diff --git a/llvm/lib/Target/PowerPC/PPCInstrVSX.td b/llvm/lib/Target/PowerPC/PPCInstrVSX.td --- a/llvm/lib/Target/PowerPC/PPCInstrVSX.td +++ b/llvm/lib/Target/PowerPC/PPCInstrVSX.td @@ -3924,8 +3924,20 @@ dag A = (i64 (PPCmfvsr (PPCfctiduz (f64 (load xoaddr:$A))))); } +// FP load dags (for f32 -> v4f32) +def LoadFP { + dag A = (f32 (load xoaddr:$A)); + dag B = (f32 (load xoaddr:$B)); + dag C = (f32 (load xoaddr:$C)); + dag D = (f32 (load xoaddr:$D)); +} + // FP merge dags (for f32 -> v4f32) def MrgFP { + dag LD32A = (COPY_TO_REGCLASS (LIWZX xoaddr:$A), VSRC); + dag LD32B = (COPY_TO_REGCLASS (LIWZX xoaddr:$B), VSRC); + dag LD32C = (COPY_TO_REGCLASS (LIWZX xoaddr:$C), VSRC); + dag LD32D = (COPY_TO_REGCLASS (LIWZX xoaddr:$D), VSRC); dag AC = (XVCVDPSP (XXPERMDI (COPY_TO_REGCLASS $A, VSRC), (COPY_TO_REGCLASS $C, VSRC), 0)); dag BD = (XVCVDPSP (XXPERMDI (COPY_TO_REGCLASS $B, VSRC), @@ -4081,7 +4093,18 @@ (v2f64 (XXPERMDI (COPY_TO_REGCLASS $A, VSRC), (COPY_TO_REGCLASS $B, VSRC), 0))>; - + // Using VMRGEW to assemble the final vector would be a lower latency + // solution. However, we choose to go with the slightly higher latency + // XXPERMDI for 2 reasons: + // 1. This is likely to occur in unrolled loops where regpressure is high, + // so we want to use the latter as it has access to all 64 VSX registers. + // 2. Using Altivec instructions in this sequence would likely cause the + // allocation of Altivec registers even for the loads which in turn would + // force the use of LXSIWZX for the loads, adding a cycle of latency to + // each of the loads which would otherwise be able to use LFIWZX. + def : Pat<(v4f32 (build_vector LoadFP.A, LoadFP.B, LoadFP.C, LoadFP.D)), + (v4f32 (XXPERMDI (XXMRGHW MrgFP.LD32A, MrgFP.LD32B), + (XXMRGHW MrgFP.LD32C, MrgFP.LD32D), 3))>; def : Pat<(v4f32 (build_vector f32:$A, f32:$B, f32:$C, f32:$D)), (VMRGEW MrgFP.AC, MrgFP.BD)>; def : Pat<(v4f32 (build_vector DblToFlt.A0, DblToFlt.A1, @@ -4148,7 +4171,18 @@ (v2f64 (XXPERMDI (COPY_TO_REGCLASS $B, VSRC), (COPY_TO_REGCLASS $A, VSRC), 0))>; - + // Using VMRGEW to assemble the final vector would be a lower latency + // solution. However, we choose to go with the slightly higher latency + // XXPERMDI for 2 reasons: + // 1. This is likely to occur in unrolled loops where regpressure is high, + // so we want to use the latter as it has access to all 64 VSX registers. + // 2. Using Altivec instructions in this sequence would likely cause the + // allocation of Altivec registers even for the loads which in turn would + // force the use of LXSIWZX for the loads, adding a cycle of latency to + // each of the loads which would otherwise be able to use LFIWZX. + def : Pat<(v4f32 (build_vector LoadFP.A, LoadFP.B, LoadFP.C, LoadFP.D)), + (v4f32 (XXPERMDI (XXMRGHW MrgFP.LD32D, MrgFP.LD32C), + (XXMRGHW MrgFP.LD32B, MrgFP.LD32A), 