| # REQUIRES: asserts |
| # RUN: llc -mtriple=amdgcn -mcpu=gfx908 -verify-misched -run-pass=machine-scheduler -verify-misched -debug-only=machine-scheduler -o - %s 2>&1 | FileCheck -check-prefix=GCN %s |
| # RUN: llc -mtriple=amdgcn -mcpu=gfx908 -verify-misched -run-pass=machine-scheduler -amdgpu-use-amdgpu-trackers=1 -verify-misched -debug-only=machine-scheduler -o - %s 2>&1 | FileCheck -check-prefix=GCN-GCNTRACKER %s |
| |
| --- | |
| define amdgpu_kernel void @high-RP-reschedule() { ret void } |
| ... |
| |
| # GCN: Unclustered High Register Pressure Reschedule stage successfully increased occupancy to 4 |
| |
| # GCN-GCNTRACKER: Occupancy before scheduling: 3, after 4. |
| # GCN-GCNTRACKER-NEXT: Ending scheduling stage: Max Occupancy Initial Schedule |
| |
| # When using the GCN Trackers, the scheduler is able to acieve desired occupancy without running high-RP-reschedule stage. |
| |
| --- |
| name: high-RP-reschedule |
| tracksRegLiveness: true |
| machineFunctionInfo: |
| occupancy: 4 |
| body: | |
| bb.0: |
| %0:vreg_128 = IMPLICIT_DEF |
| %1:vreg_128 = IMPLICIT_DEF |
| %2:vgpr_32 = IMPLICIT_DEF |
| %3:vreg_128 = IMPLICIT_DEF |
| %4:vreg_128 = IMPLICIT_DEF |
| %5:vreg_128 = IMPLICIT_DEF |
| %6:vreg_128 = IMPLICIT_DEF |
| %7:vreg_128 = IMPLICIT_DEF |
| %8:vreg_128 = IMPLICIT_DEF |
| %9:vreg_128 = IMPLICIT_DEF |
| %10:vreg_128 = IMPLICIT_DEF |
| %11:sreg_64_xexec_xnull = IMPLICIT_DEF |
| %12:vreg_64 = IMPLICIT_DEF |
| |
| bb.1: |
| %13:vgpr_32 = V_LSHRREV_B16_e32 1, %12.sub0, implicit $exec |
| %14:vgpr_32 = V_AND_B32_e32 127, %13, implicit $exec |
| %15:vgpr_32 = V_MUL_LO_U16_e32 49, %14, implicit $exec |
| %16:vgpr_32 = V_LSHRREV_B16_e32 10, %15, implicit $exec |
| %17:vgpr_32 = V_MUL_LO_U16_e32 42, %16, implicit $exec |
| %18:vgpr_32 = V_SUB_U16_e32 %12.sub0, %17, implicit $exec |
| %19:vgpr_32 = V_MOV_B32_e32 7, implicit $exec |
| %20:vgpr_32 = V_MUL_U32_U24_sdwa 0, %18, 0, %19, 0, 6, 0, 0, 6, implicit $exec |
| %21:vgpr_32 = V_LSHLREV_B32_e32 4, %20, implicit $exec |
| %22:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 608, 0, implicit $exec :: (load (s128)) |
| %23:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 576, 0, implicit $exec :: (load (s128)) |
| %24:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 592, 0, implicit $exec :: (load (s128)) |
| %25:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 624, 0, implicit $exec :: (load (s128)) |
| %26:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 672, 0, implicit $exec :: (load (s128)) |
| %27:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 640, 0, implicit $exec :: (load (s128)) |
| %28:vreg_128 = GLOBAL_LOAD_DWORDX4_SADDR %11, %21, 656, 0, implicit $exec :: (load (s128)) |
| %29:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %7.sub2_sub3, 0, %25.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %30:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %7.sub2_sub3, 0, %25.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %31:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %7.sub0_sub1, 0, %25.sub0_sub1, 1, %29, 0, 0, implicit $mode, implicit $exec |
| %32:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %7.sub0_sub1, 0, %25.sub2_sub3, 0, %30, 0, 0, implicit $mode, implicit $exec |
| %33:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %5.sub2_sub3, 0, %24.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %34:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %5.sub2_sub3, 0, %24.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %35:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %5.sub0_sub1, 0, %24.sub0_sub1, 1, %33, 0, 0, implicit $mode, implicit $exec |
| %36:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %5.sub0_sub1, 0, %24.sub2_sub3, 0, %34, 0, 0, implicit $mode, implicit $exec |
| %37:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %9.sub2_sub3, 0, %28.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %38:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %9.sub2_sub3, 0, %28.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %39:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %9.sub0_sub1, 0, %28.sub0_sub1, 1, %37, 0, 0, implicit $mode, implicit $exec |
| %40:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %9.sub0_sub1, 0, %28.sub2_sub3, 0, %38, 0, 0, implicit $mode, implicit $exec |
| %41:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %4.sub2_sub3, 0, %23.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %42:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %4.sub2_sub3, 0, %23.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %43:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %4.sub0_sub1, 0, %23.sub0_sub1, 1, %41, 0, 0, implicit $mode, implicit $exec |
