@@ -19,24 +19,19 @@
;; along with GCC; see the file COPYING3. If not see
;; <http://www.gnu.org/licenses/>.
-;; The MMA patterns use the multi-register PXImode and POImode partial
+;; The MMA patterns use the multi-register XOmode and OOmode partial
;; integer modes to implement the target specific __vector_quad and
;; __vector_pair types that the MMA built-in functions reference.
-;; To use these modes, we must define XImode and OImode move patterns
-;; so the independent parts of the compiler can use our large partial
-;; integer modes. However, if we enable the XImode and OImode move
-;; patterns, then the compiler will attempt to use them and this can
-;; cause byte swapping issues on litte-endian systems. We don't need
-;; the XImode and OImode move patterns for actual code generation,
-;; therefore, we define the XImode and OImode move patterns, but we
-;; disable their use with a "false" condition flag.
+;; We define these modes with the new OPAQUE_MODE mechanism to prevent
+;; anything from trying to open them up.
(define_constants [(MAX_MMA_OPERANDS 7)])
;; Constants for creating unspecs
(define_c_enum "unspec"
- [UNSPEC_MMA_ASSEMBLE_ACC
+ [UNSPEC_MMA_ASSEMBLE
+ UNSPEC_MMA_EXTRACT
UNSPEC_MMA_PMXVBF16GER2
UNSPEC_MMA_PMXVBF16GER2NN
UNSPEC_MMA_PMXVBF16GER2NP
@@ -265,31 +260,22 @@ (define_int_attr avvi4i4i4 [(UNSPEC_MMA_PMXVI8GER4PP "pmxvi8ger4pp")
(UNSPEC_MMA_PMXVI8GER4SPP "pmxvi8ger4spp")])
-;; Define a disabled OImode move pattern, so we can use POImode.
-(define_expand "movoi"
- [(set (match_operand:OI 0 "nonimmediate_operand")
- (match_operand:OI 1 "input_operand"))]
- "0"
-{
- gcc_unreachable ();
-})
-
-;; Vector pair support. POImode can only live in VSRs.
-(define_expand "movpoi"
- [(set (match_operand:POI 0 "nonimmediate_operand")
- (match_operand:POI 1 "input_operand"))]
+;; Vector pair support. OOmode can only live in VSRs.
+(define_expand "movoo"
+ [(set (match_operand:OO 0 "nonimmediate_operand")
+ (match_operand:OO 1 "input_operand"))]
"TARGET_MMA"
{
- rs6000_emit_move (operands[0], operands[1], POImode);
+ rs6000_emit_move (operands[0], operands[1], OOmode);
DONE;
})
-(define_insn_and_split "*movpoi"
- [(set (match_operand:POI 0 "nonimmediate_operand" "=wa,m,wa")
- (match_operand:POI 1 "input_operand" "m,wa,wa"))]
+(define_insn_and_split "*movoo"
+ [(set (match_operand:OO 0 "nonimmediate_operand" "=wa,m,wa")
+ (match_operand:OO 1 "input_operand" "m,wa,wa"))]
"TARGET_MMA
- && (gpc_reg_operand (operands[0], POImode)
- || gpc_reg_operand (operands[1], POImode))"
+ && (gpc_reg_operand (operands[0], OOmode)
+ || gpc_reg_operand (operands[1], OOmode))"
"@
lxvp%X1 %x0,%1
stxvp%X0 %x1,%0
@@ -305,38 +291,29 @@ (define_insn_and_split "*movpoi"
(set_attr "length" "*,*,8")])
-;; Define a disabled XImode move pattern, so we can use PXImode.
-(define_expand "movxi"
- [(set (match_operand:XI 0 "nonimmediate_operand")
- (match_operand:XI 1 "input_operand"))]
- "0"
-{
- gcc_unreachable ();
-})
-
-;; Vector quad support. PXImode can only live in FPRs.
-(define_expand "movpxi"
- [(set (match_operand:PXI 0 "nonimmediate_operand")
- (match_operand:PXI 1 "input_operand"))]
+;; Vector quad support. XOmode can only live in FPRs.
+(define_expand "movxo"
+ [(set (match_operand:XO 0 "nonimmediate_operand")
+ (match_operand:XO 1 "input_operand"))]
"TARGET_MMA"
{
- rs6000_emit_move (operands[0], operands[1], PXImode);
+ rs6000_emit_move (operands[0], operands[1], XOmode);
DONE;
})
-(define_insn_and_split "*movpxi"
- [(set (match_operand:PXI 0 "nonimmediate_operand" "=d,m,d,d")
- (match_operand:PXI 1 "input_operand" "m,d,d,O"))]
+(define_insn_and_split "*movxo"
+ [(set (match_operand:XO 0 "nonimmediate_operand" "=d,m,d,d")
+ (match_operand:XO 1 "input_operand" "m,d,d,O"))]
"TARGET_MMA
- && (gpc_reg_operand (operands[0], PXImode)
- || gpc_reg_operand (operands[1], PXImode))"
+ && (gpc_reg_operand (operands[0], XOmode)
+ || gpc_reg_operand (operands[1], XOmode))"
"@
#
#
#
xxsetaccz %A0"
"&& reload_completed
- && !(fpr_reg_operand (operands[0], PXImode) && operands[1] == const0_rtx)"
+ && !(fpr_reg_operand (operands[0], XOmode) && operands[1] == const0_rtx)"
[(const_int 0)]
{
rs6000_split_multireg_move (operands[0], operands[1]);
@@ -347,245 +324,329 @@ (define_insn_and_split "*movpxi"
(set_attr "max_prefixed_insns" "2,2,*,*")])
(define_expand "mma_assemble_pair"
- [(match_operand:POI 0 "vsx_register_operand")
+ [(match_operand:OO 0 "vsx_register_operand")
(match_operand:V16QI 1 "input_operand")
(match_operand:V16QI 2 "input_operand")]
"TARGET_MMA"
{
- rtx dst;
+ rtx src = gen_rtx_UNSPEC (OOmode,
+ gen_rtvec (2, operands[1], operands[2]),
+ UNSPEC_MMA_ASSEMBLE);
+ emit_move_insn (operands[0], src);
+ DONE;
+})
+
+(define_insn_and_split "*mma_assemble_pair"
+ [(set (match_operand:OO 0 "vsx_register_operand" "=wa")
+ (unspec:OO [(match_operand:V16QI 1 "mma_assemble_input_operand" "mwa")
+ (match_operand:V16QI 2 "mma_assemble_input_operand" "mwa")]
+ UNSPEC_MMA_ASSEMBLE))]
+ "TARGET_MMA
+ && vsx_register_operand (operands[0], OOmode)"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+{
+ rtx src = gen_rtx_UNSPEC (OOmode,
+ gen_rtvec (2, operands[1], operands[2]),
+ UNSPEC_MMA_ASSEMBLE);
+ rs6000_split_multireg_move (operands[0], src);
+ DONE;
+})
- /* Let the compiler know the code below fully defines our output value. */
- emit_clobber (operands[0]);
+(define_insn_and_split "*mma_disassemble_pair"
+ [(set (match_operand:V16QI 0 "mma_disassemble_output_operand" "=mwa")
+ (unspec:V16QI [(match_operand:OO 1 "input_operand" "wa")
+ (match_operand 2 "const_int_operand")]
+ UNSPEC_MMA_EXTRACT))]
+ "TARGET_MMA
+ && fpr_reg_operand (operands[1], OOmode)"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+{
+ gcc_assert (REG_P (operands[1]));
+ int reg = REGNO (operands[1]);
+ int regoff = INTVAL (operands[2]);
+ rtx src = gen_rtx_REG (V16QImode, reg + regoff);
+ emit_move_insn (operands[0], src);
+ DONE;
+})
- dst = simplify_gen_subreg (V16QImode, operands[0], POImode, 0);
- emit_move_insn (dst, operands[1]);
- dst = simplify_gen_subreg (V16QImode, operands[0], POImode, 16);
- emit_move_insn (dst, operands[2]);
+(define_expand "mma_disassemble_pair"
+ [(match_operand:V16QI 0 "mma_disassemble_output_operand")
+ (match_operand:OO 1 "input_operand")
