llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fmul.mir

199 lines
7.5 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=fiji -run-pass=instruction-select -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN
---
name: fmul_f32
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $sgpr0, $vgpr0, $vgpr1, $vgpr3_vgpr4
; GCN-LABEL: name: fmul_f32
; GCN: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GCN: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GCN: [[COPY3:%[0-9]+]]:vreg_64 = COPY $vgpr3_vgpr4
; GCN: %4:vgpr_32 = nofpexcept V_MUL_F32_e64 0, [[COPY1]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %5:vgpr_32 = nofpexcept V_MUL_F32_e64 0, [[COPY]], 0, [[COPY1]], 0, 0, implicit $mode, implicit $exec
; GCN: %6:vgpr_32 = nofpexcept V_MUL_F32_e64 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GCN: FLAT_STORE_DWORD [[COPY3]], %4, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY3]], %5, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY3]], %6, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
%0:sgpr(s32) = COPY $sgpr0
%1:vgpr(s32) = COPY $vgpr0
%2:vgpr(s32) = COPY $vgpr1
%3:vgpr(p1) = COPY $vgpr3_vgpr4
; fmul vs
%4:vgpr(s32) = G_FMUL %1, %0
; fmul sv
%5:vgpr(s32) = G_FMUL %0, %1
; fmul vv
%6:vgpr(s32) = G_FMUL %1, %2
G_STORE %4, %3 :: (store (s32), addrspace 1)
G_STORE %5, %3 :: (store (s32), addrspace 1)
G_STORE %6, %3 :: (store (s32), addrspace 1)
...
---
name: fmul_f64
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $sgpr0_sgpr1, $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; GCN-LABEL: name: fmul_f64
; GCN: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
; GCN: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GCN: [[COPY2:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
; GCN: %4:vreg_64 = nofpexcept V_MUL_F64_e64 0, [[COPY1]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %5:vreg_64 = nofpexcept V_MUL_F64_e64 0, [[COPY]], 0, [[COPY1]], 0, 0, implicit $mode, implicit $exec
; GCN: %6:vreg_64 = nofpexcept V_MUL_F64_e64 0, [[COPY1]], 0, [[COPY2]], 0, 0, implicit $mode, implicit $exec
; GCN: S_ENDPGM 0, implicit %4, implicit %5, implicit %6
%0:sgpr(s64) = COPY $sgpr0_sgpr1
%1:vgpr(s64) = COPY $vgpr0_vgpr1
%2:vgpr(s64) = COPY $vgpr2_vgpr3
%3:vgpr(p1) = COPY $vgpr4_vgpr5
; fmul vs
%4:vgpr(s64) = G_FMUL %1, %0
; fmul sv
%5:vgpr(s64) = G_FMUL %0, %1
; fmul vv
%6:vgpr(s64) = G_FMUL %1, %2
S_ENDPGM 0, implicit %4, implicit %5, implicit %6
...
---
name: fmul_f16
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $sgpr0, $vgpr0, $vgpr1, $vgpr3_vgpr4
; GCN-LABEL: name: fmul_f16
; GCN: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; GCN: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: %7:vgpr_32 = nofpexcept V_MUL_F16_e64 0, [[COPY]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %8:vgpr_32 = nofpexcept V_MUL_F16_e64 0, [[COPY]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %9:vgpr_32 = nofpexcept V_MUL_F16_e64 0, [[COPY]], 0, [[COPY1]], 0, 0, implicit $mode, implicit $exec
; GCN: S_ENDPGM 0, implicit %7, implicit %8, implicit %9
%0:sgpr(s32) = COPY $sgpr0
%1:vgpr(s32) = COPY $vgpr0
%2:vgpr(s32) = COPY $vgpr1
%3:vgpr(p1) = COPY $vgpr3_vgpr4
%4:sgpr(s16) = G_TRUNC %0
%5:vgpr(s16) = G_TRUNC %1
%6:vgpr(s16) = G_TRUNC %2
; fmul vs
%8:vgpr(s16) = G_FMUL %4, %4
; fmul sv
%9:vgpr(s16) = G_FMUL %4, %4
; fmul vv
%10:vgpr(s16) = G_FMUL %4, %5
S_ENDPGM 0, implicit %8, implicit %9, implicit %10
...
