llvm-project/llvm/test/CodeGen/X86/cmov.ll

159 lines
5.3 KiB
LLVM
Raw Normal View History

; RUN: llc < %s -verify-machineinstrs -mtriple=x86_64-apple-darwin10 -disable-cgp-select2branch | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128"
define i32 @test1(i32 %x, i32 %n, i32 %w, i32* %vp) nounwind readnone {
entry:
; CHECK-LABEL: test1:
; CHECK: btl
; CHECK-NEXT: movl $12, %eax
Instruction fixes, added instructions, and AsmString changes in the 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 llvm-svn: 91638
2009-12-18 08:01:26 +08:00
; CHECK-NEXT: cmovael (%rcx), %eax
; CHECK-NEXT: ret
%0 = lshr i32 %x, %n ; <i32> [#uses=1]
%1 = and i32 %0, 1 ; <i32> [#uses=1]
%toBool = icmp eq i32 %1, 0 ; <i1> [#uses=1]
%v = load i32, i32* %vp
%.0 = select i1 %toBool, i32 %v, i32 12 ; <i32> [#uses=1]
ret i32 %.0
}
define i32 @test2(i32 %x, i32 %n, i32 %w, i32* %vp) nounwind readnone {
entry:
; CHECK-LABEL: test2:
; CHECK: btl
; CHECK-NEXT: movl $12, %eax
Instruction fixes, added instructions, and AsmString changes in the 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 llvm-svn: 91638
2009-12-18 08:01:26 +08:00
; CHECK-NEXT: cmovbl (%rcx), %eax
; CHECK-NEXT: ret
%0 = lshr i32 %x, %n ; <i32> [#uses=1]
%1 = and i32 %0, 1 ; <i32> [#uses=1]
%toBool = icmp eq i32 %1, 0 ; <i1> [#uses=1]
%v = load i32, i32* %vp
%.0 = select i1 %toBool, i32 12, i32 %v ; <i32> [#uses=1]
ret i32 %.0
}
; x86's 32-bit cmov zeroes the high 32 bits of the destination. Make
; sure CodeGen takes advantage of that to avoid an unnecessary
; zero-extend (movl) after the cmov.
declare void @bar(i64) nounwind
define void @test3(i64 %a, i64 %b, i1 %p) nounwind {
; CHECK-LABEL: test3:
; CHECK: cmov{{n?}}el %[[R1:e..]], %[[R2:e..]]
; CHECK-NOT: movl
; CHECK: call
%c = trunc i64 %a to i32
%d = trunc i64 %b to i32
%e = select i1 %p, i32 %c, i32 %d
%f = zext i32 %e to i64
call void @bar(i64 %f)
ret void
}
; CodeGen shouldn't try to do a setne after an expanded 8-bit conditional
; move without recomputing EFLAGS, because the expansion of the conditional
; move with control flow may clobber EFLAGS (e.g., with xor, to set the
; register to zero).
; The test is a little awkward; the important part is that there's a test before the
; setne.
; PR4814
@g_3 = external global i8 ; <i8*> [#uses=1]
@g_96 = external global i8 ; <i8*> [#uses=2]
@g_100 = external global i8 ; <i8*> [#uses=2]
@_2E_str = external constant [15 x i8], align 1 ; <[15 x i8]*> [#uses=1]
define i32 @test4() nounwind {
entry:
%0 = load i8, i8* @g_3, align 1 ; <i8> [#uses=2]
%1 = sext i8 %0 to i32 ; <i32> [#uses=1]
%.lobit.i = lshr i8 %0, 7 ; <i8> [#uses=1]
%tmp.i = zext i8 %.lobit.i to i32 ; <i32> [#uses=1]
%tmp.not.i = xor i32 %tmp.i, 1 ; <i32> [#uses=1]
%iftmp.17.0.i.i = ashr i32 %1, %tmp.not.i ; <i32> [#uses=1]
%retval56.i.i = trunc i32 %iftmp.17.0.i.i to i8 ; <i8> [#uses=1]
%2 = icmp eq i8 %retval56.i.i, 0 ; <i1> [#uses=2]
%g_96.promoted.i = load i8, i8* @g_96 ; <i8> [#uses=3]
%3 = icmp eq i8 %g_96.promoted.i, 0 ; <i1> [#uses=2]
br i1 %3, label %func_4.exit.i, label %bb.i.i.i
bb.i.i.i: ; preds = %entry
%4 = load volatile i8, i8* @g_100, align 1 ; <i8> [#uses=0]
br label %func_4.exit.i
; CHECK-LABEL: test4:
; CHECK: g_100
; CHECK: testb
; CHECK-NOT: xor
; CHECK: setne
; CHECK: testb
func_4.exit.i: ; preds = %bb.i.i.i, %entry
%.not.i = xor i1 %2, true ; <i1> [#uses=1]
%brmerge.i = or i1 %3, %.not.i ; <i1> [#uses=1]
%.mux.i = select i1 %2, i8 %g_96.promoted.i, i8 0 ; <i8> [#uses=1]
br i1 %brmerge.i, label %func_1.exit, label %bb.i.i
bb.i.i: ; preds = %func_4.exit.i
%5 = load volatile i8, i8* @g_100, align 1 ; <i8> [#uses=0]
br label %func_1.exit
func_1.exit: ; preds = %bb.i.i, %func_4.exit.i
%g_96.tmp.0.i = phi i8 [ %g_96.promoted.i, %bb.i.i ], [ %.mux.i, %func_4.exit.i ] ; <i8> [#uses=2]
store i8 %g_96.tmp.0.i, i8* @g_96
%6 = zext i8 %g_96.tmp.0.i to i32 ; <i32> [#uses=1]