+ (match_operand 2 "const_int_operand")]
+ "TARGET_MMA"
+{
+ rtx src;
+ int regoff = INTVAL (operands[2]);
+ gcc_assert (IN_RANGE (regoff, 0, 1));
+ src = gen_rtx_UNSPEC (V16QImode,
+ gen_rtvec (2, operands[1], GEN_INT (regoff)),
+ UNSPEC_MMA_EXTRACT);
+ emit_move_insn (operands[0], src);
DONE;
})
(define_expand "mma_assemble_acc"
- [(match_operand:PXI 0 "fpr_reg_operand")
+ [(match_operand:XO 0 "fpr_reg_operand")
(match_operand:V16QI 1 "input_operand")
(match_operand:V16QI 2 "input_operand")
(match_operand:V16QI 3 "input_operand")
(match_operand:V16QI 4 "input_operand")]
"TARGET_MMA"
{
- rtx src = gen_rtx_UNSPEC (PXImode,
+ rtx src = gen_rtx_UNSPEC (XOmode,
gen_rtvec (4, operands[1], operands[2],
operands[3], operands[4]),
- UNSPEC_MMA_ASSEMBLE_ACC);
+ UNSPEC_MMA_ASSEMBLE);
emit_move_insn (operands[0], src);
DONE;
})
(define_insn_and_split "*mma_assemble_acc"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=d")
- (unspec:PXI [(match_operand:V16QI 1 "mma_assemble_input_operand" "mwa")
- (match_operand:V16QI 2 "mma_assemble_input_operand" "mwa")
- (match_operand:V16QI 3 "mma_assemble_input_operand" "mwa")
- (match_operand:V16QI 4 "mma_assemble_input_operand" "mwa")]
- UNSPEC_MMA_ASSEMBLE_ACC))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=d")
+ (unspec:XO [(match_operand:V16QI 1 "mma_assemble_input_operand" "mwa")
+ (match_operand:V16QI 2 "mma_assemble_input_operand" "mwa")
+ (match_operand:V16QI 3 "mma_assemble_input_operand" "mwa")
+ (match_operand:V16QI 4 "mma_assemble_input_operand" "mwa")]
+ UNSPEC_MMA_ASSEMBLE))]
"TARGET_MMA
- && fpr_reg_operand (operands[0], PXImode)"
+ && fpr_reg_operand (operands[0], XOmode)"
"#"
"&& reload_completed"
[(const_int 0)]
{
- rtx src = gen_rtx_UNSPEC (PXImode,
+ rtx src = gen_rtx_UNSPEC (XOmode,
gen_rtvec (4, operands[1], operands[2],
operands[3], operands[4]),
- UNSPEC_MMA_ASSEMBLE_ACC);
+ UNSPEC_MMA_ASSEMBLE);
rs6000_split_multireg_move (operands[0], src);
DONE;
})
+(define_insn_and_split "*mma_disassemble_acc"
+ [(set (match_operand:V16QI 0 "mma_disassemble_output_operand" "=mwa")
+ (unspec:V16QI [(match_operand:XO 1 "input_operand" "d")
+ (match_operand 2 "const_int_operand")]
+ UNSPEC_MMA_EXTRACT))]
+ "TARGET_MMA
+ && fpr_reg_operand (operands[1], XOmode)"
+ "#"
+ "&& reload_completed"
+ [(const_int 0)]
+{
+ gcc_assert (REG_P (operands[1]));
+ int reg = REGNO (operands[1]);
+ int regoff = INTVAL (operands[2]);
+ gcc_assert (IN_RANGE (regoff, 0, 3));
+ rtx src = gen_rtx_REG (V16QImode, reg + regoff);
+ emit_move_insn (operands[0], src);
+ DONE;
+})
+
+(define_expand "mma_disassemble_acc"
+ [(match_operand:V16QI 0 "mma_disassemble_output_operand")
+ (match_operand:XO 1 "input_operand")
+ (match_operand 2 "const_int_operand")]
+ "TARGET_MMA"
+{
+ rtx src;
+ int regoff = INTVAL (operands[2]);
+ gcc_assert (IN_RANGE (regoff, 0, 3));
+ src = gen_rtx_UNSPEC (V16QImode,
+ gen_rtvec (2, operands[1], GEN_INT (regoff)),
+ UNSPEC_MMA_EXTRACT);
+ emit_move_insn (operands[0], src);
+ DONE;
+})
+
;; MMA instructions that do not use their accumulators as an input, still
;; must not allow their vector operands to overlap the registers used by
;; the accumulator. We enforce this by marking the output as early clobber.
(define_insn "mma_<acc>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")]
MMA_ACC))]
"TARGET_MMA"
"<acc> %A0"
[(set_attr "type" "mma")])
(define_expand "mma_xxsetaccz"
- [(set (match_operand:PXI 0 "fpr_reg_operand")
+ [(set (match_operand:XO 0 "fpr_reg_operand")
(const_int 0))]
"TARGET_MMA"
{
- emit_insn (gen_movpxi (operands[0], const0_rtx));
+ emit_insn (gen_movxo (operands[0], const0_rtx));
DONE;
})
(define_insn "mma_<vv>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")]
- MMA_VV))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")]
+ MMA_VV))]
"TARGET_MMA"
"<vv> %A0,%x1,%x2"
[(set_attr "type" "mma")])
(define_insn "mma_<avv>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")]
- MMA_AVV))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")]
+ MMA_AVV))]
"TARGET_MMA"
"<avv> %A0,%x2,%x3"
[(set_attr "type" "mma")])
(define_insn "mma_<pv>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:POI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")]
- MMA_PV))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")]
+ MMA_PV))]
"TARGET_MMA"
"<pv> %A0,%x1,%x2"
[(set_attr "type" "mma")])
(define_insn "mma_<apv>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:POI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")]
- MMA_APV))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:OO 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")]
+ MMA_APV))]
"TARGET_MMA"
"<apv> %A0,%x2,%x3"
[(set_attr "type" "mma")])
(define_insn "mma_<vvi4i4i8>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "u8bit_cint_operand" "n")]
- MMA_VVI4I4I8))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "u8bit_cint_operand" "n")]
+ MMA_VVI4I4I8))]
"TARGET_MMA"
"<vvi4i4i8> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<avvi4i4i8>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_15_operand" "n")
- (match_operand:SI 6 "u8bit_cint_operand" "n")]
- MMA_AVVI4I4I8))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n")
+ (match_operand:SI 6 "u8bit_cint_operand" "n")]
+ MMA_AVVI4I4I8))]
"TARGET_MMA"
"<avvi4i4i8> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<vvi4i4i2>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_3_operand" "n")]
- MMA_VVI4I4I2))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_3_operand" "n")]
+ MMA_VVI4I4I2))]
"TARGET_MMA"
"<vvi4i4i2> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<avvi4i4i2>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_15_operand" "n")
- (match_operand:SI 6 "const_0_to_3_operand" "n")]
- MMA_AVVI4I4I2))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n")
+ (match_operand:SI 6 "const_0_to_3_operand" "n")]
+ MMA_AVVI4I4I2))]
"TARGET_MMA"
"<avvi4i4i2> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<vvi4i4>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n")
- (match_operand:SI 4 "const_0_to_15_operand" "n")]
- MMA_VVI4I4))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")]
+ MMA_VVI4I4))]
"TARGET_MMA"
"<vvi4i4> %A0,%x1,%x2,%3,%4"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<avvi4i4>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_15_operand" "n")]
