You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
microwatt/fpga/nodivide.patch

217 lines
7.7 KiB
Diff

[PATCH] Hack out ppc64le gcc fixed point divide instructions
This is a pretty horrible short term hack that removes hardware fixed
point divides from ppc64le gcc. It breaks VMX/VSX, but we aren't using
either on microwatt. We'll implement a hardware divide shortly and this
can go away. Please don't tell my toolchain team.
The firmware.hex file in this directory is a build of micropython using
a recent mainline gcc with this patch.
Signed-off-by: Anton Blanchard <anton@linux.ibm.com>
---
diff --git a/gcc/config/rs6000/rs6000-builtin.def b/gcc/config/rs6000/rs6000-builtin.def
index 0a2bdb79e15..02e325b73a9 100644
--- a/gcc/config/rs6000/rs6000-builtin.def
+++ b/gcc/config/rs6000/rs6000-builtin.def
@@ -1581,7 +1581,6 @@ BU_VSX_2 (VEC_MERGEH_V2DF, "mergeh_2df", CONST, vsx_mergeh_v2df)
BU_VSX_2 (VEC_MERGEH_V2DI, "mergeh_2di", CONST, vsx_mergeh_v2di)
BU_VSX_2 (XXSPLTD_V2DF, "xxspltd_2df", CONST, vsx_xxspltd_v2df)
BU_VSX_2 (XXSPLTD_V2DI, "xxspltd_2di", CONST, vsx_xxspltd_v2di)
-BU_VSX_2 (DIV_V2DI, "div_2di", CONST, vsx_div_v2di)
BU_VSX_2 (UDIV_V2DI, "udiv_2di", CONST, vsx_udiv_v2di)
BU_VSX_2 (MUL_V2DI, "mul_2di", CONST, vsx_mul_v2di)
diff --git a/gcc/config/rs6000/rs6000-c.c b/gcc/config/rs6000/rs6000-c.c
index 7f0cdc73d9b..ad0a8a74e63 100644
--- a/gcc/config/rs6000/rs6000-c.c
+++ b/gcc/config/rs6000/rs6000-c.c
@@ -1459,8 +1459,6 @@ const struct altivec_builtin_types altivec_overloaded_builtins[] = {
RS6000_BTI_V4SF, RS6000_BTI_V4SF, RS6000_BTI_V4SF, 0 },
{ VSX_BUILTIN_VEC_DIV, VSX_BUILTIN_XVDIVDP,
RS6000_BTI_V2DF, RS6000_BTI_V2DF, RS6000_BTI_V2DF, 0 },
- { VSX_BUILTIN_VEC_DIV, VSX_BUILTIN_DIV_V2DI,
- RS6000_BTI_V2DI, RS6000_BTI_V2DI, RS6000_BTI_V2DI, 0 },
{ VSX_BUILTIN_VEC_DIV, VSX_BUILTIN_UDIV_V2DI,
RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI, RS6000_BTI_unsigned_V2DI, 0 },
{ VSX_BUILTIN_VEC_DOUBLE, VSX_BUILTIN_XVCVSXDDP,
diff --git a/gcc/config/rs6000/rs6000-call.c b/gcc/config/rs6000/rs6000-call.c
index 832eda7cbad..1c5245c781b 100644
--- a/gcc/config/rs6000/rs6000-call.c
+++ b/gcc/config/rs6000/rs6000-call.c
@@ -5445,7 +5445,6 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi)
gsi_replace (gsi, g, true);
return true;
/* Flavors of vec_div (Integer). */
- case VSX_BUILTIN_DIV_V2DI:
case VSX_BUILTIN_UDIV_V2DI:
arg0 = gimple_call_arg (stmt, 0);
arg1 = gimple_call_arg (stmt, 1);
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 9a7a1da987f..c443c2fe579 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -3071,45 +3071,6 @@
"maddld %0,%1,%2,%3"
[(set_attr "type" "mul")])
-(define_insn "udiv<mode>3"
- [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
- (udiv:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
- (match_operand:GPR 2 "gpc_reg_operand" "r")))]
- ""
- "div<wd>u %0,%1,%2"
- [(set_attr "type" "div")
- (set_attr "size" "<bits>")])
-
-
-;; For powers of two we can do sra[wd]i/addze for divide and then adjust for
-;; modulus. If it isn't a power of two, force operands into register and do
-;; a normal divide.
