shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
447,783 Commits 1,713 Branches 298 Tags
Commit Graph

9 Commits

Author SHA1 Message Date
zhanghb97
ee82b864f2 [mlir] Initial MLIR VP intrinsic integration test on host and RVV emulator. 
This patch adds the initial VP intrinsic integration test on the host backend and RVV emulator. Please see more detailed [discussion on the discourse](https://discourse.llvm.org/t/mlir-vp-ops-on-rvv-backend-integration-test-and-issues-report/66343).

- Run the test cases on the host by configuring the CMake option: `-DMLIR_INCLUDE_INTEGRATION_TESTS=ON`
- Build the RVV environment and run the test cases on RVV QEMU by [this doc](https://gist.github.com/zhanghb97/ad44407e169de298911b8a4235e68497).

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D137816
 2022-11-22 17:30:24 +08:00
Christian Sigg
0f2ec35691 [MLIR] Switch lit tests to %mlir_lib_dir and %mlir_src_dir replacements. 
The old replacements will be removed soon:
- `%linalg_test_lib_dir`
- `%cuda_wrapper_library_dir`
- `%spirv_wrapper_library_dir`
- `%vulkan_wrapper_library_dir`
- `%mlir_runner_utils_dir`
- `%mlir_integration_test_dir`

Reviewed By: herhut

Differential Revision: https://reviews.llvm.org/D133270
 2022-09-06 12:34:14 +02:00
Jeff Niu
491dd5a3b2 [mlir][LLVMIR] Fix syntax in integration tests (NFC) 2022-08-18 13:09:34 -04:00
Jeff Niu
b2ccfb4d95 [mlir][LLVMIR] Change ShuffleVectorOp to use assembly format 
This patch moves `LLVM::ShuffleVectorOp` to assembly format and in the
process drops the extra type that can be inferred (both operand types
are required to be the same) and switches to a dense integer array.

The syntax change:

```
// Before
%0 = llvm.shufflevector %0, %1 [0 : i32, 0 : i32, 0 : i32, 0 : i32] : vector<4xf32>, vector<4xf32>
// After
%0 = llvm.shufflevector %0, %1 [0, 0, 0, 0] : vector<4xf32>
```

Reviewed By: dcaballe

Differential Revision: https://reviews.llvm.org/D132038
 2022-08-18 12:46:04 -04:00
Aart Bik
d926b3307e [mlir] add complex type to getZeroAttr 
Fixes issue encountered with <sparse> complex constant
https://github.com/llvm/llvm-project/issues/56428

Reviewed By: rriddle

Differential Revision: https://reviews.llvm.org/D129325
 2022-07-07 16:58:59 -07:00
Nicolas Vasilache
b2729fda60 [mlir][Vector] Add a vblendps-based impl for transpose8x8 (both intrin and inline_asm) 
This revision follows up on the conversation titled:

```[llvm-dev] Understanding and controlling some of the AVX shuffle emission paths```

The revision adds a vblendps-based implementation for transpose8x8 and further distinguishes between and intrinsics and an inline_asm implementation.

This results in roughly 20% fewer cycles as reported by llvm-mca:

After this revision (intrinsic version, resolves to virtually identical assembly as per the llvm-dev discussion, no vblendps instruction is emitted):
```
Iterations:        100
Instructions:      5900
Total Cycles:      2415
Total uOps:        7300

Dispatch Width:    6
uOps Per Cycle:    3.02
IPC:               2.44
Block RThroughput: 24.0

Cycles with backend pressure increase [ 89.90% ]
Throughput Bottlenecks:
  Resource Pressure       [ 89.65% ]
  - SKXPort1  [ 0.04% ]
  - SKXPort2  [ 12.42% ]
  - SKXPort3  [ 12.42% ]
  - SKXPort5  [ 89.52% ]
  Data Dependencies:      [ 37.06% ]
  - Register Dependencies [ 37.06% ]
  - Memory Dependencies   [ 0.00% ]
```

After this revision (inline_asm version, vblendps instructions are indeed emitted):
```
Iterations:        100
Instructions:      6300
Total Cycles:      2015
Total uOps:        7700

Dispatch Width:    6
uOps Per Cycle:    3.82
IPC:               3.13
Block RThroughput: 20.0

