2d (64bit x2) n8 |
- | CPU revision : 12 | + | NEON fadd.2d (64bit x2) n8 |
+ | NEON fmla.2d (64bit x2) n8 | ||
+ | FPU fmul (64bit x1) ns4 : | ||
+ | FPU fadd (64bit x1) ns4 : | ||
+ | FPU fmadd (64bit x1) ns4 | ||
+ | NEON fmul.2d (64bit x2) ns4 : | ||
+ | NEON fadd.2d (64bit x2) ns4 : | ||
+ | NEON fmla.2d (64bit x2) ns4 : | ||
+ | FPU fmul (64bit x1) n1 : 0.303 | ||
+ | FPU fadd (64bit x1) n1 : 0.306 | ||
+ | FPU fmadd (64bit x1) n1 : | ||
+ | NEON fmul.2d (64bit x2) n1 : 0.611 | ||
+ | NEON fadd.2d (64bit x2) n1 : 0.610 | ||
+ | NEON fmla.2d (64bit x2) n1 : 1.823 | ||
+ | NEON fmul.2d (64bit x2) n12 : | ||
+ | NEON fadd.2d (64bit x2) n12 : | ||
+ | NEON fmla.2d (64bit x2) n12 : | ||
+ | Average | ||
+ | Highest | ||
- | processor : 4 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x6 | ||
- | CPU part : 0x802 | ||
- | CPU revision : 13 | ||
- | processor : 5 | + | * Group 1: |
- | BogoMIPS : 38.00 | + | * Matrix 4x4 |
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | + | |
- | CPU implementer : | + | C++ code |
- | CPU architecture: 8 | + | NEON fmla.4s 128bit A : |
- | CPU variant : 0x6 | + | NEON fmla.4s 128bit B : |
- | CPU part : 0x802 | + | Average |
- | CPU revision : 13 | + | Highest |
- | processor : 6 | ||
- | BogoMIPS : 38.00 | ||
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | ||
- | CPU implementer : | ||
- | CPU architecture: | ||
- | CPU variant : 0x6 | ||
- | CPU part : 0x802 | ||
- | CPU revision : 13 | ||
- | processor : 7 | + | * Group 1: |
- | BogoMIPS : 38.00 | + | * FPU/NEON (HP fp) multi-thread |
- | Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp | + | TIME(s) |
- | CPU implementer : 0x51 | + | FPU fmul (16bit x1) n8 : 0.319 21091.6 |
- | CPU architecture: 8 | + | FPU fadd (16bit x1) n8 : 0.319 21093.3 |
- | CPU variant : 0x6 | + | FPU fmadd (16bit x1) n8 : |
- | CPU part : 0x802 | + | NEON fmul.4h (16bit x4) n8 : 0.319 84378.9 |
- | CPU revision : 13 | + | NEON fadd.4h (16bit x4) n8 |
+ | NEON fmla.4h (16bit x4) n8 | ||
+ | NEON fmul.8h (16bit x8) n8 | ||
+ | NEON fadd.8h (16bit x8) n8 | ||
+ | NEON fmla.8h (16bit x8) n8 | ||
+ | FPU fmul (16bit x1) ns4 : | ||
+ | FPU fadd (16bit x1) ns4 : | ||
+ | FPU fmadd (16bit x1) ns4 : 0.513 26236.3 | ||
+ | NEON fmul.4h (16bit x4) ns4 : | ||
+ | NEON fadd.4h (16bit x4) ns4 : | ||
+ | NEON fmla.4h (16bit x4) ns4 : | ||
+ | NEON fmul.8h (16bit x8) ns4 : | ||
+ | NEON fadd.8h (16bit x8) ns4 : | ||
+ | NEON fmla.8h (16bit x8) ns4 : | ||
+ | FPU fmul (16bit x1) n1 : 0.319 21087.0 | ||
+ | FPU fadd (16bit x1) n1 : 0.319 21092.7 | ||
+ | FPU fmadd (16bit x1) n1 : | ||
+ | NEON fmul.4h (16bit x4) n1 : 0.319 84365.2 | ||
+ | NEON fadd.4h (16bit x4) n1 : 0.319 84375.2 | ||
+ | NEON fmla.4h (16bit x4) n1 : 1.914 28124.4 | ||
+ | NEON fmul.8h (16bit x8) n1 : 0.638 84368.6 | ||
+ | NEON fadd.8h (16bit x8) n1 : 0.638 84377.3 | ||
+ | NEON fmla.8h (16bit x8) n1 : 1.914 56247.7 | ||
+ | NEON fmul.8h (16bit x8) n12 : | ||
+ | NEON fadd.8h (16bit x8) n12 : | ||