- MMA_AVVI4I4))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n")]
+ MMA_AVVI4I4))]
"TARGET_MMA"
"<avvi4i4> %A0,%x2,%x3,%4,%5"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<pvi4i2>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:POI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n")
- (match_operand:SI 4 "const_0_to_3_operand" "n")]
- MMA_PVI4I2))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:OO 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n")
+ (match_operand:SI 4 "const_0_to_3_operand" "n")]
+ MMA_PVI4I2))]
"TARGET_MMA"
"<pvi4i2> %A0,%x1,%x2,%3,%4"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<apvi4i2>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:POI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_3_operand" "n")]
- MMA_APVI4I2))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:OO 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_3_operand" "n")]
+ MMA_APVI4I2))]
"TARGET_MMA"
"<apvi4i2> %A0,%x2,%x3,%4,%5"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<vvi4i4i4>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:V16QI 1 "vsx_register_operand" "wa")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:SI 3 "const_0_to_15_operand" "n")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_15_operand" "n")]
- MMA_VVI4I4I4))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:V16QI 1 "vsx_register_operand" "wa")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:SI 3 "const_0_to_15_operand" "n")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n")]
+ MMA_VVI4I4I4))]
"TARGET_MMA"
"<vvi4i4i4> %A0,%x1,%x2,%3,%4,%5"
[(set_attr "type" "mma")
(set_attr "length" "8")])
(define_insn "mma_<avvi4i4i4>"
- [(set (match_operand:PXI 0 "fpr_reg_operand" "=&d")
- (unspec:PXI [(match_operand:PXI 1 "fpr_reg_operand" "0")
- (match_operand:V16QI 2 "vsx_register_operand" "wa")
- (match_operand:V16QI 3 "vsx_register_operand" "wa")
- (match_operand:SI 4 "const_0_to_15_operand" "n")
- (match_operand:SI 5 "const_0_to_15_operand" "n")
- (match_operand:SI 6 "const_0_to_15_operand" "n")]
- MMA_AVVI4I4I4))]
+ [(set (match_operand:XO 0 "fpr_reg_operand" "=&d")
+ (unspec:XO [(match_operand:XO 1 "fpr_reg_operand" "0")
+ (match_operand:V16QI 2 "vsx_register_operand" "wa")
+ (match_operand:V16QI 3 "vsx_register_operand" "wa")
+ (match_operand:SI 4 "const_0_to_15_operand" "n")
+ (match_operand:SI 5 "const_0_to_15_operand" "n")
+ (match_operand:SI 6 "const_0_to_15_operand" "n")]
+ MMA_AVVI4I4I4))]
"TARGET_MMA"
"<avvi4i4i4> %A0,%x2,%x3,%4,%5,%6"
[(set_attr "type" "mma")
@@ -1072,8 +1072,9 @@ (define_predicate "input_operand"
&& easy_fp_constant (op, mode))
return 1;
- /* Allow any integer constant. */
- if (SCALAR_INT_MODE_P (mode) && CONST_SCALAR_INT_P (op))
+ /* Allow any integer constant. Also allow consts for OPAQUE_MODE. */
+ if ((SCALAR_INT_MODE_P (mode) || OPAQUE_MODE_P (mode))
+ && CONST_SCALAR_INT_P (op))
return 1;
/* Allow easy vector constants. */
@@ -1144,6 +1145,15 @@ (define_special_predicate "mma_assemble_input_operand"
(match_test "(mode == V16QImode
&& (vsx_register_operand (op, mode) || MEM_P (op)))"))
+;; Return 1 if this operand is valid for an MMA disassemble insn.
+(define_predicate "mma_disassemble_output_operand"
+ (match_code "reg,subreg,mem")
+{
+ if (REG_P (op) && !vsx_register_operand (op, mode))
+ return false;
+ return true;
+})
+
;; Return true if operand is an operator used in rotate-and-mask instructions.
(define_predicate "rotate_mask_operator"
(match_code "rotate,ashift,lshiftrt"))
@@ -352,7 +352,7 @@
| RS6000_BTC_UNARY), \
CODE_FOR_ ## ICODE) /* ICODE */
-#define BU_MMA_V2(ENUM, NAME, ATTR, ICODE) \
+#define BU_MMA_2(ENUM, NAME, ATTR, ICODE) \
RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM, /* ENUM */ \
"__builtin_mma_" NAME, /* NAME */ \
RS6000_BTM_MMA, /* MASK */ \
@@ -360,7 +360,13 @@
| RS6000_BTC_BINARY \
| RS6000_BTC_VOID \
| RS6000_BTC_GIMPLE), \
- CODE_FOR_nothing) /* ICODE */
+ CODE_FOR_nothing) /* ICODE */ \
+ RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM ## _INTERNAL, /* ENUM */ \
+ "__builtin_mma_" NAME "_internal", /* NAME */ \
+ RS6000_BTM_MMA, /* MASK */ \
+ (RS6000_BTC_ ## ATTR /* ATTR */ \
+ | RS6000_BTC_BINARY), \
+ CODE_FOR_ ## ICODE) /* ICODE */
#define BU_MMA_3(ENUM, NAME, ATTR, ICODE) \
RS6000_BUILTIN_M (MMA_BUILTIN_ ## ENUM, /* ENUM */ \
@@ -3108,8 +3114,8 @@ BU_MMA_1 (XXMFACC, "xxmfacc", QUAD, mma_xxmfacc)
BU_MMA_1 (XXMTACC, "xxmtacc", QUAD, mma_xxmtacc)
BU_MMA_1 (XXSETACCZ, "xxsetaccz", MISC, mma_xxsetaccz)
-BU_MMA_V2 (DISASSEMBLE_ACC, "disassemble_acc", QUAD, nothing)
-BU_MMA_V2 (DISASSEMBLE_PAIR,"disassemble_pair", PAIR, nothing)
+BU_MMA_2 (DISASSEMBLE_ACC, "disassemble_acc", QUAD, mma_disassemble_acc)
+BU_MMA_2 (DISASSEMBLE_PAIR,"disassemble_pair", PAIR, mma_disassemble_pair)
BU_MMA_3 (ASSEMBLE_PAIR, "assemble_pair", MISC, mma_assemble_pair)
BU_MMA_3 (XVBF16GER2, "xvbf16ger2", MISC, mma_xvbf16ger2)
@@ -6325,6 +6325,22 @@ rs6000_discover_homogeneous_aggregate (machine_mode mode, const_tree type,
bool
rs6000_return_in_memory (const_tree type, const_tree fntype ATTRIBUTE_UNUSED)
{
+ /* We do not allow MMA types being used as return values. Only report
+ the invalid return value usage the first time we encounter it. */
+ if (cfun != NULL
+ && !cfun->machine->mma_return_type_error
+ && TREE_TYPE (cfun->decl) == fntype
+ && (TYPE_MODE (type) == OOmode || TYPE_MODE (type) == XOmode))
+ {
+ /* Record we have now handled function CFUN, so the next time we
+ are called, we do not re-report the same error. */
+ cfun->machine->mma_return_type_error = true;
+ if (TYPE_CANONICAL (type) != NULL_TREE)
+ type = TYPE_CANONICAL (type);
+ error ("invalid use of MMA type %qs as a function return value",
+ IDENTIFIER_POINTER (DECL_NAME (TYPE_NAME (type))));
+ }
+
/* For the Darwin64 ABI, test if we can fit the return value in regs. */
if (TARGET_MACHO
&& rs6000_darwin64_abi
@@ -6577,30 +6593,8 @@ machine_mode
rs6000_promote_function_mode (const_tree type ATTRIBUTE_UNUSED,
machine_mode mode,
int *punsignedp ATTRIBUTE_UNUSED,
- const_tree, int for_return)
+ const_tree, int for_return ATTRIBUTE_UNUSED)
{
- /* Warning: this is a static local variable and not always NULL!
