英文:
OpenJDK Panama Vector API jdk.incubator.vector not giving improved results for Vector dot product
问题
以下是翻译好的部分：
我正在测试 OpenJDK Panama 向量 API（jdk.incubator.vector），并在 Amazon c5.4xlarge 实例上执行了测试。但在每种情况下，简单展开的向量点积操作的性能都优于向量 API 代码。
我的问题是：
为什么我无法获得像 Richard Startin 的博客 中所示的性能提升？同样的性能改进也在 这个会议演讲 中由英特尔的人讨论过。缺少了什么？
JMH 基准测试结果：
基准测试 (size) Mode Cnt Score Error Units
FloatVector256DotProduct.unrolled 1048576 thrpt 25 2440.726 ? 21.372 ops/s
FloatVector256DotProduct.vanilla 1048576 thrpt 25 807.721 ? 0.084 ops/s
FloatVector256DotProduct.vector 1048576 thrpt 25 909.977 ? 6.542 ops/s
FloatVector256DotProduct.vectorUnrolled 1048576 thrpt 25 887.422 ? 5.557 ops/s
FloatVector256DotProduct.vectorfma 1048576 thrpt 25 916.955 ? 4.652 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 25 877.569 ? 1.451 ops/s
JavaDocExample.simpleMultiply 1048576 thrpt 25 2096.782 ? 6.778 ops/s
JavaDocExample.simpleMultiplyUnrolled 1048576 thrpt 25 1627.320 ? 6.824 ops/s
JavaDocExample.vectorMultiply 1048576 thrpt 25 2102.654 ? 11.637 ops/s
AWS 实例类型：c5.4xlarge
CPU 详细信息：
$ lscpu
架构： x86_64
CPU 操作模式： 32 位、64 位
字节顺序： 小端
CPU 数量： 16
在线 CPU 列表：0-15
每个核的线程数：2
每个插槽的核心数：8
插槽数量： 1
NUMA 节点数量：1
供应商 ID： GenuineIntel
CPU 家族： 6
型号： 85
型号名称： Intel(R) Xeon(R) Platinum 8124M CPU @ 3.00GHz
Stepping： 4
CPU MHz： 3404.362
BogoMIPS： 5999.99
Hypervisor 供应商：KVM
虚拟化类型： 完全虚拟化
L1d 缓存： 32K
L1i 缓存： 32K
L2 缓存： 1024K
L3 缓存： 25344K
NUMA 节点0 的 CPU：0-15
标志： fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves ida arat pku ospke
代码片段。 请参阅此 GitHub 仓库中的完整代码。
JavaDocExample：这是在 OpenJDK 的 vectorIntrinsic 分支的 Java 文档中共享的代码。
@Benchmark
public void simpleMultiplyUnrolled() {
for (int i = 0; i < size; i += 8) {
c[i] = a[i] * b[i];
c[i + 1] = a[i + 1] * b[i + 1];
c[i + 2] = a[i + 2] * b[i + 2];
c[i + 3] = a[i + 3] * b[i + 3];
c[i + 4] = a[i + 4] * b[i + 4];
c[i + 5] = a[i + 5] * b[i + 5];
c[i + 6] = a[i + 6] * b[i + 6];
c[i + 7] = a[i + 7] * b[i + 7];
}
}
// 其他方法的代码类似，省略
FloatVector256DotProduct：这段代码是从 Richard Startin 的博客 转载的。感谢 Richard 提供了深入的博客。
@Benchmark
public float vectorfma() {
// 代码类似，省略
}
// 其他方法的代码类似，省略
编译和使用 OpenJDK Panama dev vectorIntrinsic 分支的过程，如 此 StackOverflow 问题 中所示。
hg clone http://hg.openjdk.java.net/panama/dev/
cd dev/
hg checkout vectorIntrinsics
hg branch vectorIntrinsics
bash
<details>
<summary>英文:</summary>
I am testing [OpenJDK Panama Vector API](https://openjdk.java.net/jeps/338) jdk.incubator.vector and I performed tests on amazon c5.4xlarge instance. But in every case simple unrolled vector dot product is out performing the Vector API code.
