Hello! Attached patch fixes PR 61423. The problem was that splitters omitted apparently necessary zero extension, and left garbage in the highpart of the register.
2014-06-06 Uros Bizjak <ubiz...@gmail.com> PR target/61423 * config/i386/i386.md (*floatunssi<mode>2_i387_with_xmm): New define_insn_and_split pattern, merged from *floatunssi<mode>2_1 and corresponding splitters. Zero extend general register or memory input operand to XMM temporary. Enable for TARGET_SSE2 and TARGET_INTER_UNIT_MOVES_TO_VEC only. (floatunssi<mode>2): Update expander predicate. testsuite/ChangeLog: 2014-06-06 Uros Bizjak <ubiz...@gmail.com> PR target/61423 * gcc.target/i386/pr61423.c: New test. The patch was bootstrapped and regression tested on x86_64-pc-linux-gnu {,-m32} and committed to mainline SVN. Please note that the patch breaks bootstrap when gcc is configured with "--with-arch=core-avx-i --with-cpu=core-avx-i" due to an unrelated problem in REE pass. The failing preprocessed source from the libgcc is attached to the PR. Uros.
Index: config/i386/i386.md =================================================================== --- config/i386/i386.md (revision 211316) +++ config/i386/i386.md (working copy) @@ -4943,66 +4943,37 @@ ;; Avoid store forwarding (partial memory) stall penalty by extending ;; SImode value to DImode through XMM register instead of pushing two -;; SImode values to stack. Note that even !TARGET_INTER_UNIT_MOVES_TO_VEC -;; targets benefit from this optimization. Also note that fild -;; loads from memory only. +;; SImode values to stack. Also note that fild loads from memory only. -(define_insn "*floatunssi<mode>2_1" - [(set (match_operand:X87MODEF 0 "register_operand" "=f,f") +(define_insn_and_split "*floatunssi<mode>2_i387_with_xmm" + [(set (match_operand:X87MODEF 0 "register_operand" "=f") (unsigned_float:X87MODEF - (match_operand:SI 1 "nonimmediate_operand" "x,m"))) - (clobber (match_operand:DI 2 "memory_operand" "=m,m")) - (clobber (match_scratch:SI 3 "=X,x"))] + (match_operand:SI 1 "nonimmediate_operand" "rm"))) + (clobber (match_scratch:DI 3 "=x")) + (clobber (match_operand:DI 2 "memory_operand" "=m"))] "!TARGET_64BIT && TARGET_80387 && X87_ENABLE_FLOAT (<X87MODEF:MODE>mode, DImode) - && TARGET_SSE" + && TARGET_SSE2 && TARGET_INTER_UNIT_MOVES_TO_VEC" "#" + "&& reload_completed" + [(set (match_dup 3) (zero_extend:DI (match_dup 1))) + (set (match_dup 2) (match_dup 3)) + (set (match_dup 0) + (float:X87MODEF (match_dup 2)))] + "" [(set_attr "type" "multi") (set_attr "mode" "<MODE>")]) -(define_split - [(set (match_operand:X87MODEF 0 "register_operand") - (unsigned_float:X87MODEF - (match_operand:SI 1 "register_operand"))) - (clobber (match_operand:DI 2 "memory_operand")) - (clobber (match_scratch:SI 3))] - "!TARGET_64BIT - && TARGET_80387 && X87_ENABLE_FLOAT (<X87MODEF:MODE>mode, DImode) - && TARGET_SSE - && reload_completed" - [(set (match_dup 2) (match_dup 1)) - (set (match_dup 0) - (float:X87MODEF (match_dup 2)))] - "operands[1] = simplify_gen_subreg (DImode, operands[1], SImode, 0);") - -(define_split - [(set (match_operand:X87MODEF 0 "register_operand") - (unsigned_float:X87MODEF - (match_operand:SI 1 "memory_operand"))) - (clobber (match_operand:DI 2 "memory_operand")) - (clobber (match_scratch:SI 3))] - "!TARGET_64BIT - && TARGET_80387 && X87_ENABLE_FLOAT (<X87MODEF:MODE>mode, DImode) - && TARGET_SSE - && reload_completed" - [(set (match_dup 2) (match_dup 3)) - (set (match_dup 0) - (float:X87MODEF (match_dup 2)))] -{ - emit_move_insn (operands[3], operands[1]); - operands[3] = simplify_gen_subreg (DImode, operands[3], SImode, 0); -}) - (define_expand "floatunssi<mode>2" [(parallel [(set (match_operand:X87MODEF 0 "register_operand") (unsigned_float:X87MODEF (match_operand:SI 1 "nonimmediate_operand"))) - (clobber (match_dup 2)) - (clobber (match_scratch:SI 3))])] + (clobber (match_scratch:DI 3)) + (clobber (match_dup 2))])] "!TARGET_64BIT && ((TARGET_80387 && X87_ENABLE_FLOAT (<X87MODEF:MODE>mode, DImode) - && TARGET_SSE) + && TARGET_SSE2 && TARGET_INTER_UNIT_MOVES_TO_VEC) || (SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH))" { if (SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH) Index: testsuite/gcc.target/i386/pr61423.c =================================================================== --- testsuite/gcc.target/i386/pr61423.c (revision 0) +++ testsuite/gcc.target/i386/pr61423.c (working copy) @@ -0,0 +1,38 @@ +/* PR target/61423 */ +/* { dg-do run { target ia32 } } */ +/* { dg-options "-O1 -ftree-vectorize -msse2 -mfpmath=387 -mtune=core2" } */ + +#define N 1024 +static unsigned int A[N]; + +double +__attribute__((noinline)) +func (void) +{ + unsigned int sum = 0; + unsigned i; + double t; + + for (i = 0; i < N; i++) + sum += A[i]; + + t = sum; + return t; +} + +int +main () +{ + unsigned i; + double d; + + for(i = 0; i < N; i++) + A[i] = 1; + + d = func(); + + if (d != 1024.0) + __builtin_abort (); + + return 0; +}