From: Richard Henderson <[email protected]> Move from tcg-op-gvec.c to tcg-op.c. Use a temporary, to cover the possibility of operand overlap.
(Cc for stable as this is a prerequisite for the bug fix in the next commit.) Cc: [email protected] Signed-off-by: Richard Henderson <[email protected]> Reviewed-by: Peter Maydell <[email protected]> Reviewed-by: Philippe Mathieu-Daudé <[email protected]> Message-id: [email protected] Signed-off-by: Peter Maydell <[email protected]> (cherry picked from commit b4f6f672a3e100706ddc249c26c2c149cdac1636) Signed-off-by: Michael Tokarev <[email protected]> diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h index e02f209c093..4cded4ef974 100644 --- a/include/tcg/tcg-op-common.h +++ b/include/tcg/tcg-op-common.h @@ -161,6 +161,7 @@ void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_umin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_umax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); +void tcg_gen_ussub_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2); void tcg_gen_abs_i32(TCGv_i32, TCGv_i32); /* Replicate a value of size @vece from @in to all the lanes in @out */ @@ -271,6 +272,7 @@ void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_umin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_umax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); +void tcg_gen_ussub_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2); void tcg_gen_abs_i64(TCGv_i64, TCGv_i64); /* Replicate a value of size @vece from @in to all the lanes in @out */ diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index 7024be938e6..effe9966e34 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -243,6 +243,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64) #define tcg_gen_umin_tl tcg_gen_umin_i64 #define tcg_gen_smax_tl tcg_gen_smax_i64 #define tcg_gen_umax_tl tcg_gen_umax_i64 +#define tcg_gen_ussub_tl tcg_gen_ussub_i64 #define tcg_gen_atomic_cmpxchg_tl tcg_gen_atomic_cmpxchg_i64 #define tcg_gen_atomic_xchg_tl tcg_gen_atomic_xchg_i64 #define tcg_gen_atomic_fetch_add_tl tcg_gen_atomic_fetch_add_i64 @@ -362,6 +363,7 @@ DEF_ATOMIC2(tcg_gen_atomic_umax_fetch, i64) #define tcg_gen_umin_tl tcg_gen_umin_i32 #define tcg_gen_smax_tl tcg_gen_smax_i32 #define tcg_gen_umax_tl tcg_gen_umax_i32 +#define tcg_gen_ussub_tl tcg_gen_ussub_i32 #define tcg_gen_atomic_cmpxchg_tl tcg_gen_atomic_cmpxchg_i32 #define tcg_gen_atomic_xchg_tl tcg_gen_atomic_xchg_i32 #define tcg_gen_atomic_fetch_add_tl tcg_gen_atomic_fetch_add_i32 diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c index bc323e25009..27f3807b004 100644 --- a/tcg/tcg-op-gvec.c +++ b/tcg/tcg-op-gvec.c @@ -2399,20 +2399,6 @@ void tcg_gen_gvec_usadd(unsigned vece, uint32_t dofs, uint32_t aofs, tcg_gen_gvec_3(dofs, aofs, bofs, oprsz, maxsz, &g[vece]); } -static void tcg_gen_ussub_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 min = tcg_constant_i32(0); - tcg_gen_sub_i32(d, a, b); - tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, min, d); -} - -static void tcg_gen_ussub_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - TCGv_i64 min = tcg_constant_i64(0); - tcg_gen_sub_i64(d, a, b); - tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, min, d); -} - void tcg_gen_gvec_ussub(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t bofs, uint32_t oprsz, uint32_t maxsz) { diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index d8ae57d6047..901dba34a94 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -1264,6 +1264,16 @@ void tcg_gen_umax_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b) tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, b, a); } +void tcg_gen_ussub_i32(TCGv_i32 ret, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_ebb_new_i32(); + TCGv_i32 z = tcg_constant_i32(0); + + tcg_gen_sub_i32(t, a, b); + tcg_gen_movcond_i32(TCG_COND_LTU, ret, a, b, z, t); + tcg_temp_free_i32(t); +} + void tcg_gen_abs_i32(TCGv_i32 ret, TCGv_i32 a) { TCGv_i32 t = tcg_temp_ebb_new_i32(); @@ -2391,6 +2401,16 @@ void tcg_gen_umax_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b) tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, b, a); } +void tcg_gen_ussub_i64(TCGv_i64 ret, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_ebb_new_i64(); + TCGv_i64 z = tcg_constant_i64(0); + + tcg_gen_sub_i64(t, a, b); + tcg_gen_movcond_i64(TCG_COND_LTU, ret, a, b, z, t); + tcg_temp_free_i64(t); +} + void tcg_gen_abs_i64(TCGv_i64 ret, TCGv_i64 a) { TCGv_i64 t = tcg_temp_ebb_new_i64(); -- 2.47.3