| %44:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %4.sub0_sub1, 0, %23.sub2_sub3, 0, %42, 0, 0, implicit $mode, implicit $exec |
| %45:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %8.sub2_sub3, 0, %27.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %46:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %8.sub2_sub3, 0, %27.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %47:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %6.sub2_sub3, 0, %22.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %48:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %8.sub0_sub1, 0, %27.sub0_sub1, 1, %45, 0, 0, implicit $mode, implicit $exec |
| %49:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %8.sub0_sub1, 0, %27.sub2_sub3, 0, %46, 0, 0, implicit $mode, implicit $exec |
| %50:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %10.sub2_sub3, 0, %26.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %51:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %6.sub2_sub3, 0, %22.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %52:vreg_64 = contract nofpexcept V_MUL_F64_e64 0, %10.sub2_sub3, 0, %26.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %53:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %6.sub0_sub1, 0, %22.sub0_sub1, 1, %47, 0, 0, implicit $mode, implicit $exec |
| %54:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %10.sub0_sub1, 0, %26.sub0_sub1, 1, %50, 0, 0, implicit $mode, implicit $exec |
| %55:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %6.sub0_sub1, 0, %22.sub2_sub3, 0, %51, 0, 0, implicit $mode, implicit $exec |
| %56:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %10.sub0_sub1, 0, %26.sub2_sub3, 0, %52, 0, 0, implicit $mode, implicit $exec |
| %57:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %3.sub2_sub3, 1, %32, 0, 0, implicit $mode, implicit $exec |
| %58:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %35, 1, %39, 0, 0, implicit $mode, implicit $exec |
| %59:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %44, 1, %49, 0, 0, implicit $mode, implicit $exec |
| %60:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %53, 1, %54, 0, 0, implicit $mode, implicit $exec |
| %61:sreg_64 = S_MOV_B64_IMM_PSEUDO 4604544271217802189 |
| %62:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %3.sub0_sub1, 1, %31, 0, 0, implicit $mode, implicit $exec |
| undef %63.sub1:sreg_64 = S_MOV_B32 -1075404642 |
| %64:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %36, 1, %40, 0, 0, implicit $mode, implicit $exec |
| %65:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %43, 1, %48, 0, 0, implicit $mode, implicit $exec |
| %66:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %55, 1, %56, 0, 0, implicit $mode, implicit $exec |
| %67:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %57, 0, %58, 0, 0, implicit $mode, implicit $exec |
| %68:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %59, 0, %60, 0, 0, implicit $mode, implicit $exec |
| %69:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %3.sub2_sub3, 0, 4611686018427387904, 1, %57, 0, 0, implicit $mode, implicit $exec |
| %70:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %3.sub0_sub1, 0, 4611686018427387904, 1, %62, 0, 0, implicit $mode, implicit $exec |
| %71:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %35, 0, 4611686018427387904, 1, %58, 0, 0, implicit $mode, implicit $exec |
| %72:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %36, 0, 4611686018427387904, 1, %64, 0, 0, implicit $mode, implicit $exec |
| %73:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %43, 0, 4611686018427387904, 1, %65, 0, 0, implicit $mode, implicit $exec |
| %74:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %44, 0, 4611686018427387904, 1, %59, 0, 0, implicit $mode, implicit $exec |
| %75:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %55, 0, 4611686018427387904, 1, %66, 0, 0, implicit $mode, implicit $exec |
| %76:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %53, 0, 4611686018427387904, 1, %60, 0, 0, implicit $mode, implicit $exec |
| %77:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %62, 1, %64, 0, 0, implicit $mode, implicit $exec |
| %78:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %65, 1, %66, 0, 0, implicit $mode, implicit $exec |
| %79:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %70, 1, %71, 0, 0, implicit $mode, implicit $exec |
| %80:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %57, 0, 4611686018427387904, 1, %67, 0, 0, implicit $mode, implicit $exec |
| %81:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %59, 0, 4611686018427387904, 1, %68, 0, 0, implicit $mode, implicit $exec |
