/external/llvm-project/mlir/test/Dialect/SCF/ |
D | loop-unroll.mlir | 1 // RUN: mlir-opt %s -test-loop-unrolling='unroll-factor=2' | FileCheck %s --check-prefix UNROLL-BY-2 2 // RUN: mlir-opt %s -test-loop-unrolling='unroll-factor=3' | FileCheck %s --check-prefix UNROLL-BY-3 3 …-test-loop-unrolling='unroll-factor=2 loop-depth=0' | FileCheck %s --check-prefix UNROLL-OUTER-BY-2 4 …-test-loop-unrolling='unroll-factor=2 loop-depth=1' | FileCheck %s --check-prefix UNROLL-INNER-BY-2 5 …e-loop-unroll='unroll-factor=6 unroll-up-to-factor=true' | FileCheck %s --check-prefix UNROLL-UP-TO 15 // UNROLL-BY-2-LABEL: func @dynamic_loop_unroll 16 // UNROLL-BY-2-SAME: %[[LB:.*0]]: index, 17 // UNROLL-BY-2-SAME: %[[UB:.*1]]: index, 18 // UNROLL-BY-2-SAME: %[[STEP:.*2]]: index, 19 // UNROLL-BY-2-SAME: %[[MEM:.*3]]: memref<?xf32> [all …]
|
/external/llvm-project/mlir/test/Dialect/Affine/ |
D | unroll.mlir | 1 …unregistered-dialect %s -affine-loop-unroll="unroll-full" | FileCheck %s --check-prefix UNROLL-FULL 3 …gistered-dialect %s -affine-loop-unroll="unroll-factor=4" | FileCheck %s --check-prefix UNROLL-BY-4 4 …gistered-dialect %s -affine-loop-unroll="unroll-factor=1" | FileCheck %s --check-prefix UNROLL-BY-1 6 // UNROLL-FULL-DAG: [[$MAP0:#map[0-9]+]] = affine_map<(d0) -> (d0 + 1)> 7 // UNROLL-FULL-DAG: [[$MAP1:#map[0-9]+]] = affine_map<(d0) -> (d0 + 2)> 8 // UNROLL-FULL-DAG: [[$MAP2:#map[0-9]+]] = affine_map<(d0) -> (d0 + 3)> 9 // UNROLL-FULL-DAG: [[$MAP3:#map[0-9]+]] = affine_map<(d0) -> (d0 + 4)> 10 // UNROLL-FULL-DAG: [[$MAP4:#map[0-9]+]] = affine_map<(d0, d1) -> (d0 + 1)> 11 // UNROLL-FULL-DAG: [[$MAP5:#map[0-9]+]] = affine_map<(d0, d1) -> (d0 + 3)> 12 // UNROLL-FULL-DAG: [[$MAP6:#map[0-9]+]] = affine_map<(d0)[s0] -> (d0 + s0 + 1)> [all …]
|
/external/llvm-project/llvm/test/Transforms/LoopVectorize/ |
D | if-pred-stores.ll | 2 …terleave=2 -loop-vectorize -verify-loop-info -simplifycfg < %s | FileCheck %s --check-prefix=UNROLL 3 …interleave=2 -loop-vectorize -verify-loop-info < %s | FileCheck %s --check-prefix=UNROLL-NOSIMPLIFY 10 ; UNROLL-LABEL: @test( 11 ; UNROLL-NEXT: entry: 12 ; UNROLL-NEXT: br label [[VECTOR_BODY:%.*]] 13 ; UNROLL: vector.body: 14 ; UNROLL-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_… 15 ; UNROLL-NEXT: [[INDUCTION:%.*]] = add i64 [[INDEX]], 0 16 ; UNROLL-NEXT: [[INDUCTION1:%.*]] = add i64 [[INDEX]], 1 17 ; UNROLL-NEXT: [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[F:%.*]], i64 [[INDUCTION]] [all …]
|