*My Question* is :
Why am I not able to get the performance boost as shown in [Richard Startin's blog](https://richardstartin.github.io/posts/vector-api-dot-product). The same performance improvement is also discussed in [this conference meetup](https://www.youtube.com/watch?v=YA9wfTrBr_4) by Intel people. What is missing?
JMH benchmark test results :
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.unrolled 1048576 thrpt 25 2440.726 ? 21.372 ops/s
FloatVector256DotProduct.vanilla 1048576 thrpt 25 807.721 ? 0.084 ops/s
FloatVector256DotProduct.vector 1048576 thrpt 25 909.977 ? 6.542 ops/s
FloatVector256DotProduct.vectorUnrolled 1048576 thrpt 25 887.422 ? 5.557 ops/s
FloatVector256DotProduct.vectorfma 1048576 thrpt 25 916.955 ? 4.652 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 25 877.569 ? 1.451 ops/s
JavaDocExample.simpleMultiply 1048576 thrpt 25 2096.782 ? 6.778 ops/s
JavaDocExample.simpleMultiplyUnrolled 1048576 thrpt 25 1627.320 ? 6.824 ops/s
JavaDocExample.vectorMultiply 1048576 thrpt 25 2102.654 ? 11.637 ops/s
AWS instance type : ``c5.4xlarge``
CPU details :
$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Xeon(R) Platinum 8124M CPU @ 3.00GHz
Stepping: 4
CPU MHz: 3404.362
BogoMIPS: 5999.99
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 32K
L1i cache: 32K
L2 cache: 1024K
L3 cache: 25344K
NUMA node0 CPU(s): 0-15
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves ida arat pku ospke
**Code snippets.** Please see complete code in [this github repo](https://github.com/nitirajrathore/java-vectorization)
JavaDocExample : This is shared in the java doc of vectorIntrinsic branch of OpenJDK.
@Benchmark
public void simpleMultiplyUnrolled() {
for (int i = 0; i < size; i += 8) {
c[i] = a[i] * b[i];
c[i + 1] = a[i + 1] * b[i + 1];
c[i + 2] = a[i + 2] * b[i + 2];
c[i + 3] = a[i + 3] * b[i + 3];
c[i + 4] = a[i + 4] * b[i + 4];
c[i + 5] = a[i + 5] * b[i + 5];
c[i + 6] = a[i + 6] * b[i + 6];
c[i + 7] = a[i + 7] * b[i + 7];
}
}
@Benchmark
public void simpleMultiply() {
for (int i = 0; i < size; i++) {
c[i] = a[i] * b[i];
}
}
@Benchmark
public void vectorMultiply() {
int i = 0;
// It is assumed array arguments are of the same size
for (; i < SPECIES.loopBound(a.length); i += SPECIES.length()) {
FloatVector va = FloatVector.fromArray(SPECIES, a, i);
FloatVector vb = FloatVector.fromArray(SPECIES, b, i);
FloatVector vc = va.mul(vb);
vc.intoArray(c, i);
}
for (; i < a.length; i++) {
c[i] = a[i] * b[i];
}
}
FloatVector256DotProduct : this code is shamelessly copied from [Richard Startin's blog](https://richardstartin.github.io/posts/vector-api-dot-product). Thanks Richard for insightful blogs.
