mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-06 09:54:49 +00:00
X86 instruction tables. Also (while I was at it) cleaned up the X86 tables, removing tabs and 80-line violations. This patch was reviewed by Chris Lattner, but please let me know if there are any problems. * X86*.td Removed tabs and fixed 80-line violations * X86Instr64bit.td (IRET, POPCNT, BT_, LSL, SWPGS, PUSH_S, POP_S, L_S, SMSW) Added (CALL, CMOV) Added qualifiers (JMP) Added PC-relative jump instruction (POPFQ/PUSHFQ) Added qualifiers; renamed PUSHFQ to indicate that it is 64-bit only (ambiguous since it has no REX prefix) (MOV) Added rr form going the other way, which is encoded differently (MOV) Changed immediates to offsets, which is more correct; also fixed MOV64o64a to have to a 64-bit offset (MOV) Fixed qualifiers (MOV) Added debug-register and condition-register moves (MOVZX) Added more forms (ADC, SUB, SBB, AND, OR, XOR) Added reverse forms, which (as with MOV) are encoded differently (ROL) Made REX.W required (BT) Uncommented mr form for disassembly only (CVT__2__) Added several missing non-intrinsic forms (LXADD, XCHG) Reordered operands to make more sense for MRMSrcMem (XCHG) Added register-to-register forms (XADD, CMPXCHG, XCHG) Added non-locked forms * X86InstrSSE.td (CVTSS2SI, COMISS, CVTTPS2DQ, CVTPS2PD, CVTPD2PS, MOVQ) Added * X86InstrFPStack.td (COM_FST0, COMP_FST0, COM_FI, COM_FIP, FFREE, FNCLEX, FNOP, FXAM, FLDL2T, FLDL2E, FLDPI, FLDLG2, FLDLN2, F2XM1, FYL2X, FPTAN, FPATAN, FXTRACT, FPREM1, FDECSTP, FINCSTP, FPREM, FYL2XP1, FSINCOS, FRNDINT, FSCALE, FCOMPP, FXSAVE, FXRSTOR) Added (FCOM, FCOMP) Added qualifiers (FSTENV, FSAVE, FSTSW) Fixed opcode names (FNSTSW) Added implicit register operand * X86InstrInfo.td (opaque512mem) Added for FXSAVE/FXRSTOR (offset8, offset16, offset32, offset64) Added for MOV (NOOPW, IRET, POPCNT, IN, BTC, BTR, BTS, LSL, INVLPG, STR, LTR, PUSHFS, PUSHGS, POPFS, POPGS, LDS, LSS, LES, LFS, LGS, VERR, VERW, SGDT, SIDT, SLDT, LGDT, LIDT, LLDT, LODSD, OUTSB, OUTSW, OUTSD, HLT, RSM, FNINIT, CLC, STC, CLI, STI, CLD, STD, CMC, CLTS, XLAT, WRMSR, RDMSR, RDPMC, SMSW, LMSW, CPUID, INVD, WBINVD, INVEPT, INVVPID, VMCALL, VMCLEAR, VMLAUNCH, VMRESUME, VMPTRLD, VMPTRST, VMREAD, VMWRITE, VMXOFF, VMXON) Added (NOOPL, POPF, POPFD, PUSHF, PUSHFD) Added qualifier (JO, JNO, JB, JAE, JE, JNE, JBE, JA, JS, JNS, JP, JNP, JL, JGE, JLE, JG, JCXZ) Added 32-bit forms (MOV) Changed some immediate forms to offset forms (MOV) Added reversed reg-reg forms, which are encoded differently (MOV) Added debug-register and condition-register moves (CMOV) Added qualifiers (AND, OR, XOR, ADC, SUB, SBB) Added reverse forms, like MOV (BT) Uncommented memory-register forms for disassembler (MOVSX, MOVZX) Added forms (XCHG, LXADD) Made operand order make sense for MRMSrcMem (XCHG) Added register-register forms (XADD, CMPXCHG) Added unlocked forms * X86InstrMMX.td (MMX_MOVD, MMV_MOVQ) Added forms * X86InstrInfo.cpp: Changed PUSHFQ to PUSHFQ64 to reflect table change * X86RegisterInfo.td: Added debug and condition register sets * x86-64-pic-3.ll: Fixed testcase to reflect call qualifier * peep-test-3.ll: Fixed testcase to reflect test qualifier * cmov.ll: Fixed testcase to reflect cmov qualifier * loop-blocks.ll: Fixed testcase to reflect call qualifier * x86-64-pic-11.ll: Fixed testcase to reflect call qualifier * 2009-11-04-SubregCoalescingBug.ll: Fixed testcase to reflect call qualifier * x86-64-pic-2.ll: Fixed testcase to reflect call qualifier * live-out-reg-info.ll: Fixed testcase to reflect test qualifier * tail-opts.ll: Fixed testcase to reflect call qualifiers * x86-64-pic-10.ll: Fixed testcase to reflect call qualifier * bss-pagealigned.ll: Fixed testcase to reflect call qualifier * x86-64-pic-1.ll: Fixed testcase to reflect call qualifier * widen_load-1.ll: Fixed testcase to reflect call qualifier git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@91638 91177308-0d34-0410-b5e6-96231b3b80d8
208 lines
4.4 KiB
LLVM
208 lines
4.4 KiB
LLVM
; RUN: llc < %s -march=x86-64 -mtriple=x86_64-unknown-linux-gnu -asm-verbose=false | FileCheck %s
|
|
|
|
; These tests check for loop branching structure, and that the loop align
|
|
; directive is placed in the expected place.
|
|
|
|
; CodeGen should insert a branch into the middle of the loop in
|
|
; order to avoid a branch within the loop.
|
|
|
|
; CHECK: simple:
|
|
; CHECK: jmp .LBB1_1
|
|
; CHECK-NEXT: align
|
|
; CHECK-NEXT: .LBB1_2:
|
|
; CHECK-NEXT: callq loop_latch
|
|
; CHECK-NEXT: .LBB1_1:
|
|
; CHECK-NEXT: callq loop_header
|
|
|
|
define void @simple() nounwind {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
call void @loop_header()
|
|
%t0 = tail call i32 @get()
|
|
%t1 = icmp slt i32 %t0, 0
|
|
br i1 %t1, label %done, label %bb
|
|
|
|
bb:
|
|
call void @loop_latch()
|
|
br label %loop
|
|
|
|
done:
|
|
call void @exit()
|
|
ret void
|
|
}
|
|
|
|
; CodeGen should move block_a to the top of the loop so that it
|
|
; falls through into the loop, avoiding a branch within the loop.
|
|
|
|
; CHECK: slightly_more_involved:
|
|
; CHECK: jmp .LBB2_1
|
|
; CHECK-NEXT: align
|
|
; CHECK-NEXT: .LBB2_4:
|
|
; CHECK-NEXT: callq bar99
|
|
; CHECK-NEXT: .LBB2_1:
|
|
; CHECK-NEXT: callq body
|
|
|
|
define void @slightly_more_involved() nounwind {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
call void @body()
|
|
%t0 = call i32 @get()
|
|
%t1 = icmp slt i32 %t0, 2
|
|
br i1 %t1, label %block_a, label %bb
|
|
|
|
bb:
|
|
%t2 = call i32 @get()
|
|
%t3 = icmp slt i32 %t2, 99
|
|
br i1 %t3, label %exit, label %loop
|
|
|
|
block_a:
|
|
call void @bar99()
|
|
br label %loop
|
|
|
|
exit:
|
|
call void @exit()
|
|
ret void
|
|
}
|
|
|
|
; Same as slightly_more_involved, but block_a is now a CFG diamond with
|
|
; fallthrough edges which should be preserved.