D | induction.ll | 3 …orce-vector-interleave=2 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=UNROLL 4 …rize -force-vector-interleave=2 -force-vector-width=2 -S | FileCheck %s --check-prefix=UNROLL-NO-IC 91 ; UNROLL-NO-IC-LABEL: @scalarize_induction_variable_01( 92 ; UNROLL-NO-IC: vector.body: 93 ; UNROLL-NO-IC: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ] 94 ; UNROLL-NO-IC: %[[i0:.+]] = add i64 %index, 0 95 ; UNROLL-NO-IC: %[[i2:.+]] = add i64 %index, 2 96 ; UNROLL-NO-IC: getelementptr inbounds i64, i64* %a, i64 %[[i0]] 97 ; UNROLL-NO-IC: getelementptr inbounds i64, i64* %a, i64 %[[i2]] 105 ; UNROLL-LABEL: @scalarize_induction_variable_01( [all …]
|
D | first-order-recurrence.ll | 2 …vector-width=4 -force-vector-interleave=2 -dce -instcombine -S | FileCheck %s --check-prefix=UNROLL 3 …rize -force-vector-width=4 -force-vector-interleave=2 -S | FileCheck %s --check-prefix=UNROLL-NO-IC 4 …rize -force-vector-width=1 -force-vector-interleave=2 -S | FileCheck %s --check-prefix=UNROLL-NO-VF 29 ; UNROLL-LABEL: @recurrence_1( 30 ; UNROLL: vector.body: 31 ; UNROLL: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ [[L2:%[a-zA-Z… 32 ; UNROLL: [[L1:%[a-zA-Z0-9.]+]] = load <4 x i32> 33 ; UNROLL: [[L2]] = load <4 x i32> 34 ; UNROLL: {{.*}} = shufflevector <4 x i32> %vector.recur, <4 x i32> [[L1]], <4 x i32> <i32 … 35 ; UNROLL: {{.*}} = shufflevector <4 x i32> [[L1]], <4 x i32> [[L2]], <4 x i32> <i32 3, i32 … [all …]
|
D | gcc-examples.ll | 2 …-vector-width=4 -force-vector-interleave=4 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL 27 ;UNROLL-LABEL: @example1( 28 ;UNROLL: load <4 x i32> 29 ;UNROLL: load <4 x i32> 30 ;UNROLL: load <4 x i32> 31 ;UNROLL: load <4 x i32> 32 ;UNROLL: add nsw <4 x i32> 33 ;UNROLL: add nsw <4 x i32> 34 ;UNROLL: add nsw <4 x i32> 35 ;UNROLL: add nsw <4 x i32> [all …]
|
/external/llvm-project/llvm/test/Transforms/LoopUnroll/ARM/ |
D | loop-unrolling.ll | 1 …mtriple=armv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A 2 …riple=thumbv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A 3 …riple=thumbv7 -mcpu=cortex-a72 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A 4 …ple=thumbv8m -mcpu=cortex-m23 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T1 5 …humbv8m.main -mcpu=cortex-m33 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2 6 …ple=thumbv7em -mcpu=cortex-m7 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2 16 ; CHECK-UNROLL-A: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV2:%[a-z.0-9]+]], %for.body ] 17 ; CHECK-UNROLL-A: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1 18 ; CHECK-UNROLL-A: [[IV2]] = add nuw nsw i32 [[IV1]], 1 19 ; CHECK-UNROLL-A: [[CMP:%[a-z.0-9]+]] = icmp eq i32 [[IV2]], 1024 [all …]
|