- This function is called multiple times for the same function
- and return value. PREV_FUNC is used to keep track of the
- first time we encounter a function's return value in order
- to not report an error with that return value multiple times. */
- static struct function *prev_func = NULL;
-
- /* We do not allow MMA types being used as return values. Only report
- the invalid return value usage the first time we encounter it. */
- if (for_return
- && prev_func != cfun
- && (mode == POImode || mode == PXImode))
- {
- /* Record we have now handled function CFUN, so the next time we
- are called, we do not re-report the same error. */
- prev_func = cfun;
- if (TYPE_CANONICAL (type) != NULL_TREE)
- type = TYPE_CANONICAL (type);
- error ("invalid use of MMA type %qs as a function return value",
- IDENTIFIER_POINTER (DECL_NAME (TYPE_NAME (type))));
- }
-
PROMOTE_MODE (mode, *punsignedp, type);
return mode;
@@ -7552,7 +7546,7 @@ rs6000_function_arg (cumulative_args_t cum_v, const function_arg_info &arg)
int n_elts;
/* We do not allow MMA types being used as function arguments. */
- if (mode == POImode || mode == PXImode)
+ if (mode == OOmode || mode == XOmode)
{
if (TYPE_CANONICAL (type) != NULL_TREE)
type = TYPE_CANONICAL (type);
@@ -10073,7 +10067,8 @@ mma_expand_builtin (tree exp, rtx target, bool *expandedp)
}
unsigned attr_args = attr & RS6000_BTC_OPND_MASK;
- if (attr & RS6000_BTC_QUAD)
+ if (attr & RS6000_BTC_QUAD
+ || fcode == MMA_BUILTIN_DISASSEMBLE_PAIR_INTERNAL)
attr_args++;
gcc_assert (nopnds == attr_args);
@@ -11687,23 +11682,24 @@ rs6000_gimple_fold_mma_builtin (gimple_stmt_iterator *gsi)
gimple *new_call;
tree new_decl;
- if (rs6000_builtin_info[fncode + 1].icode == CODE_FOR_nothing)
+ if (fncode == MMA_BUILTIN_DISASSEMBLE_ACC
+ || fncode == MMA_BUILTIN_DISASSEMBLE_PAIR)
{
/* This is an MMA disassemble built-in function. */
- gcc_assert (fncode == MMA_BUILTIN_DISASSEMBLE_ACC
- || fncode == MMA_BUILTIN_DISASSEMBLE_PAIR);
-
push_gimplify_context (true);
+ unsigned nvec = (fncode == MMA_BUILTIN_DISASSEMBLE_ACC) ? 4 : 2;
tree dst_ptr = gimple_call_arg (stmt, 0);
tree src_ptr = gimple_call_arg (stmt, 1);
tree src_type = TREE_TYPE (src_ptr);
tree src = make_ssa_name (TREE_TYPE (src_type));
gimplify_assign (src, build_simple_mem_ref (src_ptr), &new_seq);
- /* If we are not disassembling an accumulator or our destination is
- another accumulator, then just copy the entire thing as is. */
- if (fncode != MMA_BUILTIN_DISASSEMBLE_ACC
- || TREE_TYPE (TREE_TYPE (dst_ptr)) == vector_quad_type_node)
+ /* If we are not disassembling an accumulator/pair or our destination is
+ another accumulator/pair, then just copy the entire thing as is. */
+ if ((fncode == MMA_BUILTIN_DISASSEMBLE_ACC
+ && TREE_TYPE (TREE_TYPE (dst_ptr)) == vector_quad_type_node)
+ || (fncode == MMA_BUILTIN_DISASSEMBLE_PAIR
+ && TREE_TYPE (TREE_TYPE (dst_ptr)) == vector_pair_type_node))
{
tree dst = build_simple_mem_ref (build1 (VIEW_CONVERT_EXPR,
src_type, dst_ptr));
@@ -11713,29 +11709,33 @@ rs6000_gimple_fold_mma_builtin (gimple_stmt_iterator *gsi)
return true;
}
- /* We're disassembling an accumulator into a different type, so we need
+ /* If we're disassembling an accumulator into a different type, we need
to emit a xxmfacc instruction now, since we cannot do it later. */
- new_decl = rs6000_builtin_decls[MMA_BUILTIN_XXMFACC_INTERNAL];
- new_call = gimple_build_call (new_decl, 1, src);
- src = make_ssa_name (vector_quad_type_node);
- gimple_call_set_lhs (new_call, src);
- gimple_seq_add_stmt (&new_seq, new_call);
+ if (fncode == MMA_BUILTIN_DISASSEMBLE_ACC)
+ {
+ new_decl = rs6000_builtin_decls[MMA_BUILTIN_XXMFACC_INTERNAL];
+ new_call = gimple_build_call (new_decl, 1, src);
+ src = make_ssa_name (vector_quad_type_node);
+ gimple_call_set_lhs (new_call, src);
+ gimple_seq_add_stmt (&new_seq, new_call);
+ }
- /* Copy the accumulator vector by vector. */
+ /* Copy the accumulator/pair vector by vector. */
+ new_decl = rs6000_builtin_decls[fncode + 1];
tree dst_type = build_pointer_type_for_mode (unsigned_V16QI_type_node,
ptr_mode, true);
tree dst_base = build1 (VIEW_CONVERT_EXPR, dst_type, dst_ptr);
- tree array_type = build_array_type_nelts (unsigned_V16QI_type_node, 4);
- tree src_array = build1 (VIEW_CONVERT_EXPR, array_type, src);
- for (unsigned i = 0; i < 4; i++)
+ for (unsigned i = 0; i < nvec; i++)
{
- unsigned index = WORDS_BIG_ENDIAN ? i : 3 - i;
- tree ref = build4 (ARRAY_REF, unsigned_V16QI_type_node, src_array,
- build_int_cst (size_type_node, i),
- NULL_TREE, NULL_TREE);
+ unsigned index = WORDS_BIG_ENDIAN ? i : nvec - 1 - i;
tree dst = build2 (MEM_REF, unsigned_V16QI_type_node, dst_base,
build_int_cst (dst_type, index * 16));
- gimplify_assign (dst, ref, &new_seq);
+ tree dstssa = make_ssa_name (unsigned_V16QI_type_node);
+ new_call = gimple_build_call (new_decl, 2, src,
+ build_int_cstu (uint16_type_node, i));
+ gimple_call_set_lhs (new_call, dstssa);
+ gimple_seq_add_stmt (&new_seq, new_call);
+ gimplify_assign (dst, dstssa, &new_seq);
}
pop_gimplify_context (NULL);
gsi_replace_with_seq (gsi, new_seq, true);
@@ -13190,17 +13190,23 @@ rs6000_init_builtins (void)
/* Vector pair and vector quad support. */
if (TARGET_EXTRA_BUILTINS)
{
- vector_pair_type_node = make_unsigned_type (256);
+ vector_pair_type_node = make_node (OPAQUE_TYPE);
+ SET_TYPE_MODE (vector_pair_type_node, OOmode);
+ TYPE_SIZE (vector_pair_type_node) = bitsize_int (GET_MODE_BITSIZE (OOmode));
+ TYPE_PRECISION (vector_pair_type_node) = GET_MODE_BITSIZE (OOmode);
+ TYPE_SIZE_UNIT (vector_pair_type_node) = size_int (GET_MODE_SIZE (OOmode));
SET_TYPE_ALIGN (vector_pair_type_node, 256);
- SET_TYPE_MODE (vector_pair_type_node, POImode);
- layout_type (vector_pair_type_node);
+ TYPE_USER_ALIGN (vector_pair_type_node) = 0;