|
|
|
|
; CHECK: yet_more_involved:
|
|
; CHECK: jmp .LBB3_1
|
|
; CHECK-NEXT: align
|
|
; CHECK-NEXT: .LBB3_4:
|
|
; CHECK-NEXT: callq bar99
|
|
; CHECK-NEXT: callq get
|
|
; CHECK-NEXT: cmpl $2999, %eax
|
|
; CHECK-NEXT: jg .LBB3_6
|
|
; CHECK-NEXT: callq block_a_true_func
|
|
; CHECK-NEXT: jmp .LBB3_7
|
|
; CHECK-NEXT: .LBB3_6:
|
|
; CHECK-NEXT: callq block_a_false_func
|
|
; CHECK-NEXT: .LBB3_7:
|
|
; CHECK-NEXT: callq block_a_merge_func
|
|
; CHECK-NEXT: .LBB3_1:
|
|
; CHECK-NEXT: callq body
|
|
|
|
define void @yet_more_involved() nounwind {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
call void @body()
|
|
%t0 = call i32 @get()
|
|
%t1 = icmp slt i32 %t0, 2
|
|
br i1 %t1, label %block_a, label %bb
|
|
|
|
bb:
|
|
%t2 = call i32 @get()
|
|
%t3 = icmp slt i32 %t2, 99
|
|
br i1 %t3, label %exit, label %loop
|
|
|
|
block_a:
|
|
call void @bar99()
|
|
%z0 = call i32 @get()
|
|
%z1 = icmp slt i32 %z0, 3000
|
|
br i1 %z1, label %block_a_true, label %block_a_false
|
|
|
|
block_a_true:
|
|
call void @block_a_true_func()
|
|
br label %block_a_merge
|
|
|
|
block_a_false:
|
|
call void @block_a_false_func()
|
|
br label %block_a_merge
|
|
|
|
block_a_merge:
|
|
call void @block_a_merge_func()
|
|
br label %loop
|
|
|
|
exit:
|
|
call void @exit()
|
|
ret void
|
|
}
|
|
|
|
; CodeGen should move the CFG islands that are part of the loop but don't
|
|
; conveniently fit anywhere so that they are at least contiguous with the
|
|
; loop.
|
|
|
|
; CHECK: cfg_islands:
|
|
; CHECK: jmp .LBB4_1
|
|
; CHECK-NEXT: align
|
|
; CHECK-NEXT: .LBB4_7:
|
|
; CHECK-NEXT: callq bar100
|
|
; CHECK-NEXT: jmp .LBB4_1
|
|
; CHECK-NEXT: .LBB4_8:
|
|
; CHECK-NEXT: callq bar101
|
|
; CHECK-NEXT: jmp .LBB4_1
|
|
; CHECK-NEXT: .LBB4_9:
|
|
; CHECK-NEXT: callq bar102
|
|
; CHECK-NEXT: jmp .LBB4_1
|
|
; CHECK-NEXT: .LBB4_5:
|
|
; CHECK-NEXT: callq loop_latch
|
|
; CHECK-NEXT: .LBB4_1:
|
|
; CHECK-NEXT: callq loop_header
|
|
|
|
define void @cfg_islands() nounwind {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
call void @loop_header()
|
|
%t0 = call i32 @get()
|
|
%t1 = icmp slt i32 %t0, 100
|
|
br i1 %t1, label %block100, label %bb
|
|
|
|
bb:
|
|
%t2 = call i32 @get()
|
|
%t3 = icmp slt i32 %t2, 101
|
|
br i1 %t3, label %block101, label %bb1
|
|
|
|
bb1:
|
|
%t4 = call i32 @get()
|
|
%t5 = icmp slt i32 %t4, 102
|
|
br i1 %t5, label %block102, label %bb2
|
|
|
|
bb2:
|
|
%t6 = call i32 @get()
|
|
%t7 = icmp slt i32 %t6, 103
|
|
br i1 %t7, label %exit, label %bb3
|
|
|
|
bb3:
|
|
call void @loop_latch()
|
|
br label %loop
|
|
|
|
exit:
|
|
call void @exit()
|
|
ret void
|
|
|
|
block100:
|
|
call void @bar100()
|
|
br label %loop
|
|
|
|
block101:
|
|
call void @bar101()
|
|
br label %loop
|
|
|
|
block102:
|
|
call void @bar102()
|
|
br label %loop
|
|
}
|
|
|
|
declare void @bar99() nounwind
|
|
declare void @bar100() nounwind
|
|
declare void @bar101() nounwind
|
|
declare void @bar102() nounwind
|
|
declare void @body() nounwind
|
|
declare void @exit() nounwind
|
|
declare void @loop_header() nounwind
|
|
declare void @loop_latch() nounwind
|
|
declare i32 @get() nounwind
|
|
declare void @block_a_true_func() nounwind
|
|
declare void @block_a_false_func() nounwind
|
|
declare void @block_a_merge_func() nounwind
|