@Benchmark
public float vectorfma() {
var sum = FloatVector.zero(F256);
for (int i = 0; i < size; i += F256.length()) {
var l = FloatVector.fromArray(F256, left, i);
var r = FloatVector.fromArray(F256, right, i);
sum = l.fma(r, sum);
}
return sum.reduceLanes(ADD);
}
@Benchmark
public float vectorfmaUnrolled() {
var sum1 = FloatVector.zero(F256);
var sum2 = FloatVector.zero(F256);
var sum3 = FloatVector.zero(F256);
var sum4 = FloatVector.zero(F256);
int width = F256.length();
for (int i = 0; i < size; i += width * 4) {
sum1 = FloatVector.fromArray(F256, left, i).fma(FloatVector.fromArray(F256, right, i), sum1);
sum2 = FloatVector.fromArray(F256, left, i + width).fma(FloatVector.fromArray(F256, right, i + width), sum2);
sum3 = FloatVector.fromArray(F256, left, i + width * 2).fma(FloatVector.fromArray(F256, right, i + width * 2), sum3);
sum4 = FloatVector.fromArray(F256, left, i + width * 3).fma(FloatVector.fromArray(F256, right, i + width * 3), sum4);
}
return sum1.add(sum2).add(sum3).add(sum4).reduceLanes(ADD);
}
@Benchmark
public float vector() {
var sum = FloatVector.zero(F256);
for (int i = 0; i < size; i += F256.length()) {
var l = FloatVector.fromArray(F256, left, i);
var r = FloatVector.fromArray(F256, right, i);
sum = l.mul(r).add(sum);
}
return sum.reduceLanes(ADD);
}
@Benchmark
public float vectorUnrolled() {
var sum1 = FloatVector.zero(F256);
var sum2 = FloatVector.zero(F256);
var sum3 = FloatVector.zero(F256);
var sum4 = FloatVector.zero(F256);
int width = F256.length();
for (int i = 0; i < size; i += width * 4) {
sum1 = FloatVector.fromArray(F256, left, i).mul(FloatVector.fromArray(F256, right, i)).add(sum1);
sum2 = FloatVector.fromArray(F256, left, i + width).mul(FloatVector.fromArray(F256, right, i + width)).add(sum2);
sum3 = FloatVector.fromArray(F256, left, i + width * 2).mul(FloatVector.fromArray(F256, right, i + width * 2)).add(sum3);
sum4 = FloatVector.fromArray(F256, left, i + width * 3).mul(FloatVector.fromArray(F256, right, i + width * 3)).add(sum4);
}
return sum1.add(sum2).add(sum3).add(sum4).reduceLanes(ADD);
}
@Benchmark
public float unrolled() {
float s0 = 0f;
float s1 = 0f;
float s2 = 0f;
float s3 = 0f;
float s4 = 0f;
float s5 = 0f;
float s6 = 0f;
float s7 = 0f;
for (int i = 0; i < size; i += 8) {
s0 = Math.fma(left[i + 0], right[i + 0], s0);
s1 = Math.fma(left[i + 1], right[i + 1], s1);
s2 = Math.fma(left[i + 2], right[i + 2], s2);
s3 = Math.fma(left[i + 3], right[i + 3], s3);
s4 = Math.fma(left[i + 4], right[i + 4], s4);
s5 = Math.fma(left[i + 5], right[i + 5], s5);
s6 = Math.fma(left[i + 6], right[i + 6], s6);
s7 = Math.fma(left[i + 7], right[i + 7], s7);
}
return s0 + s1 + s2 + s3 + s4 + s5 + s6 + s7;
}
@Benchmark
public float vanilla() {
float sum = 0f;
for (int i = 0; i < size; ++i) {
sum = Math.fma(left[i], right[i], sum);
}
return sum;
}
Process followed to compile and use the OpenJDK Panama dev vectorIntrinsic branch as showed in [this SO question](https://stackoverflow.com/questions/54973158/cant-use-jdk-incubator-vector-classes-in-biginteger)
hg clone http://hg.openjdk.java.net/panama/dev/
cd dev/
hg checkout vectorIntrinsics
hg branch vectorIntrinsics
bash configure
make images
Things I checked why it should have worked.
<ol> <li>lscpu shows all sorts of avx flags.</li>
<li> I chose HVM AMI which should support AVX instructions sets. https://aws.amazon.com/ec2/instance-types/ says : † AVX, AVX2, and Enhanced Networking are only available on instances launched with HVM AMIs.</li>
<li> I can compile vector code which means I am using appropriate branch of OpenJDK. I ran my code with --add-modules=jdk.incubator.vector VM parameter.