3))>; def : Pat<(v4f32 (build_vector f32:$D, f32:$C, f32:$B, f32:$A)), (VMRGEW MrgFP.AC, MrgFP.BD)>; def : Pat<(v4f32 (build_vector DblToFlt.A0, DblToFlt.A1, diff --git a/llvm/test/CodeGen/PowerPC/float-vector-gather.ll b/llvm/test/CodeGen/PowerPC/float-vector-gather.ll --- a/llvm/test/CodeGen/PowerPC/float-vector-gather.ll +++ b/llvm/test/CodeGen/PowerPC/float-vector-gather.ll @@ -1,6 +1,5 @@ ; NOTE: This test ensures that for both Big and Little Endian cases a set of -; NOTE: 4 floats is gathered into a v4f32 register using xxmrghd, xvcvdpsp, -; NOTE: and vmrgew. +; NOTE: 4 floats is gathered into a v4f32 register using xxmrghw and xxmrgld ; RUN: llc -verify-machineinstrs -mcpu=pwr9 -ppc-vsr-nums-as-vr \ ; RUN: -ppc-asm-full-reg-names -mtriple=powerpc64le-unknown-linux-gnu < %s \ ; RUN: | FileCheck %s -check-prefix=CHECK-LE @@ -16,28 +15,24 @@ ; } ; CHECK-LE-LABEL: vector_gatherf: ; CHECK-LE: # %bb.0: # %entry -; CHECK-LE-DAG: lfs f[[REG0:[0-9]+]], 0(r3) -; CHECK-LE-DAG: lfs f[[REG1:[0-9]+]], 0(r4) -; CHECK-LE-DAG: lfs f[[REG2:[0-9]+]], 0(r5) -; CHECK-LE-DAG: lfs f[[REG3:[0-9]+]], 0(r6) -; CHECK-LE-DAG: xxmrghd vs[[REG4:[0-9]+]], vs[[REG2]], vs[[REG0]] -; CHECK-LE-NEXT: xvcvdpsp v[[VREG2:[0-9]+]], vs[[REG4]] -; CHECK-LE-NEXT: xxmrghd vs[[REG5:[0-9]+]], vs[[REG3]], vs[[REG1]] -; CHECK-LE-NEXT: xvcvdpsp v[[VREG3:[0-9]+]], vs[[REG5]] -; CHECK-LE-NEXT: vmrgew v[[VREG:[0-9]+]], v[[VREG3]], v[[VREG2]] +; CHECK-LE-DAG: lfiwzx f[[REG0:[0-9]+]], 0, r6 +; CHECK-LE-DAG: lfiwzx f[[REG1:[0-9]+]], 0, r5 +; CHECK-LE-DAG: lfiwzx f[[REG2:[0-9]+]], 0, r4 +; CHECK-LE-DAG: lfiwzx f[[REG3:[0-9]+]], 0, r3 +; CHECK-LE-DAG: xxmrghw vs[[REG0]], vs[[REG0]], vs[[REG1]] +; CHECK-LE-DAG: xxmrghw vs[[REG4:[0-9]+]], vs[[REG2]], vs[[REG3]] +; CHECK-LE-NEXT: xxmrgld v[[REG:[0-9]+]], vs[[REG0]], vs[[REG4]] ; CHECK-LE-NEXT: blr ; CHECK-BE-LABEL: vector_gatherf: ; CHECK-BE: # %bb.0: # %entry -; CHECK-BE-DAG: lfs f[[REG0:[0-9]+]], 0(r3) -; CHECK-BE-DAG: lfs f[[REG1:[0-9]+]], 0(r4) -; CHECK-BE-DAG: lfs f[[REG2:[0-9]+]], 0(r5) -; CHECK-BE-DAG: lfs f[[REG3:[0-9]+]], 0(r6) -; CHECK-BE-DAG: xxmrghd vs[[REG4:[0-9]+]], vs[[REG0]], vs[[REG2]] -; CHECK-BE-DAG: xxmrghd vs[[REG5:[0-9]+]], vs[[REG1]], vs[[REG3]] -; CHECK-BE-NEXT: xvcvdpsp v[[VREG2:[0-9]+]], vs[[REG5]] -; CHECK-BE-NEXT: xvcvdpsp v[[VREG3:[0-9]+]], vs[[REG4]] -; CHECK-BE-NEXT: vmrgew v[[VREG:[0-9]+]], v[[VREG3]], v[[VREG2]] +; CHECK-BE-DAG: lfiwzx f[[REG0:[0-9]+]], 0, r3 +; CHECK-BE-DAG: lfiwzx f[[REG1:[0-9]+]], 0, r4 +; CHECK-BE-DAG: lfiwzx f[[REG2:[0-9]+]], 0, r5 +; CHECK-BE-DAG: lfiwzx f[[REG3:[0-9]+]], 0, r6 +; CHECK-BE-DAG: xxmrghw vs[[REG0]], vs[[REG0]], vs[[REG1]] +; CHECK-BE-DAG: xxmrghw vs[[REG4:[0-9]+]], vs[[REG2]], vs[[REG3]] +; CHECK-BE-NEXT: xxmrgld v[[REG:[0-9]+]], vs[[REG0]], vs[[REG4]] ; CHECK-BE-NEXT: blr entry: %0 = load float, float* %a, align 4