brintos

brintos / llvm-project-archived public Read only

0
0
Text · 8.2 KiB · ceef3fb Raw
146 lines · plain
1; Intel chips with slow unaligned memory accesses2 3; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=pentium3      2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SCALAR4; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=pentium3m     2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SCALAR5; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=pentium-m     2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE6; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=pentium4      2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE7; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=pentium4m     2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE8; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=yonah         2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE9; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=prescott      2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE10; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=nocona        2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE11; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=core2         2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE12; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=penryn        2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE13; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bonnell       2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE14 15; Intel chips with fast unaligned memory accesses16 17; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=silvermont     2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE18; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=nehalem        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE19; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=westmere       2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE20; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=sandybridge    2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX12821; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=ivybridge      2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX12822; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=haswell        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25623; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=broadwell      2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25624; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=knl            2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX51225; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=skylake-avx512 2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25626 27; AMD chips with slow unaligned memory accesses28 29; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=athlon-4      2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SCALAR30; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=athlon-xp     2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SCALAR31; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=k8            2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE32; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=opteron       2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE33; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=athlon64      2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE34; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=athlon-fx     2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE35; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=k8-sse3       2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE36; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=opteron-sse3  2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE37; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=athlon64-sse3 2>&1 | FileCheck %s --check-prefixes=SLOW,SLOW-SSE38 39; AMD chips with fast unaligned memory accesses40 41; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=amdfam10      2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE42; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=barcelona     2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE43; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=btver1        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE44; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=btver2        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25645; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver1        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25646; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver2        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25647; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver3        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25648; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=bdver4        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25649; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=znver1        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25650; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=znver2        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25651; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=znver3        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX25652; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=znver4        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX51253; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=znver5        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-AVX51254 55; Other chips with slow unaligned memory accesses56 57; RUN: llc < %s -mtriple=i386-unknown-unknown -mcpu=c3-2          2>&1 | FileCheck %s --check-prefixes=SLOW58 59; Verify that the slow/fast unaligned memory attribute is set correctly for each CPU model.60; Slow chips use 4-byte stores. Fast chips with SSE or later use something other than 4-byte stores.61; Chips that don't have SSE use 4-byte stores either way, so they're not tested.62 63; Also verify that SSE4.2 or SSE4a imply fast unaligned accesses.64 65; RUN: llc < %s -mtriple=i386-unknown-unknown -mattr=sse4.2       2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE66; RUN: llc < %s -mtriple=i386-unknown-unknown -mattr=sse4a        2>&1 | FileCheck %s --check-prefixes=FAST,FAST-SSE67 68; SLOW-NOT: not a recognized processor69; FAST-NOT: not a recognized processor70define void @store_zeros(ptr %a) {71; SLOW-SCALAR-LABEL: store_zeros:72; SLOW-SCALAR:       # %bb.0:73; SLOW-SCALAR-NEXT:    movl {{[0-9]+}}(%esp), %eax74; SLOW-SCALAR-NEXT:    movl $075; SLOW-SCALAR-NEXT:    movl $076; SLOW-SCALAR-NEXT:    movl $077; SLOW-SCALAR-NEXT:    movl $078; SLOW-SCALAR-NEXT:    movl $079; SLOW-SCALAR-NEXT:    movl $080; SLOW-SCALAR-NEXT:    movl $081; SLOW-SCALAR-NEXT:    movl $082; SLOW-SCALAR-NEXT:    movl $083; SLOW-SCALAR-NEXT:    movl $084; SLOW-SCALAR-NEXT:    movl $085; SLOW-SCALAR-NEXT:    movl $086; SLOW-SCALAR-NEXT:    movl $087; SLOW-SCALAR-NEXT:    movl $088; SLOW-SCALAR-NEXT:    movl $089; SLOW-SCALAR-NEXT:    movl $090; SLOW-SCALAR-NOT:     movl91;92; SLOW-SSE-LABEL: store_zeros:93; SLOW-SSE:       # %bb.0:94; SLOW-SSE-NEXT:    movl {{[0-9]+}}(%esp), %eax95; SLOW-SSE-NEXT:    xorps %xmm0, %xmm096; SLOW-SSE-NEXT:    movsd %xmm097; SLOW-SSE-NEXT:    movsd %xmm098; SLOW-SSE-NEXT:    movsd %xmm099; SLOW-SSE-NEXT:    movsd %xmm0100; SLOW-SSE-NEXT:    movsd %xmm0101; SLOW-SSE-NEXT:    movsd %xmm0102; SLOW-SSE-NEXT:    movsd %xmm0103; SLOW-SSE-NEXT:    movsd %xmm0104; SLOW-SSE-NOT:     movsd105;106; FAST-SSE-LABEL: store_zeros:107; FAST-SSE:       # %bb.0:108; FAST-SSE-NEXT:    movl {{[0-9]+}}(%esp), %eax109; FAST-SSE-NEXT:    xorps %xmm0, %xmm0110; FAST-SSE-NEXT:    movups %xmm0111; FAST-SSE-NEXT:    movups %xmm0112; FAST-SSE-NEXT:    movups %xmm0113; FAST-SSE-NEXT:    movups %xmm0114; FAST-SSE-NOT:     movups115;116; FAST-AVX128-LABEL: store_zeros:117; FAST-AVX128:       # %bb.0:118; FAST-AVX128-NEXT:    movl {{[0-9]+}}(%esp), %eax119; FAST-AVX128-NEXT:    vxorps %xmm0, %xmm0, %xmm0120; FAST-AVX128-NEXT:    vmovups %xmm0121; FAST-AVX128-NEXT:    vmovups %xmm0122; FAST-AVX128-NEXT:    vmovups %xmm0123; FAST-AVX128-NEXT:    vmovups %xmm0124; FAST-AVX128-NOT:     vmovups125;126; FAST-AVX256-LABEL: store_zeros:127; FAST-AVX256:       # %bb.0:128; FAST-AVX256-NEXT:    movl {{[0-9]+}}(%esp), %eax129; FAST-AVX256-NEXT:    vxorps %xmm0, %xmm0, %xmm0130; FAST-AVX256-NEXT:    vmovups %ymm0131; FAST-AVX256-NEXT:    vmovups %ymm0132; FAST-AVX256-NOT:     vmovups133;134; FAST-AVX512-LABEL: store_zeros:135; FAST-AVX512:       # %bb.0:136; FAST-AVX512-NEXT:    movl {{[0-9]+}}(%esp), %eax137; FAST-AVX512-NEXT:    vxorps %xmm0, %xmm0, %xmm0138; FAST-AVX512-NEXT:    vmovups %zmm0, (%eax)139; FAST-AVX512-NOT:     vmovups140  call void @llvm.memset.p0.i64(ptr %a, i8 0, i64 64, i1 false)141  ret void142}143 144declare void @llvm.memset.p0.i64(ptr nocapture, i8, i64, i1)145 146