D | upperbound.ll | 1 …: opt -loop-unroll -S -mtriple arm-none-eabi -mcpu=cortex-m7 %s | FileCheck %s -check-prefix=UNROLL 5 ; UNROLL-LABEL: @test 6 ; UNROLL: load i32, i32* 7 ; UNROLL: load i32, i32* 8 ; UNROLL: load i32, i32* 9 ; UNROLL-NOT: load i32, i32*
|
/external/llvm-project/llvm/test/Transforms/LoopUnroll/ |
D | runtime-loop5.ll | 1 … < %s -S -loop-unroll -unroll-runtime=true -unroll-count=16 | FileCheck --check-prefix=UNROLL-16 %s 2 …pt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=4 | FileCheck --check-prefix=UNROLL-4 %s 4 …rk-emit>,loop-unroll' -unroll-runtime=true -unroll-count=16 | FileCheck --check-prefix=UNROLL-16 %s 5 …mark-emit>,loop-unroll' -unroll-runtime=true -unroll-count=4 | FileCheck --check-prefix=UNROLL-4 %s 11 ; UNROLL-16-LABEL: @test( 12 ; UNROLL-4-LABEL: @test( 18 ; UNROLL-16-LABEL: for.body: 19 ; UNROLL-4-LABEL: for.body: 24 ; UNROLL-16-LABEL: for.body 25 ; UNROLL-16-LABEL: getelementptr [all …]
|
D | loop-remarks.ll | 1 …unroll -pass-remarks=loop-unroll -unroll-count=16 2>&1 | FileCheck -check-prefix=COMPLETE-UNROLL %s 2 …p-unroll -pass-remarks=loop-unroll -unroll-count=4 2>&1 | FileCheck -check-prefix=PARTIAL-UNROLL %s 3 …ll-count=4 -unroll-runtime=true -unroll-remainder 2>&1 | FileCheck %s --check-prefix=RUNTIME-UNROLL 5 ; COMPLETE-UNROLL: remark: {{.*}}: completely unrolled loop with 16 iterations 6 ; PARTIAL-UNROLL: remark: {{.*}}: unrolled loop by a factor of 4 7 ; RUNTIME-UNROLL: remark: {{.*}}: unrolled loop by a factor of 4 27 ; RUNTIME-UNROLL-NOT: remark: {{.*}}: completely unrolled loop with 3 iterations 28 ; RUNTIME-UNROLL: remark: {{.*}}: unrolled loop by a factor of 4
|
/external/llvm/test/Transforms/LoopUnroll/ |
D | runtime-loop5.ll | 1 … < %s -S -loop-unroll -unroll-runtime=true -unroll-count=16 | FileCheck --check-prefix=UNROLL-16 %s 2 …pt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=4 | FileCheck --check-prefix=UNROLL-4 %s 8 ; UNROLL-16-LABEL: @test( 9 ; UNROLL-4-LABEL: @test( 15 ; UNROLL-16-LABEL: for.body: 16 ; UNROLL-4-LABEL: for.body: 21 ; UNROLL-16-LABEL: for.body 22 ; UNROLL-16-LABEL: getelementptr 23 ; UNROLL-16-LABEL-NOT: getelementptr 25 ; UNROLL-4-LABEL: getelementptr [all …]
|
/external/XNNPACK/scripts/ |
D | generate-f32-spmm.sh | 9 tools/xngen src/f32-spmm/scalar.c.in -D MR=1 -D NR=1 -D UNROLL=1 -o src/f32-spmm/gen/1x1-minmax-sca… 10 tools/xngen src/f32-spmm/scalar.c.in -D MR=2 -D NR=1 -D UNROLL=1 -o src/f32-spmm/gen/2x1-minmax-sca… 11 tools/xngen src/f32-spmm/scalar.c.in -D MR=4 -D NR=1 -D UNROLL=1 -o src/f32-spmm/gen/4x1-minmax-sca… 12 tools/xngen src/f32-spmm/scalar.c.in -D MR=8 -D NR=1 -D UNROLL=1 -o src/f32-spmm/gen/8x1-minmax-sca… 