Cycles with backend pressure increase [ 83.47% ]
Throughput Bottlenecks:
  Resource Pressure       [ 83.18% ]
  - SKXPort0  [ 14.49% ]
  - SKXPort1  [ 14.54% ]
  - SKXPort2  [ 19.70% ]
  - SKXPort3  [ 19.70% ]
  - SKXPort5  [ 83.03% ]
  - SKXPort6  [ 14.49% ]
  Data Dependencies:      [ 39.75% ]
  - Register Dependencies [ 39.75% ]
  - Memory Dependencies   [ 0.00% ]
```

An accessible copy of the conversation is available [here](https://gist.github.com/nicolasvasilache/68c7f34012584b0e00f335bcb374ede0).

Differential Revision: https://reviews.llvm.org/D114393
 2021-11-23 07:31:22 +00:00
Mehdi Amini
e0b7bee7cf Revert "[mlir][Vector] Add a vblendps-based impl for transpose8x8 (both intrin and inline_asm)" 
This reverts commit a9e236bed835c58be381dadb973a1db0681e4795.
This broke the Windows build:

mlir\include\mlir/Dialect/X86Vector/Transforms.h(28): error C2061: syntax error: identifier 'uint'
 2021-11-22 19:23:18 +00:00
Nicolas Vasilache
a9e236bed8 [mlir][Vector] Add a vblendps-based impl for transpose8x8 (both intrin and inline_asm) 
This revision follows up on the conversation titled:

```[llvm-dev] Understanding and controlling some of the AVX shuffle emission paths```

The revision adds a vblendps-based implementation for transpose8x8 and further distinguishes between and intrinsics and an inline_asm implementation.

This results in roughly 20% fewer cycles as reported by llvm-mca:

After this revision (intrinsic version, resolves to virtually identical assembly as per the llvm-dev discussion, no vblendps instruction is emitted):
```
Iterations:        100
Instructions:      5900
Total Cycles:      2415
Total uOps:        7300

Dispatch Width:    6
uOps Per Cycle:    3.02
IPC:               2.44
Block RThroughput: 24.0

Cycles with backend pressure increase [ 89.90% ]
Throughput Bottlenecks:
  Resource Pressure       [ 89.65% ]
  - SKXPort1  [ 0.04% ]
  - SKXPort2  [ 12.42% ]
  - SKXPort3  [ 12.42% ]
  - SKXPort5  [ 89.52% ]
  Data Dependencies:      [ 37.06% ]
  - Register Dependencies [ 37.06% ]
  - Memory Dependencies   [ 0.00% ]
```

After this revision (inline_asm version, vblendps instructions are indeed emitted):
```
Iterations:        100
Instructions:      6300
Total Cycles:      2015
Total uOps:        7700

Dispatch Width:    6
uOps Per Cycle:    3.82
IPC:               3.13
Block RThroughput: 20.0

Cycles with backend pressure increase [ 83.47% ]
Throughput Bottlenecks:
  Resource Pressure       [ 83.18% ]
  - SKXPort0  [ 14.49% ]
  - SKXPort1  [ 14.54% ]
  - SKXPort2  [ 19.70% ]
  - SKXPort3  [ 19.70% ]
  - SKXPort5  [ 83.03% ]
  - SKXPort6  [ 14.49% ]
  Data Dependencies:      [ 39.75% ]
  - Register Dependencies [ 39.75% ]
  - Memory Dependencies   [ 0.00% ]
```

An accessible copy of the conversation is available [here](https://gist.github.com/nicolasvasilache/68c7f34012584b0e00f335bcb374ede0).

Reviewed By: ftynse, dcaballe

Differential Revision: https://reviews.llvm.org/D114335
 2021-11-22 10:32:34 +00:00
Mehdi Amini
99b0032ce0 Move the MLIR integration tests as a subdirectory of test (NFC) 
This does not change the behavior directly: the tests only run when
`-DMLIR_INCLUDE_INTEGRATION_TESTS=ON` is configured. However running
`ninja check-mlir` will not run all the tests within a single
lit invocation. The previous behavior would wait for all the integration
tests to complete before starting to run the first regular test. The
test results were also reported separately. This change is unifying all
of this and allow concurrent execution of the integration tests with
regular non-regression and unit-tests.

Differential Revision: https://reviews.llvm.org/D97241
 2021-02-23 05:55:47 +00:00