I also added some other VM params like state in [this intel blog](https://software.intel.com/en-us/articles/vector-api-developer-program-for-java) : -XX:TypeProfileLevel=121 </li>
<li> I checked the compiled assembly code it does contain vmulps instructions. Although it was difficult to find them as I am calling methods in vector api code and multiplication is happening at some other inside the called mul/fma method.</li>
<li>I have done lot more testing with different SIZE like 64, 128, 256, 512 and also using the ``FloatVector.SPECIES_PREFERRED``. In all cases vector api code is significantly slower then the simple multiplication code with unrolling.</li>
</ol>
</details>
# 答案1
**得分**: 2
我在这篇帖子中看到了一个问题，由 @iwanowww 在这里回答：https://gist.github.com/iwanowww/221df8893fbaa4b6b0904e3036221b1d 。简而言之，这是一个已经在之前修复的回归问题，具体细节如下。
**简而言之，现在已经修复了**
> (1) 在最新的 vectorIntrinsics 分支中，FloatVector256DotProduct.vector* 中的回归问题是由于向量操作内联化中的一个 bug 导致的：
```java
2675 92 b net.codingdemon.vectorization.FloatVector256DotProduct::vector (75 bytes)
...
@ 3 jdk.incubator.vector.FloatVector::zero (35 bytes) force inline by annotation
@ 6 jdk.incubator.vector.FloatVector$FloatSpecies::vectorType (5 bytes) accessor
@ 13 jdk.incubator.vector.AbstractSpecies::length (5 bytes) accessor
@ 19 jdk.incubator.vector.FloatVector::toBits (6 bytes) force inline by annotation
@ 1 java.lang.Float::floatToIntBits (15 bytes) (intrinsic)
@ 23 java.lang.invoke.Invokers$Holder::linkToTargetMethod (8 bytes) force inline by annotation
@ 4 java.lang.invoke.LambdaForm$MH/0x0000000800b8c040::invoke (8 bytes) force inline by annotation
@ 28 jdk.internal.vm.vector.VectorSupport::broadcastCoerced (35 bytes) failed to inline (intrinsic)
以下补丁修复了这个 bug：
diff --git a/src/hotspot/share/opto/vectorIntrinsics.cpp b/src/hotspot/share/opto/vectorIntrinsics.cpp
--- a/src/hotspot/share/opto/vectorIntrinsics.cpp
+++ b/src/hotspot/share/opto/vectorIntrinsics.cpp
@@ -476,7 +476,7 @@
// TODO 当支持掩码使用时，VecMaskNotUsed 需要变为 VecMaskUseLoad。
if (!arch_supports_vector(VectorNode::replicate_opcode(elem_bt), num_elem, elem_bt,
- is_vector_mask(vbox_klass) ? VecMaskUseStore : VecMaskNotUsed), true /*has_scalar_args*/) {
+ (is_vector_mask(vbox_klass) ? VecMaskUseStore : VecMaskNotUsed), true /*has_scalar_args*/)) {
if (C->print_intrinsics()) {
tty->print_cr(" ** not supported: arity=0 op=broadcast vlen=%d etype=%s ismask=%d",
num_elem, type2name(elem_bt),
之前：
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vanilla 1048576 thrpt 5 679.280 ± 13.731 ops/s
FloatVector256DotProduct.unrolled 1048576 thrpt 5 2319.770 ± 123.943 ops/s
FloatVector256DotProduct.vector 1048576 thrpt 5 803.740 ± 42.596 ops/s
FloatVector256DotProduct.vectorUnrolled 1048576 thrpt 5 797.153 ± 49.129 ops/s
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 828.172 ± 16.936 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 798.037 ± 85.566 ops/s
