colin
/
onnx-mlir
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
onnx-mlir/test/mlir/krnl/ops.mlir

75 lines
3.3 KiB
MLIR
Raw Normal View History

[NFC] Change ONNF based names to ONNX-MLIR (#32) * Rename onnf to onnx-mlir. * Change workspace name.
2020-03-17 21:16:33 +08:00
// RUN: onnx-mlir-opt %s -mlir-print-op-generic | FileCheck -check-prefix=GENERIC %s
// RUN: onnx-mlir-opt %s | FileCheck %s
[MLIR] Refactor Krnl Dialect and Krnl Dialect Lowering (#375) * Store bounds as affine map attributes & check in test cases with generic printer * Upgrading MLIR MLIR is outdated on Buildbot, rebuilding a newer version. * work with new version of mlir * check-in parser tests * custom printer * nit * bug fix * enable custom asm printer test * enable custom asm printer test * more consistent variable naming * test max/min * variable naming scheme change to MLIR style * can lower krnl to llvm * kernel -> llvm * comments * bug fix * try fixing ci * fix ci * deactivate model test * fix lit test * nit * fix z buildbot
2019-11-28 11:56:34 +08:00
Enable e2e tests (#29) * Sync with latest MLIR. * Enable ONNX backend tests as a means to test ONNF lowering end-to-end. * Install ONNX using quiet mode. * Remove debug comments. * Install ONNX from third_party/onnx. * Check python version and fix pip command for installing ONNX. * Using --user install option to prevent permission denied. * Remove unused imports. * Try using stock ONNX pip package as there are more tests in them. * Pip got stuck building wheels, try sudo. * Use verbose install to debug. * Invalidate cache to build LLVM tools. * Fix mlir installation script location. * Debug to locate ONNF. * Sanity check. * Check out ONNF code first. * Use verbose LIT output. * 1. Update documentation to always use verbose LIT. 2. Update krnl ops to reflect new affine map attribute syntax. * See if conda exists * Install ONNX by manually cloning the repo. * Install cmake first. * Using sudo priviledge when installing. * Limit build parallelism. * Limit parallelism. * Larger memory. * Install onnx package with pip. * Build MLIR tools. * Invalidate cache. * Compile model.so with -fPIC. * Remove module dump to get concise debug output. * Print command before executing. * Use quiet install mode to reduce logging. * Use -relocation-model=pic to generate position independent code. * 1. Remove MAKEFLAGS because now buildbot has enough memory. 2. Run DocCheck as a last step. * 1. Add verbose mode for backtend test. * When dumping to LLVM bitcode, do not dump module IR, but print a message indicating that bitcode has been written to disk. * Do not pass MakeFlags to CMake. * Add more explaination for posible reasons of failing to identify tests.
2020-01-21 01:30:08 +08:00
// GENERIC-DAG: #{{.*}} = affine_map<() -> (0)>
// GENERIC-DAG: #{{.*}} = affine_map<() -> (10)>
// GENERIC-DAG: #{{.*}} = affine_map<() -> (1)>
// GENERIC-DAG: #{{.*}} = affine_map<() -> (11)>
// GENERIC-DAG: #{{.*}} = affine_map<(d0, d1) -> (d0 - d1)>
// GENERIC-DAG: #{{.*}} = affine_map<(d0, d1) -> (d0 + d1)>
[MLIR] Refactor Krnl Dialect and Krnl Dialect Lowering (#375) * Store bounds as affine map attributes & check in test cases with generic printer * Upgrading MLIR MLIR is outdated on Buildbot, rebuilding a newer version. * work with new version of mlir * check-in parser tests * custom printer * nit * bug fix * enable custom asm printer test * enable custom asm printer test * more consistent variable naming * test max/min * variable naming scheme change to MLIR style * can lower krnl to llvm * kernel -> llvm * comments * bug fix * try fixing ci * fix ci * deactivate model test * fix lit test * nit * fix z buildbot
2019-11-28 11:56:34 +08:00
func @simple_iterate(%N : index) {
%ii, %ij, %ik = krnl.define_loops 3
%oi, %oj, %ok = krnl.optimize_loops {
krnl.return_loops %ii, %ij, %ik
} : () -> (!krnl.loop, !krnl.loop, !krnl.loop)
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index, %{{.*}}: index):
// GENERIC-NEXT: "krnl.terminate"() : () -> ()
// GENERIC-NEXT: bounds = [#{{.*}}, #{{.*}}, #{{.*}}, #{{.*}}]
// CHECK: krnl.iterate(%{{.*}}, %{{.*}}) with (%{{.*}} -> %{{.*}} = 0 to 10, %{{.*}} -> %{{.*}} = 1 to 11) {
krnl.iterate(%oi, %oj) with (%ii -> %i = 0 to 10, %ij -> %j = 1 to 11) {
}
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index, %{{.*}}: index):
// CHECK: krnl.iterate(%{{.*}}, %{{.*}}) with (%{{.*}} -> %{{.*}} = 0 to 10, %{{.*}} -> %{{.*}} = 0 to 10) {
krnl.iterate(%oi, %oj) with (%ii -> %i = 0 to 10, %ij -> %j = 0 to 10) {
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index):
// CHECK: krnl.iterate(%{{.*}}) with (%{{.*}} -> %{{.*}} = 0 to 10) {
krnl.iterate(%ok) with (%ik -> %k = 0 to 10) {
}
}
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index, %{{.*}}: index):