lang_hooks.types.register_builtin_type (vector_pair_type_node,
"__vector_pair");
- vector_quad_type_node = make_unsigned_type (512);
- SET_TYPE_ALIGN (vector_quad_type_node, 512);
- SET_TYPE_MODE (vector_quad_type_node, PXImode);
- layout_type (vector_quad_type_node);
+ vector_quad_type_node = make_node (OPAQUE_TYPE);
+ SET_TYPE_MODE (vector_quad_type_node, XOmode);
+ TYPE_SIZE (vector_quad_type_node) = bitsize_int (GET_MODE_BITSIZE (XOmode));
+ TYPE_PRECISION (vector_quad_type_node) = GET_MODE_BITSIZE (XOmode);
+ TYPE_SIZE_UNIT (vector_quad_type_node) = size_int (GET_MODE_SIZE (XOmode));
+ SET_TYPE_ALIGN (vector_pair_type_node, 512);
+ TYPE_USER_ALIGN (vector_quad_type_node) = 0;
lang_hooks.types.register_builtin_type (vector_quad_type_node,
"__vector_quad");
}
@@ -13236,8 +13242,8 @@ rs6000_init_builtins (void)
builtin_mode_to_type[V8HImode][1] = unsigned_V8HI_type_node;
builtin_mode_to_type[V16QImode][0] = V16QI_type_node;
builtin_mode_to_type[V16QImode][1] = unsigned_V16QI_type_node;
- builtin_mode_to_type[POImode][1] = vector_pair_type_node;
- builtin_mode_to_type[PXImode][1] = vector_quad_type_node;
+ builtin_mode_to_type[OOmode][1] = vector_pair_type_node;
+ builtin_mode_to_type[XOmode][1] = vector_quad_type_node;
tdecl = add_builtin_type ("__bool char", bool_char_type_node);
TYPE_NAME (bool_char_type_node) = tdecl;
@@ -14049,21 +14055,21 @@ mma_init_builtins (void)
}
else
{
- if ((attr & RS6000_BTC_QUAD) == 0)
+ if ( !( d->code == MMA_BUILTIN_DISASSEMBLE_ACC_INTERNAL
+ || d->code == MMA_BUILTIN_DISASSEMBLE_PAIR_INTERNAL)
+ && ((attr & RS6000_BTC_QUAD) == 0))
attr_args--;
/* Ensure we have the correct number and type of operands. */
gcc_assert (attr_args == insn_data[icode].n_operands - 1);
}
- if (icode == CODE_FOR_nothing)
+ /* This is a disassemble pair/acc function. */
+ if ( d->code == MMA_BUILTIN_DISASSEMBLE_ACC
+ || d->code == MMA_BUILTIN_DISASSEMBLE_PAIR)
{
- /* This is a disassemble MMA built-in function. */
- gcc_assert (attr_args == RS6000_BTC_BINARY
- && (d->code == MMA_BUILTIN_DISASSEMBLE_ACC
- || d->code == MMA_BUILTIN_DISASSEMBLE_PAIR));
op[nopnds++] = build_pointer_type (void_type_node);
- if (attr & RS6000_BTC_QUAD)
+ if (d->code == MMA_BUILTIN_DISASSEMBLE_ACC)
op[nopnds++] = build_pointer_type (vector_quad_type_node);
else
op[nopnds++] = build_pointer_type (vector_pair_type_node);
@@ -14071,13 +14077,17 @@ mma_init_builtins (void)
else
{
/* This is a normal MMA built-in function. */
- unsigned j = (attr & RS6000_BTC_QUAD) ? 1 : 0;
+ unsigned j = 0;
+ if (attr & RS6000_BTC_QUAD
+ && d->code != MMA_BUILTIN_DISASSEMBLE_ACC_INTERNAL
+ && d->code != MMA_BUILTIN_DISASSEMBLE_PAIR_INTERNAL)
+ j = 1;
for (; j < (unsigned) insn_data[icode].n_operands; j++)
{
machine_mode mode = insn_data[icode].operand[j].mode;
- if (gimple_func && mode == PXImode)
+ if (gimple_func && mode == XOmode)
op[nopnds++] = build_pointer_type (vector_quad_type_node);
- else if (gimple_func && mode == POImode
+ else if (gimple_func && mode == OOmode
&& d->code == MMA_BUILTIN_ASSEMBLE_PAIR)
op[nopnds++] = build_pointer_type (vector_pair_type_node);
else
@@ -83,12 +83,6 @@ VECTOR_MODE (INT, SI, 2); /* V2SI */
combination. */
PARTIAL_INT_MODE (TI, 128, PTI);
-/* Define, but don't use the larger integer modes. We need an integer mode
- defined that is the same size as the vector pair and vector quad modes. */
-
-INT_MODE (OI, 32);
-INT_MODE (XI, 64);
-
/* Modes used by __vector_pair and __vector_quad. */
-PARTIAL_INT_MODE (OI, 256, POI); /* __vector_pair. */
-PARTIAL_INT_MODE (XI, 512, PXI); /* __vector_quad. */
+OPAQUE_MODE (OO, 32); /* instead of POI */
+OPAQUE_MODE (XO, 64); /* instead of PXI */
@@ -2787,7 +2787,7 @@ expand_block_move (rtx operands[], bool might_overlap)
rtx src, dest;
bool move_with_length = false;
- /* Use POImode for paired vsx load/store. Use V2DI for single
+ /* Use OOmode for paired vsx load/store. Use V2DI for single
unaligned vsx load/store, for consistency with what other
expansions (compare) already do, and so we can use lxvd2x on
p8. Order is VSX pair unaligned, VSX unaligned, Altivec, VSX
@@ -2799,8 +2799,8 @@ expand_block_move (rtx operands[], bool might_overlap)
&& (align >= 256 || !STRICT_ALIGNMENT))
{
move_bytes = 32;
- mode = POImode;
- gen_func.mov = gen_movpoi;
+ mode = OOmode;
+ gen_func.mov = gen_movoo;
}
else if (TARGET_POWERPC64 && TARGET_BLOCK_OPS_UNALIGNED_VSX
&& VECTOR_MEM_VSX_P (V2DImode)
@@ -1826,15 +1826,12 @@ rs6000_hard_regno_mode_ok_uncached (int regno, machine_mode mode)
mode = GET_MODE_INNER (mode);
/* Vector pair modes need even/odd VSX register pairs. Only allow vector
- registers. We need to allow OImode to have the same registers as POImode,
- even though we do not enable the move pattern for OImode. */
- if (mode == POImode || mode == OImode)
+ registers. */
+ if (mode == OOmode)
return (TARGET_MMA && VSX_REGNO_P (regno) && (regno & 1) == 0);
- /* MMA accumulator modes need FPR registers divisible by 4. We need to allow
- XImode to have the same registers as PXImode, even though we do not enable
- the move pattern for XImode. */
- if (mode == PXImode || mode == XImode)
+ /* MMA accumulator modes need FPR registers divisible by 4. */
+ if (mode == XOmode)
return (TARGET_MMA && FP_REGNO_P (regno) && (regno & 3) == 0);
/* PTImode can only go in GPRs. Quad word memory operations require even/odd
@@ -1941,8 +1938,8 @@ rs6000_hard_regno_mode_ok (unsigned int regno, machine_mode mode)
GPR registers, and TImode can go in any GPR as well as VSX registers (PR
57744).
- Similarly, don't allow POImode (vector pair, restricted to even VSX
- registers) or PXImode (vector quad, restricted to FPR registers divisible
+ Similarly, don't allow OOmode (vector pair, restricted to even VSX
+ registers) or XOmode (vector quad, restricted to FPR registers divisible
by 4) to tie with other modes.
