/external/libgav1/libgav1/src/dsp/x86/ |
D | common_avx2.h | 34 namespace avx2 { 48 using avx2::Load2; 49 using avx2::Load2x2; 50 using avx2::Load4; 51 using avx2::Load4x2; 52 using avx2::LoadAligned16; 53 using avx2::LoadAligned16Msan; 54 using avx2::LoadHi8; 55 using avx2::LoadHi8Msan; 56 using avx2::LoadLo8; [all …]
|
/external/XNNPACK/scripts/ |
D | generate-f32-vscaleexpminusmax.sh | 8 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=8 -o src/f32-vscaleexpminusmax/… 9 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=16 -o src/f32-vscaleexpminusmax… 10 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=24 -o src/f32-vscaleexpminusmax… 11 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=32 -o src/f32-vscaleexpminusmax… 12 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=40 -o src/f32-vscaleexpminusmax… 13 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=48 -o src/f32-vscaleexpminusmax… 14 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=56 -o src/f32-vscaleexpminusmax… 15 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=64 -o src/f32-vscaleexpminusmax… 16 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=72 -o src/f32-vscaleexpminusmax… 17 tools/xngen src/f32-vscaleexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=80 -o src/f32-vscaleexpminusmax… [all …]
|
D | generate-f32-vscaleextexp.sh | 8 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=8 -o src/f32-vscaleextexp/gen/avx2-p… 9 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=16 -o src/f32-vscaleextexp/gen/avx2-… 10 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=24 -o src/f32-vscaleextexp/gen/avx2-… 11 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=32 -o src/f32-vscaleextexp/gen/avx2-… 12 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=40 -o src/f32-vscaleextexp/gen/avx2-… 13 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=48 -o src/f32-vscaleextexp/gen/avx2-… 14 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=56 -o src/f32-vscaleextexp/gen/avx2-… 15 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=64 -o src/f32-vscaleextexp/gen/avx2-… 16 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=72 -o src/f32-vscaleextexp/gen/avx2-… 17 tools/xngen src/f32-vscaleextexp/avx2-p5.c.in -D ELEMENTS_TILE=80 -o src/f32-vscaleextexp/gen/avx2-… [all …]
|
D | generate-f32-raddextexp.sh | 8 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=64 -D ACCUMULATORS=1 -o src/f32-raddex… 9 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=64 -D ACCUMULATORS=2 -o src/f32-raddex… 10 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=64 -D ACCUMULATORS=4 -o src/f32-raddex… 11 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=72 -D ACCUMULATORS=1 -o src/f32-raddex… 12 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=72 -D ACCUMULATORS=3 -o src/f32-raddex… 13 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=80 -D ACCUMULATORS=1 -o src/f32-raddex… 14 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=80 -D ACCUMULATORS=2 -o src/f32-raddex… 15 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=80 -D ACCUMULATORS=5 -o src/f32-raddex… 16 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=96 -D ACCUMULATORS=1 -o src/f32-raddex… 17 tools/xngen src/f32-raddextexp/avx2-p5.c.in -D ELEMENTS_TILE=96 -D ACCUMULATORS=2 -o src/f32-raddex… [all …]
|
D | generate-f32-raddexpminusmax.sh | 8 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=64 -D ACCUMULATORS=1 -o src/f32-rad… 9 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=64 -D ACCUMULATORS=2 -o src/f32-rad… 10 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=64 -D ACCUMULATORS=4 -o src/f32-rad… 11 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=72 -D ACCUMULATORS=1 -o src/f32-rad… 12 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=72 -D ACCUMULATORS=3 -o src/f32-rad… 13 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=80 -D ACCUMULATORS=1 -o src/f32-rad… 14 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=80 -D ACCUMULATORS=2 -o src/f32-rad… 15 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=80 -D ACCUMULATORS=5 -o src/f32-rad… 16 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=96 -D ACCUMULATORS=1 -o src/f32-rad… 17 …ls/xngen src/f32-raddexpminusmax/avx2-p5.c.in -D ELEMENTS_TILE=96 -D ACCUMULATORS=2 -o src/f32-rad… [all …]
|