// CHECK: krnl.iterate(%{{.*}}, %{{.*}}) with (%{{.*}} -> %{{.*}} = 0 to %{{.*}}, %{{.*}} -> %{{.*}} = 0 to 10) {
krnl.iterate(%oi, %oj) with (%ii -> %i = 0 to %N, %ij -> %j = 0 to 10) {
}
return
}
func @affine_map_bound(%N : index) {
%ii, %ij, %ik = krnl.define_loops 3
%oi, %oj, %ok = krnl.optimize_loops {
krnl.return_loops %ii, %ij, %ik
} : () -> (!krnl.loop, !krnl.loop, !krnl.loop)
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index, %{{.*}}: index):
// CHECK: krnl.iterate(%{{.*}}, %{{.*}}) with (%{{.*}} -> %{{.*}} = 0 to 10, %{{.*}} -> %{{.*}} = 0 to 10) {
Enable e2e tests (#29) * Sync with latest MLIR. * Enable ONNX backend tests as a means to test ONNF lowering end-to-end. * Install ONNX using quiet mode. * Remove debug comments. * Install ONNX from third_party/onnx. * Check python version and fix pip command for installing ONNX. * Using --user install option to prevent permission denied. * Remove unused imports. * Try using stock ONNX pip package as there are more tests in them. * Pip got stuck building wheels, try sudo. * Use verbose install to debug. * Invalidate cache to build LLVM tools. * Fix mlir installation script location. * Debug to locate ONNF. * Sanity check. * Check out ONNF code first. * Use verbose LIT output. * 1. Update documentation to always use verbose LIT. 2. Update krnl ops to reflect new affine map attribute syntax. * See if conda exists * Install ONNX by manually cloning the repo. * Install cmake first. * Using sudo priviledge when installing. * Limit build parallelism. * Limit parallelism. * Larger memory. * Install onnx package with pip. * Build MLIR tools. * Invalidate cache. * Compile model.so with -fPIC. * Remove module dump to get concise debug output. * Print command before executing. * Use quiet install mode to reduce logging. * Use -relocation-model=pic to generate position independent code. * 1. Remove MAKEFLAGS because now buildbot has enough memory. 2. Run DocCheck as a last step. * 1. Add verbose mode for backtend test. * When dumping to LLVM bitcode, do not dump module IR, but print a message indicating that bitcode has been written to disk. * Do not pass MakeFlags to CMake. * Add more explaination for posible reasons of failing to identify tests.
2020-01-21 01:30:08 +08:00
krnl.iterate(%oi, %oj) with (%ii -> %i = affine_map<()->(0)>() to affine_map<()->(10)>(), %ij -> %j = 0 to 10) {
[MLIR] Refactor Krnl Dialect and Krnl Dialect Lowering (#375) * Store bounds as affine map attributes & check in test cases with generic printer * Upgrading MLIR MLIR is outdated on Buildbot, rebuilding a newer version. * work with new version of mlir * check-in parser tests * custom printer * nit * bug fix * enable custom asm printer test * enable custom asm printer test * more consistent variable naming * test max/min * variable naming scheme change to MLIR style * can lower krnl to llvm * kernel -> llvm * comments * bug fix * try fixing ci * fix ci * deactivate model test * fix lit test * nit * fix z buildbot
2019-11-28 11:56:34 +08:00
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index):
// CHECK: krnl.iterate(%{{.*}}) with (%{{.*}} -> %{{.*}} = #{{.*}}(%{{.*}}, %{{.*}}) to #{{.*}}(%{{.*}}, %{{.*}})) {
Enable e2e tests (#29) * Sync with latest MLIR. * Enable ONNX backend tests as a means to test ONNF lowering end-to-end. * Install ONNX using quiet mode. * Remove debug comments. * Install ONNX from third_party/onnx. * Check python version and fix pip command for installing ONNX. * Using --user install option to prevent permission denied. * Remove unused imports. * Try using stock ONNX pip package as there are more tests in them. * Pip got stuck building wheels, try sudo. * Use verbose install to debug. * Invalidate cache to build LLVM tools. * Fix mlir installation script location. * Debug to locate ONNF. * Sanity check. * Check out ONNF code first. * Use verbose LIT output. * 1. Update documentation to always use verbose LIT. 2. Update krnl ops to reflect new affine map attribute syntax. * See if conda exists * Install ONNX by manually cloning the repo. * Install cmake first. * Using sudo priviledge when installing. * Limit build parallelism. * Limit parallelism. * Larger memory. * Install onnx package with pip. * Build MLIR tools. * Invalidate cache. * Compile model.so with -fPIC. * Remove module dump to get concise debug output. * Print command before executing. * Use quiet install mode to reduce logging. * Use -relocation-model=pic to generate position independent code. * 1. Remove MAKEFLAGS because now buildbot has enough memory. 2. Run DocCheck as a last step. * 1. Add verbose mode for backtend test. * When dumping to LLVM bitcode, do not dump module IR, but print a message indicating that bitcode has been written to disk. * Do not pass MakeFlags to CMake. * Add more explaination for posible reasons of failing to identify tests.