+ | NEON fmla.8h (16bit x8) n12 : | ||
+ | Average | ||
+ | Highest | ||
- | Hardware : Qualcomm Technologies, | ||
- | Qualcomm Technologies, | + | * Group 1: Thread=4 |
+ | * FPU/NEON (SP fp) multi-thread | ||
+ | TIME(s) | ||
+ | FPU fmul (32bit x1) n8 : 0.319 21086.7 | ||
+ | FPU fadd (32bit x1) n8 : 0.319 21087.6 | ||
+ | FPU fmadd (32bit x1) n8 : | ||
+ | NEON fmul.2s (32bit x2) n8 : 0.319 42174.9 | ||
+ | NEON fadd.2s (32bit x2) n8 : 0.319 42174.9 | ||
+ | NEON fmla.2s (32bit x2) n8 : 0.319 84342.4 | ||
+ | NEON fmul.4s (32bit x4) n8 : 0.638 42179.2 | ||
+ | NEON fadd.4s (32bit x4) n8 : 0.638 42174.4 | ||
+ | NEON fmla.4s (32bit x4) n8 : 0.638 84354.6 | ||
+ | FPU fmul (32bit x1) ns4 : | ||
+ | FPU fadd (32bit x1) ns4 : | ||
+ | FPU fmadd (32bit x1) ns4 : 0.506 26601.7 | ||
+ | NEON fmul.2s (32bit x2) ns4 : | ||
+ | NEON fadd.2s (32bit x2) ns4 : | ||
+ | NEON fmla.2s (32bit x2) ns4 : | ||
+ | NEON fmul.4s (32bit x4) ns4 : | ||
+ | NEON fadd.4s (32bit x4) ns4 : | ||
+ | NEON fmla.4s (32bit x4) ns4 : | ||
+ | FPU fmul (32bit x1) n1 : 0.319 21089.6 | ||
+ | FPU fadd (32bit x1) n1 : 0.319 21087.5 | ||
+ | FPU fmadd (32bit x1) n1 : | ||
+ | NEON fmul.2s (32bit x2) n1 : 0.319 42178.2 | ||
+ | NEON fadd.2s (32bit x2) n1 : 0.319 42181.3 | ||
+ | NEON fmla.2s (32bit x2) n1 : 1.914 14060.8 | ||
+ | NEON fmul.4s (32bit x4) n1 : 0.638 42178.1 | ||
+ | NEON fadd.4s (32bit x4) n1 : 0.638 42178.8 | ||
+ | NEON fmla.4s (32bit x4) n1 : 1.914 28124.7 | ||
+ | NEON fmul.4s (32bit x4) n12 : | ||
+ | NEON fadd.4s (32bit x4) n12 : | ||
+ | NEON fmla.4s (32bit x4) n12 : | ||
+ | Average | ||
+ | Highest | ||
+ | |||
+ | |||
+ | * Group 1: Thread=4 | ||
+ | * FPU/NEON (DP fp) multi-thread | ||
+ | TIME(s) | ||
+ | FPU fmul (64bit x1) n8 : 0.319 21091.0 | ||
+ | FPU fadd (64bit x1) n8 : 0.319 21089.9 | ||
+ | FPU fmadd (64bit x1) n8 : | ||
+ | NEON fmul.2d (64bit x2) n8 : 0.638 21084.7 | ||
+ | NEON fadd.2d (64bit x2) n8 : 0.638 21092.6 | ||
+ | NEON fmla.2d (64bit x2) n8 : 0.649 41472.2 | ||
+ | FPU fmul (64bit x1) ns4 : | ||
+ | FPU fadd (64bit x1) ns4 : | ||
+ | FPU fmadd (64bit x1) ns4 : 0.504 26674.3 | ||
+ | NEON fmul.2d (64bit x2) ns4 : | ||
+ | NEON fadd.2d (64bit x2) ns4 : | ||
+ | NEON fmla.2d (64bit x2) ns4 : | ||
+ | FPU fmul (64bit x1) n1 : 0.324 20789.9 | ||
+ | FPU fadd (64bit x1) n1 : 0.329 20459.1 | ||
+ | FPU fmadd (64bit x1) n1 : | ||
+ | NEON fmul.2d (64bit x2) n1 : 0.638 21089.3 | ||
+ | NEON fadd.2d (64bit x2) n1 : 0.638 21088.4 | ||
+ | NEON fmla.2d (64bit x2) n1 : 1.914 14062.3 | ||
+ | NEON fmul.2d (64bit x2) n12 : | ||
+ | NEON fadd.2d (64bit x2) n12 : | ||
+ | NEON fmla.2d (64bit x2) n12 : | ||
+ | Average | ||
+ | Highest | ||
+ | |||
+ | |||
+ | * Group 1: Thread=4 | ||
+ | * Matrix 4x4 multi-thread | ||
+ | TIME(s) | ||
+ | C++ code : 0.327 30720.8 | ||
+ | NEON fmla.4s 128bit A : | ||
+ | NEON fmla.4s 128bit B : | ||
+ | Average | ||
+ | Highest | ||
- | 2019/01/05 13: | ||
</ | </ | ||
opengl/vfpbenchlog.txt · 最終更新: 2020/12/30 23:46 by oga