D | generate-f32-velu.sh | 146 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=8 -o src/f32-velu/gen/velu-avx2-… 147 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=16 -o src/f32-velu/gen/velu-avx2-… 148 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=24 -o src/f32-velu/gen/velu-avx2-… 149 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=32 -o src/f32-velu/gen/velu-avx2-… 150 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=40 -o src/f32-velu/gen/velu-avx2-… 151 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=48 -o src/f32-velu/gen/velu-avx2-… 152 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=56 -o src/f32-velu/gen/velu-avx2-… 153 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=64 -o src/f32-velu/gen/velu-avx2-… 154 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=72 -o src/f32-velu/gen/velu-avx2-… 155 tools/xngen src/f32-velu/avx2-rr1-lut4-p4-perm.c.in -D BATCH_TILE=80 -o src/f32-velu/gen/velu-avx2-… [all …]
|
D | generate-qs8-dwconv.sh | 32 …/xngen src/qs8-dwconv/unipass-avx2-mul16.c.in -D CHANNEL_TILE=16 -D KERNEL_TILE=9 -o src/qs8-dwcon… 33 …/xngen src/qs8-dwconv/unipass-avx2-mul16.c.in -D CHANNEL_TILE=32 -D KERNEL_TILE=9 -o src/qs8-dwcon… 35 …s/xngen src/qs8-dwconv/unipass-avx2-mul32.c.in -D CHANNEL_TILE=8 -D KERNEL_TILE=9 -o src/qs8-dwco… 36 …/xngen src/qs8-dwconv/unipass-avx2-mul32.c.in -D CHANNEL_TILE=16 -D KERNEL_TILE=9 -o src/qs8-dwcon… 37 …/xngen src/qs8-dwconv/unipass-avx2-mul32.c.in -D CHANNEL_TILE=24 -D KERNEL_TILE=9 -o src/qs8-dwcon… 38 …/xngen src/qs8-dwconv/unipass-avx2-mul32.c.in -D CHANNEL_TILE=32 -D KERNEL_TILE=9 -o src/qs8-dwcon…
|
/external/llvm/test/CodeGen/X86/ |
D | avx2-intrinsics-x86-upgrade.ll | 2 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mattr=avx2 | FileCheck %s 9 …%res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 7) ; <<16 x i16>… 12 declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i32) nounwind readnone 20 …%res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 7) ; <<4 x i32>… 23 declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i32) nounwind readnone 31 …%res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 7) ; <<8 x i32>… 34 declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i32) nounwind readnone 42 …%res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i32 7) ; <<16 x i16>> … 45 declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i32) nounwind readnone 53 %res = call <4 x i64> @llvm.x86.avx2.psll.dq.bs(<4 x i64> %a0, i32 7) ; <<4 x i64>> [#uses=1] [all …]
|
D | avx2-intrinsics-x86.ll | 2 ; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=avx2 | FileCheck %s --check-prefix=AVX2 15 …%res = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a0, <8 x i32> %a1) ; <<16 x i16>> [#uses… 18 declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>) nounwind readnone 31 …%res = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses… 34 declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>) nounwind readnone 47 …%res = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses… 50 declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>) nounwind readnone 63 %res = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a0, <32 x i8> %a1) ; <<32 x i8>> [#uses=1] 66 declare <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8>, <32 x i8>) nounwind readnone 79 …%res = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a0, <16 x i16> %a1) ; <<16 x i16>> [#use… [all …]
|
D | combine-avx2-intrinsics.ll | 1 ; RUN: llc < %s -march=x86-64 -mcpu=core-avx2 | FileCheck %s 7 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a0, i32 7) 16 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a0, i32 7) 25 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a0, i32 7) 34 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 0) 43 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 0) 52 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 0) 61 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 -1) 70 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 -1) 79 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 -1) [all …]
|
D | avx2-gather.ll | 2 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core-avx2 | FileCheck %s 4 declare <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float>, i8*, 9 %res = call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> undef, 21 declare <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double>, i8*, 26 %res = call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> undef, 36 declare <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float>, i8*, 41 %res = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, 49 declare <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double>, i8*, 54 %res = call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> undef,
|