JavaDocExample.simpleMultiply 1048576 thrpt 5 1888.662 ± 55.922 ops/s
JavaDocExample.simpleMultiplyUnrolled 1048576 thrpt 5 1486.322 ± 93.864 ops/s
JavaDocExample.vectorMultiply 1048576 thrpt 5 1525.046 ± 110.700 ops/s
之后：
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vanilla 1048576 thrpt 5 666.581 ± 8.727 ops/s
FloatVector256DotProduct.unrolled 1048576 thrpt 5 2416.695 ± 106.223 ops/s
FloatVector256DotProduct.vector 1048576 thrpt 5 3776.422 ± 117.357 ops/s
FloatVector256DotProduct.vectorUnrolled 1048576 thrpt 5 3734.246 ± 122.463 ops/s
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 3804.485 ± 44.797 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 1158.018 ± 15.955 ops/s
JavaDocExample.simpleMultiply 1048576 thrpt 5 1914.794 ± 51.329 ops/s
JavaDocExample.simpleMultiplyUnrolled 1048576 thrpt 5 1405.345 ± 52.025 ops/s
JavaDocExample.vectorMultiply 1048576 thrpt 5 1832.133 ± 56.256 ops/s
(2) vectorfmaUnrolled 中的回归问题（与 vectorfma 相比）是由于众所周知的内联问题导致的，这破坏了向量盒消除：
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 3804.485 ± 44.797 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 1158.018 ± 15.955 ops/s
19727 95 b net.codingdemon.vectorization.FloatVector256DotProduct::vectorfmaUnrolled (228 bytes)
...
@ 209 jdk.incubator.vector.FloatVector::add (9 bytes) force inline by annotation
@ 5 jdk.incubator.vector.FloatVector::lanewise (0 bytes) virtual call
@ 213 jdk
<details>
<summary>英文:</summary>
I came across this post which was answered in the by @iwanowww here: https://gist.github.com/iwanowww/221df8893fbaa4b6b0904e3036221b1d . In short, this was a regression issue that was fixed since then, details below.
**TL;DR it is fixed now**
> (1) The regression in FloatVector256DotProduct.vector* with latest vectorIntrinsics branch is caused by a bug in vector operations intrinsification:
2675 92 b net.codingdemon.vectorization.FloatVector256DotProduct::vector (75 bytes)
...
@ 3 jdk.incubator.vector.FloatVector::zero (35 bytes) force inline by annotation
@ 6 jdk.incubator.vector.FloatVector$FloatSpecies::vectorType (5 bytes) accessor
@ 13 jdk.incubator.vector.AbstractSpecies::length (5 bytes) accessor
@ 19 jdk.incubator.vector.FloatVector::toBits (6 bytes) force inline by annotation
@ 1 java.lang.Float::floatToIntBits (15 bytes) (intrinsic)
@ 23 java.lang.invoke.Invokers$Holder::linkToTargetMethod (8 bytes) force inline by annotation
@ 4 java.lang.invoke.LambdaForm$MH/0x0000000800b8c040::invoke (8 bytes) force inline by annotation
@ 28 jdk.internal.vm.vector.VectorSupport::broadcastCoerced (35 bytes) failed to inline (intrinsic)
> The following patch fixes the bug:
diff --git a/src/hotspot/share/opto/vectorIntrinsics.cpp b/src/hotspot/share/opto/vectorIntrinsics.cpp
--- a/src/hotspot/share/opto/vectorIntrinsics.cpp
+++ b/src/hotspot/share/opto/vectorIntrinsics.cpp
@@ -476,7 +476,7 @@
// TODO When mask usage is supported, VecMaskNotUsed needs to be VecMaskUseLoad.