[opaque pointer type] Add textual IR support for explicit type parameter to the call instruction See r230786 and r230794 for similar changes to gep and load respectively. Call is a bit different because it often doesn't have a single explicit type - usually the type is deduced from the arguments, and just the return type is explicit. In those cases there's no need to change the IR. When that's not the case, the IR usually contains the pointer type of the first operand - but since typed pointers are going away, that representation is insufficient so I'm just stripping the "pointerness" of the explicit type away. This does make the IR a bit weird - it /sort of/ reads like the type of the first operand: "call void () %x(" but %x is actually of type "void ()*" and will eventually be just of type "ptr". But this seems not too bad and I don't think it would benefit from repeating the type ("void (), void () * %x(" and then eventually "void (), ptr %x(") as has been done with gep and load. This also has a side benefit: since the explicit type is no longer a pointer, there's no ambiguity between an explicit type and a function that returns a function pointer. Previously this case needed an explicit type (eg: a function returning a void() function was written as "call void () () * @x(" rather than "call void () * @x(" because of the ambiguity between a function returning a pointer to a void() function and a function returning void). No ambiguity means even function pointer return types can just be written alone, without writing the whole function's type. This leaves /only/ the varargs case where the explicit type is required. Given the special type syntax in call instructions, the regex-fu used for migration was a bit more involved in its own unique way (as every one of these is) so here it is. Use it in conjunction with the apply.sh script and associated find/xargs commands I've provided in rr230786 to migrate your out of tree tests. Do let me know if any of this doesn't cover your cases & we can iterate on a more general script/regexes to help others with out of tree tests. About 9 test cases couldn't be automatically migrated - half of those were functions returning function pointers, where I just had to manually delete the function argument types now that we didn't need an explicit function type there. The other half were typedefs of function types used in calls - just had to manually drop the * from those. import fileinput import sys import re pat = re.compile(r'((?:=|:|^|\s)call\s(?:[^@]*?))(\s*$|\s*(?:(?:\[\[[a-zA-Z0-9_]+\]\]|[@%](?:(")?[\\\?@a-zA-Z0-9_.]*?(?(3)"|)|{{.*}}))(?:\(|$)|undef|inttoptr|bitcast|null|asm).*$)') addrspace_end = re.compile(r"addrspace\(\d+\)\s*\*$") func_end = re.compile("(?:void.*|\)\s*)\*$") def conv(match, line): if not match or re.search(addrspace_end, match.group(1)) or not re.search(func_end, match.group(1)): return line return line[:match.start()] + match.group(1)[:match.group(1).rfind('*')].rstrip() + match.group(2) + line[match.end():] for line in sys.stdin: sys.stdout.write(conv(re.search(pat, line), line)) llvm-svn: 235145
2015-04-17 07:24:18 +08:00
%7 = tail call i32 (i8*, ...) @printf(i8* noalias getelementptr ([15 x i8], [15 x i8]* @_2E_str, i64 0, i64 0), i32 %6) nounwind ; <i32> [#uses=0]
ret i32 0
}
declare i32 @printf(i8* nocapture, ...) nounwind
; Should compile to setcc | -2.
; rdar://6668608
define i32 @test5(i32* nocapture %P) nounwind readonly {
entry:
; CHECK-LABEL: test5:
; CHECK: xorl %eax, %eax
; CHECK: setg %al
; CHECK: orl $-2, %eax
; CHECK: ret
%0 = load i32, i32* %P, align 4 ; <i32> [#uses=1]
%1 = icmp sgt i32 %0, 41 ; <i1> [#uses=1]
%iftmp.0.0 = select i1 %1, i32 -1, i32 -2 ; <i32> [#uses=1]
ret i32 %iftmp.0.0
}
define i32 @test6(i32* nocapture %P) nounwind readonly {
entry:
; CHECK-LABEL: test6:
; CHECK: xorl %eax, %eax
; CHECK: setl %al
; CHECK: leal 4(%rax,%rax,8), %eax
; CHECK: ret
%0 = load i32, i32* %P, align 4 ; <i32> [#uses=1]
%1 = icmp sgt i32 %0, 41 ; <i1> [#uses=1]
%iftmp.0.0 = select i1 %1, i32 4, i32 13 ; <i32> [#uses=1]
ret i32 %iftmp.0.0
}
2009-09-15 10:27:23 +08:00
; Don't try to use a 16-bit conditional move to do an 8-bit select,
; because it isn't worth it. Just use a branch instead.
define i8 @test7(i1 inreg %c, i8 inreg %a, i8 inreg %b) nounwind {
; CHECK-LABEL: test7:
2009-09-15 10:27:23 +08:00
; CHECK: testb $1, %dil
; CHECK-NEXT: jne LBB
%d = select i1 %c, i8 %a, i8 %b
ret i8 %d
}