D | stack-folding-int-avx2.ll | 1 ; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx2 < %s | FileCheck %s 20 declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly 31 declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly 42 declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly 68 %2 = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i8 7) 71 declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i8) nounwind readnone 77 %2 = call <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8> %a0) 80 declare <32 x i8> @llvm.x86.avx2.pabs.b(<32 x i8>) nounwind readnone 86 %2 = call <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32> %a0) 89 declare <8 x i32> @llvm.x86.avx2.pabs.d(<8 x i32>) nounwind readnone [all …]
|
/external/llvm-project/llvm/test/CodeGen/X86/ |
D | avx2-intrinsics-x86-upgrade.ll | 2 ; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=avx2 | FileCheck %s --check-prefixes=CHECK,X86 4 ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=avx2 | FileCheck %s --check-prefixes=CHECK,X64 12 …%res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 7) ; <<16 x i16>… 15 declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i32) nounwind readnone 23 …%res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 7) ; <<4 x i32>… 26 declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i32) nounwind readnone 34 …%res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 7) ; <<8 x i32>… 37 declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i32) nounwind readnone 51 %res = call <4 x i64> @llvm.x86.avx2.movntdqa(i8* %a0) ; <<4 x i64>> [#uses=1] 54 declare <4 x i64> @llvm.x86.avx2.movntdqa(i8*) nounwind readonly [all …]
|
D | combine-avx2-intrinsics.ll | 2 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s 11 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a0, i32 7) 19 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a0, i32 7) 27 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a0, i32 7) 35 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 0) 43 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 0) 51 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 0) 60 %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 -1) 69 %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 -1) 78 %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 -1) [all …]
|
D | avx2-intrinsics-x86.ll | 2 ; RUN: llc < %s -disable-peephole -mtriple=i686-unknown-unknown -mattr=avx2 -show-mc-encoding | Fil… 4 ; RUN: llc < %s -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=avx2 -show-mc-encoding | F… 17 …%res = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a0, <8 x i32> %a1) ; <<16 x i16>> [#uses… 20 declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>) nounwind readnone 51 …%res = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> zeroinitializer, <8 x i32> <i32 255, i32 … 66 …%res = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses… 69 declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>) nounwind readnone 100 …%res = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> <i16 0, i16 255, i16 256, i16 65535, i16 … 115 …%res = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a0, <16 x i16> %a1) ; <<32 x i8>> [#uses… 118 declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>) nounwind readnone [all …]
|
/external/tensorflow/third_party/jpeg/ |
D | BUILD.bazel | 185 "simd/x86_64/jccolor-avx2.o", 187 "simd/x86_64/jcgray-avx2.o", 191 "simd/x86_64/jcsample-avx2.o", 193 "simd/x86_64/jdcolor-avx2.o", 195 "simd/x86_64/jdmerge-avx2.o", 197 "simd/x86_64/jdsample-avx2.o", 201 "simd/x86_64/jfdctint-avx2.o", 205 "simd/x86_64/jidctint-avx2.o", 209 "simd/x86_64/jquanti-avx2.o", 223 "simd/x86_64/jccolext-avx2.asm", [all …]
|
/external/libaom/libaom/test/ |
D | intrapred_test.cc | 245 lowbd_entry(dc, 32, 32, avx2), lowbd_entry(dc_top, 32, 32, avx2), 246 lowbd_entry(dc_left, 32, 32, avx2), lowbd_entry(dc_128, 32, 32, avx2), 247 lowbd_entry(v, 32, 32, avx2), lowbd_entry(h, 32, 32, avx2), 248 lowbd_entry(dc, 32, 16, avx2), lowbd_entry(dc_top, 32, 16, avx2), 249 lowbd_entry(dc_left, 32, 16, avx2), lowbd_entry(dc_128, 32, 16, avx2), 250 lowbd_entry(v, 32, 16, avx2), lowbd_entry(paeth, 16, 8, avx2), 251 lowbd_entry(paeth, 16, 16, avx2), lowbd_entry(paeth, 16, 32, avx2), 252 lowbd_entry(paeth, 32, 16, avx2), lowbd_entry(paeth, 32, 32, avx2),
|
/external/libaom/libaom/av1/common/x86/ |
D | cfl_avx2.c | 20 CFL_SUBSAMPLE(avx2, sub, bd, 32, 32) \ 21 CFL_SUBSAMPLE(avx2, sub, bd, 32, 16) \ 22 CFL_SUBSAMPLE(avx2, sub, bd, 32, 8) \ 274 CFL_PREDICT_X(avx2, 32, 8, lbd); 275 CFL_PREDICT_X(avx2, 32, 16, lbd); 276 CFL_PREDICT_X(avx2, 32, 32, lbd); 344 CFL_PREDICT_X(avx2, 16, 4, hbd) 345 CFL_PREDICT_X(avx2, 16, 8, hbd) 346 CFL_PREDICT_X(avx2, 16, 16, hbd) 347 CFL_PREDICT_X(avx2, 16, 32, hbd) [all …]