13 tools/xngen src/f32-spmm/scalar.c.in -D MR=8 -D NR=2 -D UNROLL=1 -o src/f32-spmm/gen/8x2-minmax-sca… 14 tools/xngen src/f32-spmm/scalar.c.in -D MR=8 -D NR=4 -D UNROLL=1 -o src/f32-spmm/gen/8x4-minmax-sca… 23 tools/xngen src/f32-spmm/neon.c.in -D MR=4 -D NR=1 -D UNROLL=1 -D FMA=0 -o src/f32-spmm/gen/4x1-mi… 24 tools/xngen src/f32-spmm/neon.c.in -D MR=8 -D NR=1 -D UNROLL=1 -D FMA=0 -o src/f32-spmm/gen/8x1-mi… 25 tools/xngen src/f32-spmm/neon.c.in -D MR=12 -D NR=1 -D UNROLL=1 -D FMA=0 -o src/f32-spmm/gen/12x1-m… 26 tools/xngen src/f32-spmm/neon.c.in -D MR=16 -D NR=1 -D UNROLL=1 -D FMA=0 -o src/f32-spmm/gen/16x1-m… [all …]
|
D | generate-f16-spmm.sh | 9 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=8 -D NR=1 -D UNROLL=1 -o src/f16-spmm/gen/8x1-mi… 10 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=16 -D NR=1 -D UNROLL=1 -o src/f16-spmm/gen/16x1-m… 11 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=24 -D NR=1 -D UNROLL=1 -o src/f16-spmm/gen/24x1-m… 12 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=32 -D NR=1 -D UNROLL=1 -o src/f16-spmm/gen/32x1-m… 14 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=8 -D NR=1 -D UNROLL=2 -o src/f16-spmm/gen/8x1-mi… 15 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=16 -D NR=1 -D UNROLL=2 -o src/f16-spmm/gen/16x1-m… 16 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=24 -D NR=1 -D UNROLL=2 -o src/f16-spmm/gen/24x1-m… 17 tools/xngen src/f16-spmm/neonfp16arith.c.in -D MR=32 -D NR=1 -D UNROLL=2 -o src/f16-spmm/gen/32x1-m…
|
/external/llvm-project/mlir/test/Conversion/VectorToSCF/ |
D | vector-to-loops.mlir | 2 …-convert-vector-to-scf=full-unroll=true -split-input-file | FileCheck %s --check-prefix=FULL-UNROLL 178 // FULL-UNROLL-DAG: #[[$MAP1:.*]] = affine_map<()[s0] -> (s0 + 1)> 179 // FULL-UNROLL-DAG: #[[$MAP2:.*]] = affine_map<()[s0] -> (s0 + 2)> 186 // FULL-UNROLL-LABEL: transfer_read_progressive( 187 // FULL-UNROLL-SAME: %[[A:[a-zA-Z0-9]+]]: memref<?x?xf32>, 188 // FULL-UNROLL-SAME: %[[base:[a-zA-Z0-9]+]]: index 210 // FULL-UNROLL: %[[pad:.*]] = constant 7.000000e+00 : f32 211 // FULL-UNROLL: %[[VEC0:.*]] = constant dense<7.000000e+00> : vector<3x15xf32> 212 // FULL-UNROLL: %[[C0:.*]] = constant 0 : index 213 // FULL-UNROLL: %[[SPLAT:.*]] = constant dense<7.000000e+00> : vector<15xf32> [all …]
|
/external/llvm/test/Transforms/LoopVectorize/ |
