derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
78 lines
5.9 KiB
Plaintext
78 lines
5.9 KiB
Plaintext
// Test hlfir.matmul operation lowering to fir runtime call
|
|
// RUN: fir-opt %s -lower-hlfir-intrinsics | FileCheck %s
|
|
|
|
func.func @_QPmatmul1(%arg0: !fir.box<!fir.array<?x?xi32>> {fir.bindc_name = "lhs"}, %arg1: !fir.box<!fir.array<?x?xi32>> {fir.bindc_name = "rhs"}, %arg2: !fir.box<!fir.array<?x?xi32>> {fir.bindc_name = "res"}) {
|
|
%0:2 = hlfir.declare %arg0 {uniq_name = "_QFmatmul1Elhs"} : (!fir.box<!fir.array<?x?xi32>>) -> (!fir.box<!fir.array<?x?xi32>>, !fir.box<!fir.array<?x?xi32>>)
|
|
%1:2 = hlfir.declare %arg2 {uniq_name = "_QFmatmul1Eres"} : (!fir.box<!fir.array<?x?xi32>>) -> (!fir.box<!fir.array<?x?xi32>>, !fir.box<!fir.array<?x?xi32>>)
|
|
%2:2 = hlfir.declare %arg1 {uniq_name = "_QFmatmul1Erhs"} : (!fir.box<!fir.array<?x?xi32>>) -> (!fir.box<!fir.array<?x?xi32>>, !fir.box<!fir.array<?x?xi32>>)
|
|
%3 = hlfir.matmul %0#0 %2#0 {fastmath = #arith.fastmath<contract>} : (!fir.box<!fir.array<?x?xi32>>, !fir.box<!fir.array<?x?xi32>>) -> !hlfir.expr<?x?xi32>
|
|
hlfir.assign %3 to %1#0 : !hlfir.expr<?x?xi32>, !fir.box<!fir.array<?x?xi32>>
|
|
hlfir.destroy %3 : !hlfir.expr<?x?xi32>
|
|
return
|
|
}
|
|
// CHECK-LABEL: func.func @_QPmatmul1(
|
|
// CHECK: %[[ARG0:.*]]: !fir.box<!fir.array<?x?xi32>> {fir.bindc_name = "lhs"}
|
|
// CHECK: %[[ARG1:.*]]: !fir.box<!fir.array<?x?xi32>> {fir.bindc_name = "rhs"}
|
|
// CHECK: %[[ARG2:.*]]: !fir.box<!fir.array<?x?xi32>> {fir.bindc_name = "res"}
|
|
// CHECK-DAG: %[[TRUE:.*]] = arith.constant true
|
|
// CHECK-DAG: %[[LHS_VAR:.*]]:2 = hlfir.declare %[[ARG0]]
|
|
// CHECK-DAG: %[[RHS_VAR:.*]]:2 = hlfir.declare %[[ARG1]]
|
|
// CHECK-DAG: %[[RES_VAR:.*]]:2 = hlfir.declare %[[ARG2]]
|
|
|
|
// CHECK-DAG: %[[RET_BOX:.*]] = fir.alloca !fir.box<!fir.heap<!fir.array<?x?xi32>>>
|
|
// CHECK-DAG: %[[RET_ADDR:.*]] = fir.zero_bits !fir.heap<!fir.array<?x?xi32>>
|
|
// CHECK-DAG: %[[C0:.*]] = arith.constant 0 : index
|
|
// CHECK-DAG: %[[RET_SHAPE:.*]] = fir.shape %[[C0]], %[[C0]] : (index, index) -> !fir.shape<2>
|
|
// CHECK-DAG: %[[RET_EMBOX:.*]] = fir.embox %[[RET_ADDR]](%[[RET_SHAPE]])
|
|
// CHECK-DAG: fir.store %[[RET_EMBOX]] to %[[RET_BOX]]
|
|
|
|
// CHECK: %[[RET_ARG:.*]] = fir.convert %[[RET_BOX]] : (!fir.ref<!fir.box<!fir.heap<!fir.array<?x?xi32>>>>) -> !fir.ref<!fir.box<none>>
|
|
// CHECK-DAG: %[[LHS_ARG:.*]] = fir.convert %[[LHS_VAR]]#1 : (!fir.box<!fir.array<?x?xi32>>) -> !fir.box<none>
|
|
// CHECK-DAG: %[[RHS_ARG:.*]] = fir.convert %[[RHS_VAR]]#1 : (!fir.box<!fir.array<?x?xi32>>) -> !fir.box<none>
|
|
// CHECK: fir.call @_FortranAMatmulInteger4Integer4(%[[RET_ARG]], %[[LHS_ARG]], %[[RHS_ARG]], %[[LOC_STR:.*]], %[[LOC_N:.*]]) fastmath<contract>
|
|
|
|
// CHECK: %[[RET:.*]] = fir.load %[[RET_BOX]]
|
|
// CHECK-DAG: %[[BOX_DIMS:.*]]:3 = fir.box_dims %[[RET]]
|
|
// CHECK-DAG: %[[ADDR:.*]] = fir.box_addr %[[RET]]
|
|
// CHECK-NEXT: %[[SHIFT:.*]] = fir.shape_shift %[[BOX_DIMS]]#0, %[[BOX_DIMS]]#1
|
|
// TODO: fix alias analysis in hlfir.assign bufferization
|
|