if (!arch_supports_vector(VectorNode::replicate_opcode(elem_bt), num_elem, elem_bt,
-
is_vector_mask(vbox_klass) ? VecMaskUseStore : VecMaskNotUsed), true /*has_scalar_args*/) {
-
(is_vector_mask(vbox_klass) ? VecMaskUseStore : VecMaskNotUsed), true /*has_scalar_args*/)) {if (C->print_intrinsics()) {
tty->print_cr(" ** not supported: arity=0 op=broadcast vlen=%d etype=%s ismask=%d",
num_elem, type2name(elem_bt),
> BEFORE:
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vanilla 1048576 thrpt 5 679.280 ± 13.731 ops/s
FloatVector256DotProduct.unrolled 1048576 thrpt 5 2319.770 ± 123.943 ops/s
FloatVector256DotProduct.vector 1048576 thrpt 5 803.740 ± 42.596 ops/s
FloatVector256DotProduct.vectorUnrolled 1048576 thrpt 5 797.153 ± 49.129 ops/s
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 828.172 ± 16.936 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 798.037 ± 85.566 ops/s
JavaDocExample.simpleMultiply 1048576 thrpt 5 1888.662 ± 55.922 ops/s
JavaDocExample.simpleMultiplyUnrolled 1048576 thrpt 5 1486.322 ± 93.864 ops/s
JavaDocExample.vectorMultiply 1048576 thrpt 5 1525.046 ± 110.700 ops/s
> AFTER:
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vanilla 1048576 thrpt 5 666.581 ± 8.727 ops/s
FloatVector256DotProduct.unrolled 1048576 thrpt 5 2416.695 ± 106.223 ops/s
FloatVector256DotProduct.vector 1048576 thrpt 5 3776.422 ± 117.357 ops/s
FloatVector256DotProduct.vectorUnrolled 1048576 thrpt 5 3734.246 ± 122.463 ops/s
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 3804.485 ± 44.797 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 1158.018 ± 15.955 ops/s
JavaDocExample.simpleMultiply 1048576 thrpt 5 1914.794 ± 51.329 ops/s
JavaDocExample.simpleMultiplyUnrolled 1048576 thrpt 5 1405.345 ± 52.025 ops/s
JavaDocExample.vectorMultiply 1048576 thrpt 5 1832.133 ± 56.256 ops/s
> (2) The regression in vectorfmaUnrolled (compared to vectorfma) is caused by well-known inlining issues which break vector box elimination:
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 3804.485 ± 44.797 ops/s
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 1158.018 ± 15.955 ops/s
19727 95 b net.codingdemon.vectorization.FloatVector256DotProduct::vectorfmaUnrolled (228 bytes)
...
@ 209 jdk.incubator.vector.FloatVector::add (9 bytes) force inline by annotation
@ 5 jdk.incubator.vector.FloatVector::lanewise (0 bytes) virtual call
@ 213 jdk.incubator.vector.FloatVector::add (9 bytes) force inline by annotation
@ 5 jdk.incubator.vector.FloatVector::lanewise (0 bytes) virtual call
@ 218 jdk.incubator.vector.FloatVector::add (9 bytes) force inline by annotation
@ 5 jdk.incubator.vector.FloatVector::lanewise (0 bytes) virtual call
...
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vectorfma 1048576 thrpt 5 3938.922 ± 97.041 ops/s
FloatVector256DotProduct.vectorfma:·gc.alloc.rate.norm 1048576 thrpt 5 0.111 ± 0.003 B/op
FloatVector256DotProduct.vectorfmaUnrolled 1048576 thrpt 5 2052.549 ± 68.859 ops/s
FloatVector256DotProduct.vectorfmaUnrolled:·gc.alloc.rate.norm 1048576 thrpt 5 1573537.127 ± 22.886 B/op
> Until the inlining is fixed, as a workaround, a warm-up phase with smaller data input can help:
Benchmark (size) Mode Cnt Score Error Units
FloatVector256DotProduct.vectorfma 128 thrpt 5 54838734.769 ± 161477.746 ops/s
FloatVector256DotProduct.vectorfma:·gc.alloc.rate.norm 128 thrpt 5 ≈ 10⁻⁵ B/op
FloatVector256DotProduct.vectorfmaUnrolled 128 thrpt 5 68993637.658 ± 359974.720 ops/s
FloatVector256DotProduct.vectorfmaUnrolled:·gc.alloc.rate.norm 128 thrpt 5 ≈ 10⁻⁵ B/op
</details>
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论