[llvm-commits] [llvm] r112176 - /llvm/trunk/lib/Target/ARM/ARMInstrThumb2.td

Bill Wendling isanbard at gmail.com
Thu Aug 26 02:07:33 PDT 2010


Author: void
Date: Thu Aug 26 04:07:33 2010
New Revision: 112176

URL: http://llvm.org/viewvc/llvm-project?rev=112176&view=rev
Log:
There seems to be a (potential) hardware bug with the CMN instruction and
comparison with 0. These two pieces of code should give identical results:

  rsbs r1, r1, 0
  cmp  r0, r1
  mov  r0, #0
  it   ls
  mov  r0, #1

and:

  cmn  r0, r1
  mov  r0, #0
  it   ls
  mov  r0, #1

However, the CMN gives the *opposite* result when r1 is 0. This is because the
carry flag is set in the CMP case but not in the CMN case. In short, the CMP
instruction doesn't perform a truncate of the (logical) NOT of 0 plus the value
of r0 and the carry bit (because the "carry bit" parameter to AddWithCarry is
defined as 1 in this case, the carry flag will always be set when r0 >= 0). The
CMN instruction doesn't perform a NOT of 0 so there is never a "carry" when this
AddWithCarry is performed (because the "carry bit" parameter to AddWithCarry is
defined as 0).

The AddWithCarry in the CMP case seems to be relying upon the identity:

  ~x + 1 = -x

However when x is 0 and unsigned, this doesn't hold:

   x = 0
  ~x = 0xFFFF FFFF
  ~x + 1 = 0x1 0000 0000
  (-x = 0) != (0x1 0000 0000 = ~x + 1)

Therefore, we should disable *all* versions of CMN, especially when comparing
against zero, until we can limit when the CMN instruction is used (when we know
that the RHS is not 0) or when we have a hardware fix for this.

(See the ARM docs for the "AddWithCarry" pseudo-code.)

This is related to <rdar://problem/7569620>.


Modified:
    llvm/trunk/lib/Target/ARM/ARMInstrThumb2.td

Modified: llvm/trunk/lib/Target/ARM/ARMInstrThumb2.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/ARM/ARMInstrThumb2.td?rev=112176&r1=112175&r2=112176&view=diff
==============================================================================
--- llvm/trunk/lib/Target/ARM/ARMInstrThumb2.td (original)
+++ llvm/trunk/lib/Target/ARM/ARMInstrThumb2.td Thu Aug 26 04:07:33 2010
@@ -2141,18 +2141,60 @@
 defm t2CMPz : T2I_cmp_irs<0b1101, "cmp",
                           BinOpFrag<(ARMcmpZ node:$LHS, node:$RHS)>>;
 
-//FIXME: Disable CMN, as CCodes are backwards from compare expectations
-//       Compare-to-zero still works out, just not the relationals
+// FIXME: There seems to be a (potential) hardware bug with the CMN instruction
+// and comparison with 0. These two pieces of code should give identical
+// results:
+//
+//   rsbs r1, r1, 0
+//   cmp  r0, r1
+//   mov  r0, #0
+//   it   ls
+//   mov  r0, #1
+//
+// and:
+// 
+//   cmn  r0, r1
+//   mov  r0, #0
+//   it   ls
+//   mov  r0, #1
+//
+// However, the CMN gives the *opposite* result when r1 is 0. This is because
+// the carry flag is set in the CMP case but not in the CMN case. In short, the
+// CMP instruction doesn't perform a truncate of the (logical) NOT of 0 plus the
+// value of r0 and the carry bit (because the "carry bit" parameter to
+// AddWithCarry is defined as 1 in this case, the carry flag will always be set
+// when r0 >= 0). The CMN instruction doesn't perform a NOT of 0 so there is
+// never a "carry" when this AddWithCarry is performed (because the "carry bit"
+// parameter to AddWithCarry is defined as 0).
+//
+// The AddWithCarry in the CMP case seems to be relying upon the identity:
+// 
+//   ~x + 1 = -x
+//
+// However when x is 0 and unsigned, this doesn't hold:
+//
+//    x = 0
+//   ~x = 0xFFFF FFFF
+//   ~x + 1 = 0x1 0000 0000
+//   (-x = 0) != (0x1 0000 0000 = ~x + 1)
+//
+// Therefore, we should disable *all* versions of CMN, especially when comparing
+// against zero, until we can limit when the CMN instruction is used (when we
+// know that the RHS is not 0) or when we have a hardware fix for this.
+//
+// (See the ARM docs for the "AddWithCarry" pseudo-code.)
+//
+// This is related to <rdar://problem/7569620>.
+//
 //defm t2CMN  : T2I_cmp_irs<0b1000, "cmn",
 //                          BinOpFrag<(ARMcmp node:$LHS,(ineg node:$RHS))>>;
-defm t2CMNz : T2I_cmp_irs<0b1000, "cmn",
-                          BinOpFrag<(ARMcmpZ node:$LHS,(ineg node:$RHS))>>;
-
+//defm t2CMNz : T2I_cmp_irs<0b1000, "cmn",
+//                          BinOpFrag<(ARMcmpZ node:$LHS,(ineg node:$RHS))>>;
+//
 //def : T2Pat<(ARMcmp  GPR:$src, t2_so_imm_neg:$imm),
 //            (t2CMNri GPR:$src, t2_so_imm_neg:$imm)>;
-
-def : T2Pat<(ARMcmpZ  GPR:$src, t2_so_imm_neg:$imm),
-            (t2CMNzri GPR:$src, t2_so_imm_neg:$imm)>;
+//def : T2Pat<(ARMcmpZ  GPR:$src, t2_so_imm_neg:$imm),
+//            (t2CMNzri GPR:$src, t2_so_imm_neg:$imm)>;
 
 defm t2TST  : T2I_cmp_irs<0b0000, "tst",
                           BinOpFrag<(ARMcmpZ (and node:$LHS, node:$RHS), 0)>>;





More information about the llvm-commits mailing list