Altivec/VSX vector tests were moved ahead of scalar float mode, so that IEEE
@@ -1951,8 +1948,8 @@ rs6000_hard_regno_mode_ok (unsigned int regno, machine_mode mode)
static bool
rs6000_modes_tieable_p (machine_mode mode1, machine_mode mode2)
{
- if (mode1 == PTImode || mode1 == POImode || mode1 == PXImode
- || mode2 == PTImode || mode2 == POImode || mode2 == PXImode)
+ if (mode1 == PTImode || mode1 == OOmode || mode1 == XOmode
+ || mode2 == PTImode || mode2 == OOmode || mode2 == XOmode)
return mode1 == mode2;
if (ALTIVEC_OR_VSX_VECTOR_MODE (mode1))
@@ -2241,10 +2238,8 @@ rs6000_debug_reg_global (void)
V2DFmode,
V8SFmode,
V4DFmode,
- OImode,
- XImode,
- POImode,
- PXImode,
+ OOmode,
+ XOmode,
CCmode,
CCUNSmode,
CCEQmode,
@@ -2706,13 +2701,13 @@ rs6000_setup_reg_addr_masks (void)
since it will be broken into two vector moves. Vector quads can
only do offset loads. */
else if ((addr_mask != 0) && TARGET_MMA
- && (m2 == POImode || m2 == PXImode))
+ && (m2 == OOmode || m2 == XOmode))
{
addr_mask |= RELOAD_REG_OFFSET;
if (rc == RELOAD_REG_FPR || rc == RELOAD_REG_VMX)
{
addr_mask |= RELOAD_REG_QUAD_OFFSET;
- if (m2 == POImode)
+ if (m2 == OOmode)
addr_mask |= RELOAD_REG_INDEXED;
}
}
@@ -2921,13 +2916,13 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
/* Add support for vector pairs and vector quad registers. */
if (TARGET_MMA)
{
- rs6000_vector_unit[POImode] = VECTOR_NONE;
- rs6000_vector_mem[POImode] = VECTOR_VSX;
- rs6000_vector_align[POImode] = 256;
+ rs6000_vector_unit[OOmode] = VECTOR_NONE;
+ rs6000_vector_mem[OOmode] = VECTOR_VSX;
+ rs6000_vector_align[OOmode] = 256;
- rs6000_vector_unit[PXImode] = VECTOR_NONE;
- rs6000_vector_mem[PXImode] = VECTOR_VSX;
- rs6000_vector_align[PXImode] = 512;
+ rs6000_vector_unit[XOmode] = VECTOR_NONE;
+ rs6000_vector_mem[XOmode] = VECTOR_VSX;
+ rs6000_vector_align[XOmode] = 512;
}
/* Register class constraints for the constraints that depend on compile
@@ -3064,10 +3059,10 @@ rs6000_init_hard_regno_mode_ok (bool global_init_p)
if (TARGET_MMA)
{
- reg_addr[POImode].reload_store = CODE_FOR_reload_poi_di_store;
- reg_addr[POImode].reload_load = CODE_FOR_reload_poi_di_load;
- reg_addr[PXImode].reload_store = CODE_FOR_reload_pxi_di_store;
- reg_addr[PXImode].reload_load = CODE_FOR_reload_pxi_di_load;
+ reg_addr[OOmode].reload_store = CODE_FOR_reload_oo_di_store;
+ reg_addr[OOmode].reload_load = CODE_FOR_reload_oo_di_load;
+ reg_addr[XOmode].reload_store = CODE_FOR_reload_xo_di_store;
+ reg_addr[XOmode].reload_load = CODE_FOR_reload_xo_di_load;
}
}
}
@@ -8129,8 +8124,8 @@ reg_offset_addressing_ok_p (machine_mode mode)
/* The vector pair/quad types support offset addressing if the
underlying vectors support offset addressing. */
- case E_POImode:
- case E_PXImode:
+ case E_OOmode:
+ case E_XOmode:
return TARGET_MMA;
case E_SDmode:
@@ -10323,11 +10318,11 @@ rs6000_emit_move (rtx dest, rtx source, machine_mode mode)
operands[1] = force_const_mem (mode, operands[1]);
break;
- case E_POImode:
- case E_PXImode:
+ case E_OOmode:
+ case E_XOmode:
if (CONST_INT_P (operands[1]) && INTVAL (operands[1]) != 0)
error ("%qs is an opaque type, and you can't set it to other values.",
- (mode == POImode) ? "__vector_pair" : "__vector_quad");
+ (mode == OOmode) ? "__vector_pair" : "__vector_quad");
break;
case E_SImode:
@@ -12596,10 +12591,10 @@ rs6000_preferred_reload_class (rtx x, enum reg_class rclass)
the GPR registers. */
if (rclass == GEN_OR_FLOAT_REGS)
{
- if (mode == POImode)
+ if (mode == OOmode)
return VSX_REGS;
- if (mode == PXImode)
+ if (mode == XOmode)
return FLOAT_REGS;
if (GET_MODE_CLASS (mode) == MODE_INT)
@@ -16323,15 +16318,15 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we have a vector quad register for MMA, and this is a load or store,
see if we can use vector paired load/stores. */
- if (mode == PXImode && TARGET_MMA
+ if (mode == XOmode && TARGET_MMA
&& (MEM_P (dst) || MEM_P (src)))
{
- reg_mode = POImode;
+ reg_mode = OOmode;
nregs /= 2;
}
/* If we have a vector pair/quad mode, split it into two/four separate
vectors. */
- else if (mode == POImode || mode == PXImode)
+ else if (mode == OOmode || mode == XOmode)
reg_mode = V1TImode;
else if (FP_REGNO_P (reg))
reg_mode = DECIMAL_FLOAT_MODE_P (mode) ? DDmode :
@@ -16377,12 +16372,16 @@ rs6000_split_multireg_move (rtx dst, rtx src)
return;
}
- /* The __vector_pair and __vector_quad modes are multi-register modes,
- so if have to load or store the registers, we have to be careful to
- properly swap them if we're in little endian mode below. This means
- the last register gets the first memory location. */
- if (mode == POImode || mode == PXImode)
+ /* The __vector_pair and __vector_quad modes are multi-register
+ modes, so if have to load or store the registers, we have to be
+ careful to properly swap them if we're in little endian mode
+ below. This means the last register gets the first memory
+ location. We also need to be careful of using the right register
+ numbers if we are splitting XO to OO. */
+ if (mode == OOmode || mode == XOmode)
{
+ nregs = hard_regno_nregs (reg, mode);
+ int reg_mode_nregs = hard_regno_nregs (reg, reg_mode);
if (MEM_P (dst))
{
unsigned offset = 0;
@@ -16391,15 +16390,15 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
if (TARGET_MMA
- && GET_MODE (src) == PXImode && FP_REGNO_P (REGNO (src)))
+ && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
- for (int i = 0; i < nregs; i++)
+ for (int i = 0; i < nregs; i += reg_mode_nregs)
{
- unsigned subreg = (WORDS_BIG_ENDIAN)
- ? i * size : (nregs - 1 - i) * size;
+ unsigned subreg =
+ (WORDS_BIG_ENDIAN) ? i : (nregs - reg_mode_nregs - i);
rtx dst2 = adjust_address (dst, reg_mode, offset);
- rtx src2 = simplify_gen_subreg (reg_mode, src, mode, subreg);
+ rtx src2 = gen_rtx_REG (reg_mode, reg + subreg);
offset += size;
emit_insn (gen_rtx_SET (dst2, src2));
}
@@ -16412,11 +16411,11 @@ rs6000_split_multireg_move (rtx dst, rtx src)
unsigned offset = 0;
unsigned size = GET_MODE_SIZE (reg_mode);
- for (int i = 0; i < nregs; i++)
+ for (int i = 0; i < nregs; i += reg_mode_nregs)
{
- unsigned subreg = (WORDS_BIG_ENDIAN)
- ? i * size : (nregs - 1 - i) * size;
- rtx dst2 = simplify_gen_subreg (reg_mode, dst, mode, subreg);
+ unsigned subreg =
+ (WORDS_BIG_ENDIAN) ? i : (nregs - reg_mode_nregs - i);
+ rtx dst2 = gen_rtx_REG (reg_mode, reg + subreg);
rtx src2 = adjust_address (src, reg_mode, offset);
offset += size;
emit_insn (gen_rtx_SET (dst2, src2));
