llvm-6502/test/CodeGen/R600/trunc.ll
Matt Arsenault f1b16047b7 R600/SI: Prefer selecting more e64 instruction forms.
Add some more tests to make sure better operand
choices are still made. Leave some cases that seem
to have no reason to ever be e64 alone.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217789 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-15 17:15:02 +00:00

68 lines
2.4 KiB
LLVM

; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs< %s | FileCheck -check-prefix=SI %s
; RUN: llc -march=r600 -mcpu=cypress < %s | FileCheck -check-prefix=EG %s
define void @trunc_i64_to_i32_store(i32 addrspace(1)* %out, i64 %in) {
; SI-LABEL: @trunc_i64_to_i32_store
; SI: S_LOAD_DWORD [[SLOAD:s[0-9]+]], s[0:1], 0xb
; SI: V_MOV_B32_e32 [[VLOAD:v[0-9]+]], [[SLOAD]]
; SI: BUFFER_STORE_DWORD [[VLOAD]]
; EG-LABEL: @trunc_i64_to_i32_store
; EG: MEM_RAT_CACHELESS STORE_RAW T0.X, T1.X, 1
; EG: LSHR
; EG-NEXT: 2(
%result = trunc i64 %in to i32 store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: @trunc_load_shl_i64:
; SI-DAG: S_LOAD_DWORDX2
; SI-DAG: S_LOAD_DWORD [[SREG:s[0-9]+]],
; SI: S_LSHL_B32 [[SHL:s[0-9]+]], [[SREG]], 2
; SI: V_MOV_B32_e32 [[VSHL:v[0-9]+]], [[SHL]]
; SI: BUFFER_STORE_DWORD [[VSHL]],
define void @trunc_load_shl_i64(i32 addrspace(1)* %out, i64 %a) {
%b = shl i64 %a, 2
%result = trunc i64 %b to i32
store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: @trunc_shl_i64:
; SI: S_LOAD_DWORDX2 s{{\[}}[[LO_SREG:[0-9]+]]:{{[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd
; SI: S_LSHL_B64 s{{\[}}[[LO_SHL:[0-9]+]]:{{[0-9]+\]}}, s{{\[}}[[LO_SREG]]:{{[0-9]+\]}}, 2
; SI: S_ADD_U32 s[[LO_SREG2:[0-9]+]], s[[LO_SHL]],
; SI: S_ADDC_U32
; SI: V_MOV_B32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG2]]
; SI: BUFFER_STORE_DWORD v[[LO_VREG]],
define void @trunc_shl_i64(i64 addrspace(1)* %out2, i32 addrspace(1)* %out, i64 %a) {
%aa = add i64 %a, 234 ; Prevent shrinking store.
%b = shl i64 %aa, 2
%result = trunc i64 %b to i32
store i32 %result, i32 addrspace(1)* %out, align 4
store i64 %b, i64 addrspace(1)* %out2, align 8 ; Prevent reducing ops to 32-bits
ret void
}
; SI-LABEL: @trunc_i32_to_i1:
; SI: V_AND_B32_e32 v{{[0-9]+}}, 1, v{{[0-9]+}}
; SI: V_CMP_EQ_I32
define void @trunc_i32_to_i1(i32 addrspace(1)* %out, i32 addrspace(1)* %ptr) {
%a = load i32 addrspace(1)* %ptr, align 4
%trunc = trunc i32 %a to i1
%result = select i1 %trunc, i32 1, i32 0
store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}
; SI-LABEL: @sgpr_trunc_i32_to_i1:
; SI: V_AND_B32_e64 v{{[0-9]+}}, 1, s{{[0-9]+}}
; SI: V_CMP_EQ_I32
define void @sgpr_trunc_i32_to_i1(i32 addrspace(1)* %out, i32 %a) {
%trunc = trunc i32 %a to i1
%result = select i1 %trunc, i32 1, i32 0
store i32 %result, i32 addrspace(1)* %out, align 4
ret void
}