| /llvm-project-15.0.7/llvm/test/CodeGen/AMDGPU/ |
| H A D | detect-dead-lanes.mir | 1 # RUN: llc -march=amdgcn -run-pass detect-dead-lanes -o - %s | FileCheck %s 42 # Check defined lanes transfer; Includes checking for some special cases like 122 # Check used lanes transfer; Includes checking for some special cases like 203 # Check that copies to physregs use all lanes, copies from physregs define all 204 # lanes. So we should not get a dead/undef flag here. 296 ; let's swiffle some lanes around for fun... 308 # for the used lanes. The example reads sub3 lane at the end, however with each 349 ; rotate lanes, but skip sub2 lane... 359 # Similar to loop1 test, but check for fixpoint of defined lanes. 392 ; rotate subreg lanes, skipping sub1
|
| H A D | combine-add-zext-xor.ll | 4 ; Test that unused lanes in the s_xor result are masked out with v_cndmask. 35 ; Test that unused lanes in the s_xor result are masked out with v_cndmask. 67 ; Test that unused lanes in the s_or result are masked out with v_cndmask. 100 ; Test that unused lanes in the s_or result are masked out with v_cndmask. 133 ; Test that unused lanes in the s_and result are masked out with v_cndmask. 166 ; Test that unused lanes in the s_and result are masked out with v_cndmask.
|
| H A D | dead-lane.mir | 1 # RUN: llc -march=amdgcn -mcpu=tonga %s -start-before detect-dead-lanes -stop-before machine-schedu… 2 # RUN: llc -march=amdgcn -mcpu=tonga %s -start-before detect-dead-lanes -stop-before machine-schedu…
|
| H A D | loop_exit_with_xor.ll | 3 ; Where the mask of lanes wanting to exit the loop on this iteration is not 35 ; Where the mask of lanes wanting to exit the loop on this iteration is 59 ; Another case where the mask of lanes wanting to exit the loop is not masked
|
| H A D | scalar-branch-missing-and-exec.ll | 9 ; without ensuring that the resulting mask has bits clear for inactive lanes. 11 ; set bits for inactive lanes.
|
| H A D | subreg-undef-def-with-other-subreg-defs.mir | 4 # Deciding which lanes are killed needs to account for other defs in the 8 # current vreg uses because it shared no lanes with %0.sub1 use on the
|
| H A D | at-least-one-def-value-assert.mir | 13 # used, but not defined. There are also lanes in %0 that are not used
|
| H A D | call-skip.ll | 3 ; A call should be skipped if all lanes are zero, since we don't know
|
| H A D | skip-branch-trap.ll | 5 ; An s_cbranch_execnz is required to avoid trapping if all lanes are 0
|
| H A D | regcoalesce-keep-valid-lanes-implicit-def-bug39602.mir | 5 # lanes on an implicit_def that later cannot be erased.
|
| H A D | extend-phi-subrange-not-in-parent.mir | 5 # the rest of the lanes). After %2 is split, after refineSubRanges the
|
| /llvm-project-15.0.7/llvm/test/MachineVerifier/ |
| H A D | test_g_fcmp.mir | 18 ; CHECK: Bad machine code: Generic vector icmp/fcmp must preserve number of lanes 22 ; CHECK: Bad machine code: Generic vector icmp/fcmp must preserve number of lanes
|
| H A D | test_g_icmp.mir | 18 ; CHECK: Bad machine code: Generic vector icmp/fcmp must preserve number of lanes 22 ; CHECK: Bad machine code: Generic vector icmp/fcmp must preserve number of lanes
|
| /llvm-project-15.0.7/openmp/libomptarget/DeviceRTL/src/ |
| H A D | Utils.cpp | 143 return impl::shuffleDown(lanes::All, Val, Delta, SrcLane); in __kmpc_shuffle_int32() 150 hi = impl::shuffleDown(lanes::All, hi, Delta, Width); in __kmpc_shuffle_int64() 151 lo = impl::shuffleDown(lanes::All, lo, Delta, Width); in __kmpc_shuffle_int64()
|
| /llvm-project-15.0.7/llvm/test/CodeGen/RISCV/rvv/ |
| H A D | constant-folding-crash.ll | 18 define void @constant_folding_crash(i8* %v54, <4 x <4 x i32>*> %lanes.a, <4 x <4 x i32>*> %lanes.b,… 78 %ptrs = select i1 %cmp, <4 x <4 x i32>*> %lanes.a, <4 x <4 x i32>*> %lanes.b
|
| /llvm-project-15.0.7/llvm/docs/ |