|
/external/llvm/test/Transforms/InstCombine/ |
D | x86-vector-shifts.ll | 65 %1 = tail call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %v, i32 0) 74 %1 = tail call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %v, i32 15) 83 %1 = tail call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %v, i32 64) 91 %1 = tail call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %v, i32 0) 100 %1 = tail call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %v, i32 15) 109 %1 = tail call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %v, i32 64) 196 %1 = tail call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %v, i32 0) 205 %1 = tail call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %v, i32 15) 213 %1 = tail call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %v, i32 64) 221 %1 = tail call <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32> %v, i32 0) [all …]
|
/external/llvm-project/llvm/test/Analysis/BasicAA/ |
D | pr18573.ll | 3 ; Check that llvm.x86.avx2.gather.d.ps.256 intrinsic is not eliminated as gather and store memory a… 8 declare <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float>, i8*, <8 x i32>, <8 x float>, i8) #0 16 …%v1 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 19 …%v2 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 25 ; CHECK: llvm.x86.avx2.gather.d.ps.256 27 ; CHECK: llvm.x86.avx2.gather.d.ps.256 37 …%v1 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 40 …%v2 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 46 ; CHECK: llvm.x86.avx2.gather.d.ps.256 48 ; CHECK-NOT: llvm.x86.avx2.gather.d.ps.256 [all …]
|
/external/llvm/test/Analysis/BasicAA/ |
D | pr18573.ll | 3 ; Check that llvm.x86.avx2.gather.d.ps.256 intrinsic is not eliminated as gather and store memory a… 8 declare <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float>, i8*, <8 x i32>, <8 x float>, i8) #0 16 …%v1 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 19 …%v2 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 25 ; CHECK: llvm.x86.avx2.gather.d.ps.256 27 ; CHECK: llvm.x86.avx2.gather.d.ps.256 37 …%v1 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 40 …%v2 = tail call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arr.ptr, <8 x i… 46 ; CHECK: llvm.x86.avx2.gather.d.ps.256 48 ; CHECK-NOT: llvm.x86.avx2.gather.d.ps.256 [all …]
|
/external/libaom/libaom/aom_dsp/x86/ |
D | fft_avx2.c | 23 GEN_FFT_8(static INLINE void, avx2, float, __m256, _mm256_load_ps, 26 GEN_FFT_16(static INLINE void, avx2, float, __m256, _mm256_load_ps, 29 GEN_FFT_32(static INLINE void, avx2, float, __m256, _mm256_load_ps, 49 GEN_IFFT_8(static INLINE void, avx2, float, __m256, _mm256_load_ps, 52 GEN_IFFT_16(static INLINE void, avx2, float, __m256, _mm256_load_ps, 55 GEN_IFFT_32(static INLINE void, avx2, float, __m256, _mm256_load_ps,
|
/external/libjpeg-turbo/ |
D | BUILD.gn | 37 "simd/i386/jccolor-avx2.asm", 40 "simd/i386/jcgray-avx2.asm", 45 "simd/i386/jcsample-avx2.asm", 48 "simd/i386/jdcolor-avx2.asm", 51 "simd/i386/jdmerge-avx2.asm", 54 "simd/i386/jdsample-avx2.asm", 61 "simd/i386/jfdctint-avx2.asm", 69 "simd/i386/jidctint-avx2.asm", 78 "simd/i386/jquanti-avx2.asm", 89 "simd/x86_64/jccolor-avx2.asm", [all …]
|
D | Android.bp | 159 "simd/i386/jccolor-avx2.asm", 162 "simd/i386/jcgray-avx2.asm", 167 "simd/i386/jcsample-avx2.asm", 170 "simd/i386/jdcolor-avx2.asm", 173 "simd/i386/jdmerge-avx2.asm", 176 "simd/i386/jdsample-avx2.asm", 183 "simd/i386/jfdctint-avx2.asm", 191 "simd/i386/jidctint-avx2.asm", 200 "simd/i386/jquanti-avx2.asm", 214 "simd/x86_64/jccolor-avx2.asm", [all …]
|
/external/llvm-project/llvm/test/Transforms/InstCombine/X86/ |
D | x86-avx2.ll | 11 …%a = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 0, i32 1, i32 2, i32 3… 19 …%a = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 0, i32 1, i32 2, … 31 %a = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> zeroinitializer) 40 %a = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> zeroinitializer) 51 …%a = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 7, i32 6, i32 5, i32 4… 60 …%a = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 7, i32 6, i32 5, … 71 …%a = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> <i32 undef, i32 6, i32 5, i… 80 …%a = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> <i32 undef, i32 6, i32… 92 %2 = tail call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %1) 99 ; CHECK-NEXT: [[TMP1:%.*]] = tail call <8 x float> @llvm.x86.avx2.permps(<8 x float> [[A0:%.*]],… [all …]
|