// CHECK-NEXT: %[[TMP:.*]]:2 = hlfir.declare %[[ADDR]](%[[SHIFT]]) {uniq_name = ".tmp.intrinsic_result"}
|
|
// TODO: add shape information from original intrinsic op
|
|
// CHECK: %[[ASEXPR:.*]] = hlfir.as_expr %[[TMP]]#0 move %[[TRUE]] : (!fir.box<!fir.array<?x?xi32>>, i1) -> !hlfir.expr<?x?xi32>
|
|
// CHECK: hlfir.assign %[[ASEXPR]] to %[[RES_VAR]]#0
|
|
// CHECK: hlfir.destroy %[[ASEXPR]]
|
|
// CHECK-NEXT: return
|
|
// CHECK-NEXT: }
|
|
|
|
// nested matmuls leading to recursive pattern application
|
|
func.func @_QPtest(%arg0: !fir.ref<!fir.array<3x3xf32>> {fir.bindc_name = "a"}, %arg1: !fir.ref<!fir.array<3x3xf32>> {fir.bindc_name = "b"}, %arg2: !fir.ref<!fir.array<3x3xf32>> {fir.bindc_name = "c"}, %arg3: !fir.ref<!fir.array<3x3xf32>> {fir.bindc_name = "out"}) {
|
|
%c3 = arith.constant 3 : index
|
|
%c3_0 = arith.constant 3 : index
|
|
%0 = fir.shape %c3, %c3_0 : (index, index) -> !fir.shape<2>
|
|
%1:2 = hlfir.declare %arg0(%0) {uniq_name = "_QFtestEa"} : (!fir.ref<!fir.array<3x3xf32>>, !fir.shape<2>) -> (!fir.ref<!fir.array<3x3xf32>>, !fir.ref<!fir.array<3x3xf32>>)
|
|
%c3_1 = arith.constant 3 : index
|
|
%c3_2 = arith.constant 3 : index
|
|
%2 = fir.shape %c3_1, %c3_2 : (index, index) -> !fir.shape<2>
|
|
%3:2 = hlfir.declare %arg1(%2) {uniq_name = "_QFtestEb"} : (!fir.ref<!fir.array<3x3xf32>>, !fir.shape<2>) -> (!fir.ref<!fir.array<3x3xf32>>, !fir.ref<!fir.array<3x3xf32>>)
|
|
%c3_3 = arith.constant 3 : index
|
|
%c3_4 = arith.constant 3 : index
|
|
%4 = fir.shape %c3_3, %c3_4 : (index, index) -> !fir.shape<2>
|
|
%5:2 = hlfir.declare %arg2(%4) {uniq_name = "_QFtestEc"} : (!fir.ref<!fir.array<3x3xf32>>, !fir.shape<2>) -> (!fir.ref<!fir.array<3x3xf32>>, !fir.ref<!fir.array<3x3xf32>>)
|
|
%c3_5 = arith.constant 3 : index
|
|
%c3_6 = arith.constant 3 : index
|
|
%6 = fir.shape %c3_5, %c3_6 : (index, index) -> !fir.shape<2>
|
|
%7:2 = hlfir.declare %arg3(%6) {uniq_name = "_QFtestEout"} : (!fir.ref<!fir.array<3x3xf32>>, !fir.shape<2>) -> (!fir.ref<!fir.array<3x3xf32>>, !fir.ref<!fir.array<3x3xf32>>)
|
|
%8 = hlfir.matmul %1#0 %3#0 {fastmath = #arith.fastmath<contract>} : (!fir.ref<!fir.array<3x3xf32>>, !fir.ref<!fir.array<3x3xf32>>) -> !hlfir.expr<3x3xf32>
|
|
%9 = hlfir.matmul %8 %5#0 {fastmath = #arith.fastmath<contract>} : (!hlfir.expr<3x3xf32>, !fir.ref<!fir.array<3x3xf32>>) -> !hlfir.expr<3x3xf32>
|
|
hlfir.assign %9 to %7#0 : !hlfir.expr<3x3xf32>, !fir.ref<!fir.array<3x3xf32>>
|
|
hlfir.destroy %9 : !hlfir.expr<3x3xf32>
|
|
hlfir.destroy %8 : !hlfir.expr<3x3xf32>
|
|
return
|
|
}
|
|
// just check that we apply the patterns successfully. The details are checked above
|
|
// CHECK-LABEL: func.func @_QPtest(
|
|
// CHECK: fir.call @_FortranAMatmulReal4Real4({{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}}) fastmath<contract> : (!fir.ref<!fir.box<none>>, !fir.box<none>, !fir.box<none>, !fir.ref<i8>, i32) -> ()
|
|
// CHECK: fir.call @_FortranAMatmulReal4Real4({{.*}}, {{.*}}, {{.*}}, {{.*}}, {{.*}}) fastmath<contract> : (!fir.ref<!fir.box<none>>, !fir.box<none>, !fir.box<none>, !fir.ref<i8>, i32) -> ()
|
|
// CHECK: return
|
|
// CHECK-NEXT: }
|