D | if-pred-stores.ll | 1 …terleave=2 -loop-vectorize -verify-loop-info -simplifycfg < %s | FileCheck %s --check-prefix=UNROLL 2 …interleave=2 -loop-vectorize -verify-loop-info < %s | FileCheck %s --check-prefix=UNROLL-NOSIMPLIFY 63 ; UNROLL-LABEL: test 64 ; UNROLL: vector.body: 65 ; UNROLL: %[[IND:[a-zA-Z0-9]+]] = add i64 %{{.*}}, 0 66 ; UNROLL: %[[IND1:[a-zA-Z0-9]+]] = add i64 %{{.*}}, 1 67 ; UNROLL: %[[v0:[a-zA-Z0-9]+]] = getelementptr inbounds i32, i32* %f, i64 %[[IND]] 68 ; UNROLL: %[[v1:[a-zA-Z0-9]+]] = getelementptr inbounds i32, i32* %f, i64 %[[IND1]] 69 ; UNROLL: %[[v2:[a-zA-Z0-9]+]] = load i32, i32* %[[v0]], align 4 70 ; UNROLL: %[[v3:[a-zA-Z0-9]+]] = load i32, i32* %[[v1]], align 4 [all …]
|
D | induction.ll | 3 …orce-vector-interleave=2 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=UNROLL 4 …rize -force-vector-interleave=2 -force-vector-width=2 -S | FileCheck %s --check-prefix=UNROLL-NO-IC 85 ; UNROLL-NO-IC-LABEL: @scalarize_induction_variable_01( 86 ; UNROLL-NO-IC: vector.body: 87 ; UNROLL-NO-IC: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ] 88 ; UNROLL-NO-IC: %[[i0:.+]] = add i64 %index, 0 89 ; UNROLL-NO-IC: %[[i1:.+]] = add i64 %index, 1 90 ; UNROLL-NO-IC: %[[i2:.+]] = add i64 %index, 2 91 ; UNROLL-NO-IC: %[[i3:.+]] = add i64 %index, 3 92 ; UNROLL-NO-IC: getelementptr inbounds i64, i64* %a, i64 %[[i0]] [all …]
|
D | gcc-examples.ll | 2 …-vector-width=4 -force-vector-interleave=4 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL 28 ;UNROLL-LABEL: @example1( 29 ;UNROLL: load <4 x i32> 30 ;UNROLL: load <4 x i32> 31 ;UNROLL: load <4 x i32> 32 ;UNROLL: load <4 x i32> 33 ;UNROLL: add nsw <4 x i32> 34 ;UNROLL: add nsw <4 x i32> 35 ;UNROLL: add nsw <4 x i32> 36 ;UNROLL: add nsw <4 x i32> [all …]
|
/external/llvm/test/Transforms/LoopVectorize/X86/ |
D | gcc-examples.ll | 2 ….0 -mcpu=corei7 -force-vector-interleave=0 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL 18 ;UNROLL-LABEL: @example1( 19 ;UNROLL: load <4 x i32> 20 ;UNROLL: load <4 x i32> 21 ;UNROLL: add nsw <4 x i32> 22 ;UNROLL: add nsw <4 x i32> 23 ;UNROLL: store <4 x i32> 24 ;UNROLL: store <4 x i32> 25 ;UNROLL: ret void 53 ;UNROLL-LABEL: @example10b( [all …]
|
/external/llvm-project/llvm/test/Transforms/LoopVectorize/X86/ |
D | gcc-examples.ll | 2 ….0 -mcpu=corei7 -force-vector-interleave=0 -dce -instcombine -S | FileCheck %s -check-prefix=UNROLL 18 ;UNROLL-LABEL: @example1( 19 ;UNROLL: load <4 x i32> 20 ;UNROLL: load <4 x i32> 21 ;UNROLL: add nsw <4 x i32> 22 ;UNROLL: add nsw <4 x i32> 23 ;UNROLL: store <4 x i32> 24 ;UNROLL: store <4 x i32> 25 ;UNROLL: ret void 53 ;UNROLL-LABEL: @example10b( [all …]
|
/external/llvm-project/llvm/test/Transforms/LoopUnroll/AArch64/ |