@@ -16425,7 +16424,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
if (TARGET_MMA
- && GET_MODE (dst) == PXImode && FP_REGNO_P (REGNO (dst)))
+ && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
return;
@@ -16434,8 +16433,11 @@ rs6000_split_multireg_move (rtx dst, rtx src)
if (GET_CODE (src) == UNSPEC)
{
gcc_assert (REG_P (dst)
- && FP_REGNO_P (REGNO (dst))
- && XINT (src, 1) == UNSPEC_MMA_ASSEMBLE_ACC);
+ && ((GET_MODE (src) == XOmode
+ && FP_REGNO_P (REGNO (dst)))
+ || (GET_MODE (src) == OOmode
+ && VSX_REGNO_P (REGNO (dst))))
+ && XINT (src, 1) == UNSPEC_MMA_ASSEMBLE);
reg_mode = GET_MODE (XVECEXP (src, 0, 0));
for (int i = 0; i < XVECLEN (src, 0); i++)
@@ -16444,9 +16446,12 @@ rs6000_split_multireg_move (rtx dst, rtx src)
emit_insn (gen_rtx_SET (dst_i, XVECEXP (src, 0, i)));
}
- /* We are writing an accumulator register, so we have to
- prime it after we've written it. */
- emit_insn (gen_mma_xxmtacc (dst, dst));
+ if ( GET_MODE (src) == XOmode )
+ {
+ /* We are writing an accumulator register, so we have to
+ prime it after we've written it. */
+ emit_insn (gen_mma_xxmtacc (dst, dst));
+ }
return;
}
@@ -16459,22 +16464,35 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
if (TARGET_MMA
- && GET_MODE (src) == PXImode && FP_REGNO_P (REGNO (src)))
+ && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
/* Move register range backwards, if we might have destructive
overlap. */
int i;
- for (i = nregs - 1; i >= 0; i--)
- emit_insn (gen_rtx_SET (simplify_gen_subreg (reg_mode, dst, mode,
- i * reg_mode_size),
- simplify_gen_subreg (reg_mode, src, mode,
- i * reg_mode_size)));
+ /* XO/OO are opaque so cannot use subregs. */
+ if ( mode == OOmode || mode == XOmode )
+ {
+ for (i = nregs - 1; i >= 0; i--)
+ {
+ rtx dst_i = gen_rtx_REG (reg_mode, REGNO (dst) + i);
+ rtx src_i = gen_rtx_REG (reg_mode, REGNO (src) + i);
+ emit_insn (gen_rtx_SET (dst_i, src_i));
+ }
+ }
+ else
+ {
+ for (i = nregs - 1; i >= 0; i--)
+ emit_insn (gen_rtx_SET (simplify_gen_subreg (reg_mode, dst, mode,
+ i * reg_mode_size),
+ simplify_gen_subreg (reg_mode, src, mode,
+ i * reg_mode_size)));
+ }
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
if (TARGET_MMA
- && GET_MODE (dst) == PXImode && FP_REGNO_P (REGNO (dst)))
+ && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
}
else
@@ -16611,7 +16629,7 @@ rs6000_split_multireg_move (rtx dst, rtx src)
/* If we are reading an accumulator register, we have to
deprime it before we can access it. */
if (TARGET_MMA && REG_P (src)
- && GET_MODE (src) == PXImode && FP_REGNO_P (REGNO (src)))
+ && GET_MODE (src) == XOmode && FP_REGNO_P (REGNO (src)))
emit_insn (gen_mma_xxmfacc (src, src));
for (i = 0; i < nregs; i++)
@@ -16626,16 +16644,24 @@ rs6000_split_multireg_move (rtx dst, rtx src)
if (j == 0 && used_update)
continue;
- emit_insn (gen_rtx_SET (simplify_gen_subreg (reg_mode, dst, mode,
- j * reg_mode_size),
- simplify_gen_subreg (reg_mode, src, mode,
- j * reg_mode_size)));
+ /* XO/OO are opaque so cannot use subregs. */
+ if ( mode == OOmode || mode == XOmode )
+ {
+ rtx dst_i = gen_rtx_REG (reg_mode, REGNO (dst) + j);
+ rtx src_i = gen_rtx_REG (reg_mode, REGNO (src) + j);
+ emit_insn (gen_rtx_SET (dst_i, src_i));
+ }
+ else
+ emit_insn (gen_rtx_SET (simplify_gen_subreg (reg_mode, dst, mode,
+ j * reg_mode_size),
+ simplify_gen_subreg (reg_mode, src, mode,
+ j * reg_mode_size)));
}
/* If we are writing an accumulator register, we have to
prime it after we've written it. */
if (TARGET_MMA && REG_P (dst)
- && GET_MODE (dst) == PXImode && FP_REGNO_P (REGNO (dst)))
+ && GET_MODE (dst) == XOmode && FP_REGNO_P (REGNO (dst)))
emit_insn (gen_mma_xxmtacc (dst, dst));
if (restore_basereg != NULL_RTX)
@@ -19865,7 +19891,8 @@ rs6000_mangle_type (const_tree type)
type = TYPE_MAIN_VARIANT (type);
if (TREE_CODE (type) != VOID_TYPE && TREE_CODE (type) != BOOLEAN_TYPE
- && TREE_CODE (type) != INTEGER_TYPE && TREE_CODE (type) != REAL_TYPE)
+ && TREE_CODE (type) != INTEGER_TYPE && TREE_CODE (type) != REAL_TYPE
+ && TREE_CODE (type) != OPAQUE_TYPE)
return NULL;
if (type == bool_char_type_node) return "U6__boolc";
@@ -27186,14 +27213,14 @@ rs6000_invalid_conversion (const_tree fromtype, const_tree totype)
if (frommode != tomode)
{
- /* Do not allow conversions to/from PXImode and POImode types. */
- if (frommode == PXImode)
+ /* Do not allow conversions to/from XOmode and OOmode types. */
+ if (frommode == XOmode)
return N_("invalid conversion from type %<__vector_quad%>");
- if (tomode == PXImode)
+ if (tomode == XOmode)
return N_("invalid conversion to type %<__vector_quad%>");
- if (frommode == POImode)
+ if (frommode == OOmode)
return N_("invalid conversion from type %<__vector_pair%>");
- if (tomode == POImode)
+ if (tomode == OOmode)
return N_("invalid conversion to type %<__vector_pair%>");
}
else if (POINTER_TYPE_P (fromtype) && POINTER_TYPE_P (totype))
@@ -27202,19 +27229,19 @@ rs6000_invalid_conversion (const_tree fromtype, const_tree totype)
frommode = TYPE_MODE (TREE_TYPE (fromtype));
tomode = TYPE_MODE (TREE_TYPE (totype));
- /* Do not allow conversions to/from PXImode and POImode pointer
+ /* Do not allow conversions to/from XOmode and OOmode pointer
types, except to/from void pointers. */
if (frommode != tomode
&& frommode != VOIDmode
&& tomode != VOIDmode)
{
- if (frommode == PXImode)
+ if (frommode == XOmode)
return N_("invalid conversion from type %<* __vector_quad%>");
- if (tomode == PXImode)
+ if (tomode == XOmode)
return N_("invalid conversion to type %<* __vector_quad%>");
- if (frommode == POImode)
+ if (frommode == OOmode)
return N_("invalid conversion from type %<* __vector_pair%>");
- if (tomode == POImode)
+ if (tomode == OOmode)
return N_("invalid conversion to type %<* __vector_pair%>");
}
}
@@ -1041,7 +1041,7 @@ enum data_align { align_abi, align_opt, align_both };
/* Modes that are not vectors, but require vector alignment. Treat these like
vectors in terms of loads and stores. */
#define VECTOR_ALIGNMENT_P(MODE) \
- (FLOAT128_VECTOR_P (MODE) || (MODE) == POImode || (MODE) == PXImode)
+ (FLOAT128_VECTOR_P (MODE) || (MODE) == OOmode || (MODE) == XOmode)
#define ALTIVEC_VECTOR_MODE(MODE) \
((MODE) == V16QImode \
@@ -2556,6 +2556,7 @@ typedef struct GTY(()) machine_function
bool fpr_is_wrapped_separately[32];
bool lr_is_wrapped_separately;
bool toc_is_wrapped_separately;
+ bool mma_return_type_error;
} machine_function;
#endif
@@ -778,7 +778,7 @@ (define_mode_attr BOOL_REGS_UNARY [(TI "r,0,0,wa,v")
;; supplement addressing modes.