2020-01-21 01:30:08 +08:00
krnl.iterate(%ok) with (%ik -> %k = affine_map<(d0, d1)->(d0 - d1)>(%i, %j) to affine_map<(d0, d1)->(d0 + d1)>(%i, %j)) {
[MLIR] Refactor Krnl Dialect and Krnl Dialect Lowering (#375) * Store bounds as affine map attributes & check in test cases with generic printer * Upgrading MLIR MLIR is outdated on Buildbot, rebuilding a newer version. * work with new version of mlir * check-in parser tests * custom printer * nit * bug fix * enable custom asm printer test * enable custom asm printer test * more consistent variable naming * test max/min * variable naming scheme change to MLIR style * can lower krnl to llvm * kernel -> llvm * comments * bug fix * try fixing ci * fix ci * deactivate model test * fix lit test * nit * fix z buildbot
2019-11-28 11:56:34 +08:00
}
// GENERIC: "krnl.iterate"(%{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}, %{{.*}}) ( {
// GENERIC-NEXT: ^bb0(%{{.*}}: index):
// CHECK: krnl.iterate(%{{.*}}) with (%{{.*}} -> %{{.*}} = max #map{{.*}}(%{{.*}}, %{{.*}}) to min #map{{.*}}(%{{.*}}, %{{.*}})[%{{.*}}]) {
Enable e2e tests (#29) * Sync with latest MLIR. * Enable ONNX backend tests as a means to test ONNF lowering end-to-end. * Install ONNX using quiet mode. * Remove debug comments. * Install ONNX from third_party/onnx. * Check python version and fix pip command for installing ONNX. * Using --user install option to prevent permission denied. * Remove unused imports. * Try using stock ONNX pip package as there are more tests in them. * Pip got stuck building wheels, try sudo. * Use verbose install to debug. * Invalidate cache to build LLVM tools. * Fix mlir installation script location. * Debug to locate ONNF. * Sanity check. * Check out ONNF code first. * Use verbose LIT output. * 1. Update documentation to always use verbose LIT. 2. Update krnl ops to reflect new affine map attribute syntax. * See if conda exists * Install ONNX by manually cloning the repo. * Install cmake first. * Using sudo priviledge when installing. * Limit build parallelism. * Limit parallelism. * Larger memory. * Install onnx package with pip. * Build MLIR tools. * Invalidate cache. * Compile model.so with -fPIC. * Remove module dump to get concise debug output. * Print command before executing. * Use quiet install mode to reduce logging. * Use -relocation-model=pic to generate position independent code. * 1. Remove MAKEFLAGS because now buildbot has enough memory. 2. Run DocCheck as a last step. * 1. Add verbose mode for backtend test. * When dumping to LLVM bitcode, do not dump module IR, but print a message indicating that bitcode has been written to disk. * Do not pass MakeFlags to CMake. * Add more explaination for posible reasons of failing to identify tests.
2020-01-21 01:30:08 +08:00
krnl.iterate(%ok) with (%ik -> %k = max affine_map<(d0, d1)->(d0 - d1, 0)>(%i, %j) to min affine_map<(d0, d1)[s0]->(d0 + d1, s0)>(%i, %j)[%N]) {
[MLIR] Refactor Krnl Dialect and Krnl Dialect Lowering (#375) * Store bounds as affine map attributes & check in test cases with generic printer * Upgrading MLIR MLIR is outdated on Buildbot, rebuilding a newer version. * work with new version of mlir * check-in parser tests * custom printer * nit * bug fix * enable custom asm printer test * enable custom asm printer test * more consistent variable naming * test max/min * variable naming scheme change to MLIR style * can lower krnl to llvm * kernel -> llvm * comments * bug fix * try fixing ci * fix ci * deactivate model test * fix lit test * nit * fix z buildbot
2019-11-28 11:56:34 +08:00
}
}
return
}