-(define_expand "div<mode>3"
- [(set (match_operand:GPR 0 "gpc_reg_operand")
- (div:GPR (match_operand:GPR 1 "gpc_reg_operand")
- (match_operand:GPR 2 "reg_or_cint_operand")))]
- ""
-{
- if (CONST_INT_P (operands[2])
- && INTVAL (operands[2]) > 0
- && exact_log2 (INTVAL (operands[2])) >= 0)
- {
- emit_insn (gen_div<mode>3_sra (operands[0], operands[1], operands[2]));
- DONE;
- }
-
- operands[2] = force_reg (<MODE>mode, operands[2]);
-})
-
-(define_insn "*div<mode>3"
- [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
- (div:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
- (match_operand:GPR 2 "gpc_reg_operand" "r")))]
- ""
- "div<wd> %0,%1,%2"
- [(set_attr "type" "div")
- (set_attr "size" "<bits>")])
-
(define_insn "div<mode>3_sra"
[(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
(div:GPR (match_operand:GPR 1 "gpc_reg_operand" "r")
@@ -3170,37 +3131,6 @@
(set_attr "length" "8,12")
(set_attr "cell_micro" "not")])
-(define_expand "mod<mode>3"
- [(set (match_operand:GPR 0 "gpc_reg_operand")
- (mod:GPR (match_operand:GPR 1 "gpc_reg_operand")
- (match_operand:GPR 2 "reg_or_cint_operand")))]
- ""
-{
- int i;
- rtx temp1;
- rtx temp2;
-
- if (!CONST_INT_P (operands[2])
- || INTVAL (operands[2]) <= 0
- || (i = exact_log2 (INTVAL (operands[2]))) < 0)
- {
- if (!TARGET_MODULO)
- FAIL;
-
- operands[2] = force_reg (<MODE>mode, operands[2]);
- }
- else
- {
- temp1 = gen_reg_rtx (<MODE>mode);
- temp2 = gen_reg_rtx (<MODE>mode);
-
- emit_insn (gen_div<mode>3 (temp1, operands[1], operands[2]));
- emit_insn (gen_ashl<mode>3 (temp2, temp1, GEN_INT (i)));
- emit_insn (gen_sub<mode>3 (operands[0], operands[1], temp2));
- DONE;
- }
-})
-
;; In order to enable using a peephole2 for combining div/mod to eliminate the
;; mod, prefer putting the result of mod into a different register
(define_insn "*mod<mode>3"
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 7633171df9c..1a2ac66bd43 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -1602,53 +1602,6 @@
"xvdiv<sd>p %x0,%x1,%x2"
[(set_attr "type" "<VStype_div>")])
-; Emulate vector with scalar for vec_div in V2DImode
-(define_insn_and_split "vsx_div_v2di"
- [(set (match_operand:V2DI 0 "vsx_register_operand" "=wa")
- (unspec:V2DI [(match_operand:V2DI 1 "vsx_register_operand" "wa")
- (match_operand:V2DI 2 "vsx_register_operand" "wa")]
- UNSPEC_VSX_DIVSD))]
- "VECTOR_MEM_VSX_P (V2DImode)"
- "#"
- "VECTOR_MEM_VSX_P (V2DImode) && !reload_completed"
- [(const_int 0)]
-{
- rtx op0 = operands[0];
- rtx op1 = operands[1];
- rtx op2 = operands[2];
- rtx op3 = gen_reg_rtx (DImode);
- rtx op4 = gen_reg_rtx (DImode);
- rtx op5 = gen_reg_rtx (DImode);
- emit_insn (gen_vsx_extract_v2di (op3, op1, GEN_INT (0)));
- emit_insn (gen_vsx_extract_v2di (op4, op2, GEN_INT (0)));
- if (TARGET_POWERPC64)
- emit_insn (gen_divdi3 (op5, op3, op4));
- else
- {
- rtx libfunc = optab_libfunc (sdiv_optab, DImode);
- rtx target = emit_library_call_value (libfunc,
- op5, LCT_NORMAL, DImode,
- op3, DImode,
- op4, DImode);
- emit_move_insn (op5, target);
- }
- emit_insn (gen_vsx_extract_v2di (op3, op1, GEN_INT (1)));
- emit_insn (gen_vsx_extract_v2di (op4, op2, GEN_INT (1)));
- if (TARGET_POWERPC64)
- emit_insn (gen_divdi3 (op3, op3, op4));
- else
- {
- rtx libfunc = optab_libfunc (sdiv_optab, DImode);
- rtx target = emit_library_call_value (libfunc,
- op3, LCT_NORMAL, DImode,
- op3, DImode,
- op4, DImode);
- emit_move_insn (op3, target);
- }
- emit_insn (gen_vsx_concat_v2di (op0, op5, op3));
- DONE;
-}
- [(set_attr "type" "div")])
(define_insn_and_split "vsx_udiv_v2di"
[(set (match_operand:V2DI 0 "vsx_register_operand" "=wa")
@@ -1668,9 +1621,6 @@
rtx op5 = gen_reg_rtx (DImode);
emit_insn (gen_vsx_extract_v2di (op3, op1, GEN_INT (0)));
emit_insn (gen_vsx_extract_v2di (op4, op2, GEN_INT (0)));
- if (TARGET_POWERPC64)
- emit_insn (gen_udivdi3 (op5, op3, op4));
- else
{
rtx libfunc = optab_libfunc (udiv_optab, DImode);
rtx target = emit_library_call_value (libfunc,
@@ -1681,9 +1631,6 @@
}
emit_insn (gen_vsx_extract_v2di (op3, op1, GEN_INT (1)));
emit_insn (gen_vsx_extract_v2di (op4, op2, GEN_INT (1)));
- if (TARGET_POWERPC64)
- emit_insn (gen_udivdi3 (op3, op3, op4));
- else
{
rtx libfunc = optab_libfunc (udiv_optab, DImode);
rtx target = emit_library_call_value (libfunc,