(define_mode_iterator RELOAD [V16QI V8HI V4SI V2DI V4SF V2DF V1TI
SF SD SI DF DD DI TI PTI KF IF TF
- POI PXI])
+ OO XO])
;; Iterate over smin, smax
(define_code_iterator fp_minmax [smin smax])
@@ -181,6 +181,9 @@ main (int argc, char *argv[])
printf ("MMA double test fail: %d errors\n",ret);
else
printf ("MMA single test success: 0 MMA errors\n");
+#else
+ if (ret)
+ abort();
#endif
return ret;
@@ -189,6 +189,9 @@ main (int argc, char *argv[])
printf ("MMA single test fail: %d errors\n",ret);
else
printf ("MMA single test success: 0 MMA errors\n");
+#else
+ if (ret)
+ abort();
#endif
return ret;
similarity index 61%
rename from gcc/testsuite/gcc.target/powerpc/pr96506.c
rename to gcc/testsuite/gcc.target/powerpc/pr96506-1.c
@@ -40,27 +40,3 @@ foo3 (void)
vquad_t v;
bar3 (v); /* { dg-error "invalid use of MMA operand of type .__vector_quad. as a function parameter" } */
}
-
-__vector_pair
-foo4 (__vector_pair *src) /* { dg-error "invalid use of MMA type .__vector_pair. as a function return value" } */
-{
- return *src;
-}
-
-vpair_t
-foo5 (vpair_t *src) /* { dg-error "invalid use of MMA type .__vector_pair. as a function return value" } */
-{
- return *src;
-}
-
-__vector_quad
-foo6 (__vector_quad *src) /* { dg-error "invalid use of MMA type .__vector_quad. as a function return value" } */
-{
- return *src;
-}
-
-vquad_t
-foo7 (vquad_t *src) /* { dg-error "invalid use of MMA type .__vector_quad. as a function return value" } */
-{
- return *src;
-}
new file mode 100644
@@ -0,0 +1,38 @@
+/* PR target/96506 */
+/* { dg-do compile } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-options "-mdejagnu-cpu=power10 -O2" } */
+
+extern void bar0();
+extern void bar1();
+extern void bar2();
+extern void bar3();
+
+typedef __vector_pair vpair_t;
+typedef __vector_quad vquad_t;
+
+/* Verify we flag errors on the following. */
+
+__vector_pair
+foo4 (__vector_pair *src)
+{ /* { dg-error "invalid use of MMA type .__vector_pair. as a function return value" } */
+ return *src;
+}
+
+vpair_t
+foo5 (vpair_t *src)
+{ /* { dg-error "invalid use of MMA type .__vector_pair. as a function return value" } */
+ return *src;
+}
+
+__vector_quad
+foo6 (__vector_quad *src)
+{ /* { dg-error "invalid use of MMA type .__vector_quad. as a function return value" } */
+ return *src;
+}
+
+vquad_t
+foo7 (vquad_t *src)
+{ /* { dg-error "invalid use of MMA type .__vector_quad. as a function return value" } */
+ return *src;
+}
From: Aaron Sawdey <acsawdey@linux.ibm.com> This patch changes powerpc MMA builtins to use the new opaque mode class and use modes OO (32 bytes) and XO (64 bytes) instead of POI/PXI. Using the opaque modes prevents optimization from trying to do anything with vector pair/quad, which was the problem we were seeing with the partial integer modes. OK for trunk if bootstrap/regtest passes? gcc/ * gcc/config/rs6000/mma.md (unspec): Add assemble/extract UNSPECs. (movoi): Change to movoo. (*movpoi): Change to *movoo. (movxi): Change to movxo. (*movpxi): Change to *movxo. (mma_assemble_pair): Change to OO mode. (*mma_assemble_pair): New define_insn_and_split. (mma_disassemble_pair): New define_expand. (*mma_disassemble_pair): New define_insn_and_split. (mma_assemble_acc): Change to XO mode. (*mma_assemble_acc): Change to XO mode. (mma_disassemble_acc): New define_expand. (*mma_disassemble_acc): New define_insn_and_split. (mma_<acc>): Change to XO mode. (mma_<vv>): Change to XO mode. (mma_<avv>): Change to XO mode. (mma_<pv>): Change to OO mode. (mma_<apv>): Change to XO/OO mode. (mma_<vvi4i4i8>): Change to XO mode. (mma_<avvi4i4i8>): Change to XO mode. (mma_<vvi4i4i2>): Change to XO mode. (mma_<avvi4i4i2>): Change to XO mode. (mma_<vvi4i4>): Change to XO mode. (mma_<avvi4i4>): Change to XO mode. (mma_<pvi4i2>): Change to XO/OO mode. (mma_<apvi4i2>): Change to XO/OO mode. (mma_<vvi4i4i4>): Change to XO mode. (mma_<avvi4i4i4>): Change to XO mode. * gcc/config/rs6000/predicates.md (input_operand): Allow opaque. (mma_disassemble_output_operand): New predicate. * gcc/config/rs6000/rs6000-builtin.def: Changes to disassemble builtins. * gcc/config/rs6000/rs6000-call.c (rs6000_return_in_memory): Disallow __vector_pair/__vector_quad as return types. (rs6000_promote_function_mode): Remove function return type check because we can't test it here any more. (rs6000_function_arg): Do not allow __vector_pair/__vector_quad as as function arguments. (rs6000_gimple_fold_mma_builtin): Handle mma_disassemble_* builtins. (rs6000_init_builtins): Create types for XO/OO modes. * gcc/config/rs6000/rs6000-modes.def: Create XO and OO modes. * gcc/config/rs6000/rs6000-string.c (expand_block_move): Update to OO mode. * gcc/config/rs6000/rs6000.c (rs6000_hard_regno_mode_ok_uncached): Update for XO/OO modes. (rs6000_modes_tieable_p): Update for XO/OO modes. (rs6000_debug_reg_global): Update for XO/OO modes. (rs6000_setup_reg_addr_masks): Update for XO/OO modes. (rs6000_init_hard_regno_mode_ok): Update for XO/OO modes. (reg_offset_addressing_ok_p): Update for XO/OO modes. (rs6000_emit_move): Update for XO/OO modes. (rs6000_preferred_reload_class): Update for XO/OO modes. (rs6000_split_multireg_move): Update for XO/OO modes. (rs6000_mangle_type): Update for opaque types. (rs6000_invalid_conversion): Update for XO/OO modes. * gcc/config/rs6000/rs6000.h (VECTOR_ALIGNMENT_P): Update for XO/OO modes. * gcc/config/rs6000/rs6000.md (RELOAD): Update for XO/OO modes. gcc/testsuite/ * gcc.target/powerpc/mma-double-test.c (main): Call abort for failure. * gcc.target/powerpc/mma-single-test.c (main): Call abort for failure. * gcc.target/powerpc/pr96506.c: Rename to pr96506-1.c. * gcc.target/powerpc/pr96506-2.c: New test. --- gcc/config/rs6000/mma.md | 385 ++++++++++-------- gcc/config/rs6000/predicates.md | 14 +- gcc/config/rs6000/rs6000-builtin.def | 14 +- gcc/config/rs6000/rs6000-call.c | 144 ++++--- gcc/config/rs6000/rs6000-modes.def | 10 +- gcc/config/rs6000/rs6000-string.c | 6 +- gcc/config/rs6000/rs6000.c | 189 +++++---- gcc/config/rs6000/rs6000.h | 3 +- gcc/config/rs6000/rs6000.md | 2 +- .../gcc.target/powerpc/mma-double-test.c | 3 + .../gcc.target/powerpc/mma-single-test.c | 3 + .../powerpc/{pr96506.c => pr96506-1.c} | 24 -- gcc/testsuite/gcc.target/powerpc/pr96506-2.c | 38 ++ 13 files changed, 482 insertions(+), 353 deletions(-) rename gcc/testsuite/gcc.target/powerpc/{pr96506.c => pr96506-1.c} (61%) create mode 100644 gcc/testsuite/gcc.target/powerpc/pr96506-2.c