| H A D | AMDGPUModifierSyntax.rst | 142 all lanes in its group. 157 … Reverses the lanes for groups of 2, 4, 8, 16 or 32 lanes. 1116 Selects which lanes to pull data from, within a group of 8 lanes. This is a mandatory modifier. 1178 Note: the lanes of a wavefront are organized in four *rows* and four *banks*. 1218 Note: the lanes of a wavefront are organized in four *rows* and four *banks*. 1228 lanes in the row. 1256 Note: the lanes of a wavefront are organized in four *rows* and four *banks*. 1298 Note: the lanes of a wavefront are organized in four *rows* and four *banks*. 1324 Note: the lanes of a wavefront are organized in four *rows* and four *banks*. 1355 Note: the lanes of a wavefront are organized in four *rows* and four *banks*. [all …]
|
| /llvm-project-15.0.7/clang/include/clang/Basic/ |
| H A D | arm_neon_incl.td | 87 // - "H" - Halve the number of lanes in the type. 88 // - "D" - Double the number of lanes in the type. 104 // all lanes. The type of the vector is the base type of the intrinsic. 109 // the same type by duplicating the scalar value into all lanes. 168 // is a width in bits to reverse. The lanes this maps to is determined 173 // mask0 - The initial sequence of lanes for shuffle ARG0 175 // mask0 - The initial sequence of lanes for shuffle ARG1
|
| /llvm-project-15.0.7/mlir/include/mlir/Dialect/ArmSVE/ |
| H A D | ArmSVE.td | 63 op_description # [{ on active lanes. Inactive lanes will keep the value of 86 op_description # [{ on active lanes. Inactive lanes will keep the value of
|
| /llvm-project-15.0.7/llvm/test/CodeGen/SystemZ/ |
| H A D | regcoal-subranges-update.mir | 4 # Check that when we split the live-range with several active lanes 16 # clearing the dead value w.r.t. lanes when doing the splitting. I.e., we were ending
|
| H A D | regcoal-subranges-update-remat.mir | 5 # only a sub register, it sets the subranges of the unused lanes as being dead
|
| /llvm-project-15.0.7/llvm/lib/Target/AArch64/ |
| H A D | AArch64SchedAmpere1.td | 721 // -- Load 1-element structure to one/all lanes 722 // ---- all lanes 728 // -- Load 1-element structure to one/all lanes, 1D size 743 // -- Load 2-element structure to all lanes of 2 registers, 1D size 746 // -- Load 2-element structure to all lanes of 2 registers, other sizes 758 // -- Load 3-element structure to all lanes of 3 registers, 1D size 761 // -- Load 3-element structure to all lanes of 3 registers, other sizes 776 // -- Load 4-element structure to all lanes of 4 registers, 1D size 779 // -- Load 4-element structure to all lanes of 4 registers, other sizes
|
| H A D | AArch64SchedThunderX2T99.td | 1602 // ASIMD load, 1 element, all lanes, D-form, B/H/S 1603 // ASIMD load, 1 element, all lanes, D-form, D 1604 // ASIMD load, 1 element, all lanes, Q-form 1624 // ASIMD load, 2 element, all lanes, D-form, B/H/S 1625 // ASIMD load, 2 element, all lanes, D-form, D 1626 // ASIMD load, 2 element, all lanes, Q-form 1647 // ASIMD load, 3 element, all lanes, D-form, B/H/S 1648 // ASIMD load, 3 element, all lanes, D-form, D 1650 // ASIMD load, 3 element, all lanes, Q-form, D 1672 // ASIMD load, 4 element, all lanes, D-form, D [all …]
|
| H A D | AArch64SchedThunderX3T110.td | 1727 // ASIMD load, 1 element, all lanes, D-form, B/H/S 1728 // ASIMD load, 1 element, all lanes, D-form, D 1729 // ASIMD load, 1 element, all lanes, Q-form 1750 // ASIMD load, 2 element, all lanes, D-form, B/H/S 1751 // ASIMD load, 2 element, all lanes, D-form, D 1752 // ASIMD load, 2 element, all lanes, Q-form 1774 // ASIMD load, 3 element, all lanes, D-form, B/H/S 1775 // ASIMD load, 3 element, all lanes, D-form, D 1777 // ASIMD load, 3 element, all lanes, Q-form, D 1800 // ASIMD load, 4 element, all lanes, D-form, D [all …]
|
| /llvm-project-15.0.7/openmp/libomptarget/DeviceRTL/include/ |
| H A D | Types.h | 139 namespace lanes {
|
| /llvm-project-15.0.7/llvm/test/CodeGen/X86/ |
| H A D | vector-partial-undef.ll | 77 ; and undef, C --> 0, so this tests that we are tracking known zero lanes. 96 ; or undef, C --> -1, so this tests that we are tracking known all-ones lanes.
|