| %82:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %69, 1, %72, 0, 0, implicit $mode, implicit $exec |
| %83:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %74, 1, %75, 0, 0, implicit $mode, implicit $exec |
| %84:vreg_64 = contract nofpexcept V_ADD_F64_e64 0, %73, 1, %76, 0, 0, implicit $mode, implicit $exec |
| %85:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %62, 0, 4611686018427387904, 1, %77, 0, 0, implicit $mode, implicit $exec |
| %86:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %65, 0, 4611686018427387904, 1, %78, 0, 0, implicit $mode, implicit $exec |
| %63.sub0:sreg_64 = COPY %61.sub0 |
| %87:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %68, 0, %61, 0, %67, 0, 0, implicit $mode, implicit $exec |
| %88:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %81, 0, %63, 0, %80, 0, 0, implicit $mode, implicit $exec |
| %89:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %70, 0, 4611686018427387904, 1, %79, 0, 0, implicit $mode, implicit $exec |
| %90:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %69, 0, 4611686018427387904, 1, %82, 0, 0, implicit $mode, implicit $exec |
| %91:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %74, 0, 4611686018427387904, 1, %83, 0, 0, implicit $mode, implicit $exec |
| %92:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %73, 0, 4611686018427387904, 1, %84, 0, 0, implicit $mode, implicit $exec |
| %93:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %86, 0, %63, 0, %85, 0, 0, implicit $mode, implicit $exec |
| %94:vreg_64 = contract nofpexcept V_FMA_F64_e64 0, %78, 0, %61, 0, %77, 0, 0, implicit $mode, implicit $exec |
| undef %95.sub2_sub3:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %78, 0, %61, 0, %87, 0, 0, implicit $mode, implicit $exec |
| undef %96.sub2_sub3:vreg_128 = contract nofpexcept V_ADD_F64_e64 0, %82, 0, %84, 0, 0, implicit $mode, implicit $exec |
| undef %97.sub2_sub3:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %86, 0, %61, 0, %88, 0, 0, implicit $mode, implicit $exec |
| undef %98.sub2_sub3:vreg_128 = contract nofpexcept V_ADD_F64_e64 0, %90, 1, %91, 0, 0, implicit $mode, implicit $exec |
| %98.sub0_sub1:vreg_128 = contract nofpexcept V_ADD_F64_e64 0, %89, 1, %92, 0, 0, implicit $mode, implicit $exec |
| %97.sub0_sub1:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %81, 0, %63, 0, %93, 0, 0, implicit $mode, implicit $exec |
| %96.sub0_sub1:vreg_128 = contract nofpexcept V_ADD_F64_e64 0, %79, 1, %83, 0, 0, implicit $mode, implicit $exec |
| %95.sub0_sub1:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %68, 0, %63, 0, %94, 0, 0, implicit $mode, implicit $exec |
| undef %99.sub2_sub3:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %67, 0, 4611686018427387904, 1, %95.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| undef %100.sub2_sub3:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %82, 0, 4611686018427387904, 1, %96.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| undef %101.sub2_sub3:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %80, 0, 4611686018427387904, 1, %97.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| undef %102.sub2_sub3:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %90, 0, 4611686018427387904, 1, %98.sub2_sub3, 0, 0, implicit $mode, implicit $exec |
| %102.sub0_sub1:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %89, 0, 4611686018427387904, 1, %98.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %101.sub0_sub1:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %85, 0, 4611686018427387904, 1, %97.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %100.sub0_sub1:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %79, 0, 4611686018427387904, 1, %96.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %99.sub0_sub1:vreg_128 = contract nofpexcept V_FMA_F64_e64 0, %77, 0, 4611686018427387904, 1, %95.sub0_sub1, 0, 0, implicit $mode, implicit $exec |
| %103:vgpr_32 = V_ADD_U32_sdwa 0, %2, 0, %18, 0, 6, 0, 6, 0, implicit $exec |
| %104:vgpr_32 = V_LSHL_ADD_U32_e64 %103, 4, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %102, 0, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %101, 672, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %100, 1344, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %99, 2016, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %98, 2688, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %97, 3360, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %96, 4032, 0, implicit $exec |
| DS_WRITE_B128_gfx9 %104, %95, 4704, 0, implicit $exec |
| |
| bb.2: |
| S_ENDPGM 0, implicit %0, implicit %1 |
| ... |