---
name: fmul_modifiers_f32
legalized: true
regBankSelected: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2_vgpr3
; GCN-LABEL: name: fmul_modifiers_f32
; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: [[COPY1:%[0-9]+]]:vreg_64 = COPY $vgpr2_vgpr3
; GCN: %6:vgpr_32 = nofpexcept V_MUL_F32_e64 2, [[COPY]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %7:vgpr_32 = nofpexcept V_MUL_F32_e64 0, [[COPY]], 2, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %8:vgpr_32 = nofpexcept V_MUL_F32_e64 2, [[COPY]], 2, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %9:vgpr_32 = nofpexcept V_MUL_F32_e64 1, [[COPY]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %10:vgpr_32 = nofpexcept V_MUL_F32_e64 0, [[COPY]], 1, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %11:vgpr_32 = nofpexcept V_MUL_F32_e64 1, [[COPY]], 1, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %12:vgpr_32 = nofpexcept V_MUL_F32_e64 3, [[COPY]], 0, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %13:vgpr_32 = nofpexcept V_MUL_F32_e64 0, [[COPY]], 3, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %14:vgpr_32 = nofpexcept V_MUL_F32_e64 3, [[COPY]], 3, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: %15:vgpr_32 = nofpexcept V_MUL_F32_e64 3, [[COPY]], 1, [[COPY]], 0, 0, implicit $mode, implicit $exec
; GCN: FLAT_STORE_DWORD [[COPY1]], %6, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %7, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %8, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %9, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %10, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %11, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %12, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %13, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %14, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
; GCN: FLAT_STORE_DWORD [[COPY1]], %15, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1)
%0:vgpr(s32) = COPY $vgpr0
%1:vgpr(s32) = COPY $vgpr1
%2:vgpr(p1) = COPY $vgpr2_vgpr3
%3:vgpr(s32) = G_FABS %0
%4:vgpr(s32) = G_FNEG %0
%5:vgpr(s32) = G_FNEG %3
; fabs lhs
%6:vgpr(s32) = G_FMUL %3, %0
; fabs rhs
%7:vgpr(s32) = G_FMUL %0, %3
; fabs lhs, rhs
%8:vgpr(s32) = G_FMUL %3, %3
; fneg lhs
%9:vgpr(s32) = G_FMUL %4, %0
; fneg rhs
%10:vgpr(s32) = G_FMUL %0, %4
; fneg lhs, rhs
%11:vgpr(s32) = G_FMUL %4, %4
; fneg fabs lhs
%12:vgpr(s32) = G_FMUL %5, %0
; fneg fabs rhs
%13:vgpr(s32) = G_FMUL %0, %5
; fneg fabs lhs, rhs
%14:vgpr(s32) = G_FMUL %5, %5
; fneg fabs lhs, fneg rhs
%15:vgpr(s32) = G_FMUL %5, %4
G_STORE %6, %2 :: (store (s32), addrspace 1)
G_STORE %7, %2 :: (store (s32), addrspace 1)
G_STORE %8, %2 :: (store (s32), addrspace 1)
G_STORE %9, %2 :: (store (s32), addrspace 1)
G_STORE %10, %2 :: (store (s32), addrspace 1)
G_STORE %11, %2 :: (store (s32), addrspace 1)
G_STORE %12, %2 :: (store (s32), addrspace 1)
G_STORE %13, %2 :: (store (s32), addrspace 1)
G_STORE %14, %2 :: (store (s32), addrspace 1)
G_STORE %15, %2 :: (store (s32), addrspace 1)
...