D | full-unroll-trip-count-upper-bound.ll | 1 ; RUN: opt -loop-unroll -S -mtriple aarch64 -mcpu=cortex-a57 %s | FileCheck %s -check-prefix=UNROLL 15 ; UNROLL-LABEL: @test 16 ; UNROLL: load i32, i32* 17 ; UNROLL: load i32, i32* 18 ; UNROLL: load i32, i32* 19 ; UNROLL: load i32, i32* 20 ; UNROLL-NOT: load i32, i32*
|
/external/llvm/test/Transforms/LoopVectorize/AArch64/ |
D | first-order-recurrence.ll | 2 …vector-width=4 -force-vector-interleave=2 -dce -instcombine -S | FileCheck %s --check-prefix=UNROLL 30 ; UNROLL: vector.body: 31 ; UNROLL: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ [[L2:%[a-zA-Z0-9.]+… 32 ; UNROLL: [[L1:%[a-zA-Z0-9.]+]] = load <4 x i32> 33 ; UNROLL: [[L2]] = load <4 x i32> 34 ; UNROLL: {{.*}} = shufflevector <4 x i32> %vector.recur, <4 x i32> [[L1]], <4 x i32> <i32 3, i32… 35 ; UNROLL: {{.*}} = shufflevector <4 x i32> [[L1]], <4 x i32> [[L2]], <4 x i32> <i32 3, i32 4, i32… 37 ; UNROLL: middle.block: 38 ; UNROLL: %vector.recur.extract = extractelement <4 x i32> [[L2]], i32 3 92 ; UNROLL: vector.body: [all …]
|
/external/llvm-project/llvm/test/Transforms/HardwareLoops/ARM/ |
D | structure.ll | 6 ; RUN: llc -mtriple=thumbv8.1m.main | FileCheck %s --check-prefix=CHECK-UNROLL 329 ; CHECK-UNROLL-LABEL: unroll_inc_int 330 ; CHECK-UNROLL: [[PREHEADER:.LBB[0-9_]+]]: @ %for.body.preheader 331 ; CHECK-UNROLL-NOT: dls 332 ; CHECK-UNROLL: [[LOOP:.LBB[0-9_]+]]: @ %for.body 333 ; CHECK-UNROLL-NOT: le lr, [[LOOP]] 334 ; CHECK-UNROLL: bne [[LOOP]] 335 ; CHECK-UNROLL: wls lr, lr, [[EXIT:.LBB[0-9_]+]] 336 ; CHECK-UNROLL: [[EPIL:.LBB[0-9_]+]]: 337 ; CHECK-UNROLL: le lr, [[EPIL]] [all …]
|
/external/XNNPACK/src/f16-spmm/ |
D | neonfp16arith.c.in | 15 void xnn_f16_spmm_minmax_ukernel_${MR}x${NR}__neonfp16arith${"_x%d" % UNROLL if UNROLL > 1 else ""}( 45 $if UNROLL > 1: 47 $for K in range(1, UNROLL): 51 $for K in range(1, UNROLL): 53 for (; nnz >= ${UNROLL}; nnz -= ${UNROLL}) { 54 $for K in range(UNROLL): 56 dmap += ${UNROLL}; 57 $for K in range(UNROLL): 68 $for K in range(1, UNROLL):
|
/external/XNNPACK/src/f32-spmm/ |
D | sse.c.in | 15 void xnn_f32_spmm_minmax_ukernel_${MR}x${NR}__sse${"_x" + str(UNROLL) if UNROLL > 1 else ""}( 40 $if UNROLL > 1: 43 $for K in range(1, UNROLL): 47 $for K in range(1, UNROLL): 49 for (; nnz >= ${UNROLL}; nnz -= ${UNROLL}) { 50 $for K in range(UNROLL): 52 dmap += ${UNROLL}; 53 $for K in range(UNROLL): 65 $for K in range(1, UNROLL):
|
D | neon.c.in | 17 …ax_ukernel_${MR}x${NR}__${"neonfma" if FMA else "neon"}${"_x" + str(UNROLL) if UNROLL > 1 else ""}( 42 $if UNROLL > 1: 44 $for K in range(1, UNROLL): 48 $for K in range(1, UNROLL): 50 for (; nnz >= ${UNROLL}; nnz -= ${UNROLL}) { 51 $for K in range(UNROLL): 53 dmap += ${UNROLL}; 54 $for K in range(UNROLL): 68 $for K in range(1, UNROLL):
|