[gcc(refs/vendors/ibm/heads/perf)] Fix PR target/93932
Jiu Fu Guo
guojiufu@gcc.gnu.org
Thu Mar 19 05:57:08 GMT 2020
https://gcc.gnu.org/g:75c299acc47b19fd6c445a6931798325a54e6fb4
commit 75c299acc47b19fd6c445a6931798325a54e6fb4
Author: Michael Meissner <meissner@gcc.gnu.org>
Date: Thu Feb 27 14:41:39 2020 -0500
Fix PR target/93932
[gcc]
2020-02-27 Michael Meissner <meissner@linux.ibm.com>
PR target/93932
* config/rs6000/vsx.md (vsx_extract_<mode>_var, VSX_D iterator):
Split the insn into two parts. This insn only does variable
extract from a register.
(vsx_extract_<mode>_var_load, VSX_D iterator): New insn, do
variable extract from memory.
(vsx_extract_v4sf_var): Split the insn into two parts. This insn
only does variable extract from a register.
(vsx_extract_v4sf_var_load): New insn, do variable extract from
memory.
(vsx_extract_<mode>_var, VSX_EXTRACT_I iterator): Split the insn
into two parts. This insn only does variable extract from a
register.
(vsx_extract_<mode>_var_load, VSX_EXTRACT_I iterator): New insn,
do variable extract from memory.
[gcc/testsuite]
2020-02-27 Michael Meissner <meissner@linux.ibm.com>
PR target/93932
* gcc.target/powerpc/fold-vec-extract-longlong.p8.c: Adjust
instruction counts.
Diff:
---
gcc/ChangeLog | 18 +++++
gcc/config/rs6000/vsx.md | 90 +++++++++++++++++-----
gcc/testsuite/ChangeLog | 6 ++
.../powerpc/fold-vec-extract-longlong.p8.c | 25 +++---
4 files changed, 107 insertions(+), 32 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 38064ccbdb8..f5d4e6dd582 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,21 @@
+2020-02-27 Michael Meissner <meissner@linux.ibm.com>
+
+ PR target/93932
+ * config/rs6000/vsx.md (vsx_extract_<mode>_var, VSX_D iterator):
+ Split the insn into two parts. This insn only does variable
+ extract from a register.
+ (vsx_extract_<mode>_var_load, VSX_D iterator): New insn, do
+ variable extract from memory.
+ (vsx_extract_v4sf_var): Split the insn into two parts. This insn
+ only does variable extract from a register.
+ (vsx_extract_v4sf_var_load): New insn, do variable extract from
+ memory.
+ (vsx_extract_<mode>_var, VSX_EXTRACT_I iterator): Split the insn
+ into two parts. This insn only does variable extract from a
+ register.
+ (vsx_extract_<mode>_var_load, VSX_EXTRACT_I iterator): New insn,
+ do variable extract from memory.
+
2020-02-27 Martin Jambor <mjambor@suse.cz>
Feng Xue <fxue@os.amperecomputing.com>
diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md
index 189c7d842ac..b5d80f677dc 100644
--- a/gcc/config/rs6000/vsx.md
+++ b/gcc/config/rs6000/vsx.md
@@ -3245,14 +3245,14 @@
"vslo %0,%1,%2"
[(set_attr "type" "vecperm")])
-;; Variable V2DI/V2DF extract
+;; Variable V2DI/V2DF extract from a register
(define_insn_and_split "vsx_extract_<mode>_var"
- [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=v,wa,r")
- (unspec:<VS_scalar> [(match_operand:VSX_D 1 "input_operand" "v,Q,Q")
- (match_operand:DI 2 "gpc_reg_operand" "r,r,r")]
+ [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=v")
+ (unspec:<VS_scalar> [(match_operand:VSX_D 1 "gpc_reg_operand" "v")
+ (match_operand:DI 2 "gpc_reg_operand" "r")]
UNSPEC_VSX_EXTRACT))
- (clobber (match_scratch:DI 3 "=r,&b,&b"))
- (clobber (match_scratch:V2DI 4 "=&v,X,X"))]
+ (clobber (match_scratch:DI 3 "=r"))
+ (clobber (match_scratch:V2DI 4 "=&v"))]
"VECTOR_MEM_VSX_P (<MODE>mode) && TARGET_DIRECT_MOVE_64BIT"
"#"
"&& reload_completed"
@@ -3263,6 +3263,23 @@
DONE;
})
+;; Variable V2DI/V2DF extract from memory
+(define_insn_and_split "*vsx_extract_<mode>_var_load"
+ [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=wa,r")
+ (unspec:<VS_scalar> [(match_operand:VSX_D 1 "memory_operand" "Q,Q")
+ (match_operand:DI 2 "gpc_reg_operand" "r,r")]
+ UNSPEC_VSX_EXTRACT))
+ (clobber (match_scratch:DI 3 "=&b,&b"))]
+ "VECTOR_MEM_VSX_P (<MODE>mode) && TARGET_DIRECT_MOVE_64BIT"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0) (match_dup 4))]
+{
+ operands[4] = rs6000_adjust_vec_address (operands[0], operands[1], operands[2],
+ operands[3], <VS_scalar>mode);
+}
+ [(set_attr "type" "fpload,load")])
+
;; Extract a SF element from V4SF
(define_insn_and_split "vsx_extract_v4sf"
[(set (match_operand:SF 0 "vsx_register_operand" "=wa")
@@ -3315,14 +3332,14 @@
(set_attr "length" "8")
(set_attr "isa" "*,p7v,p9v,*")])
-;; Variable V4SF extract
+;; Variable V4SF extract from a register
(define_insn_and_split "vsx_extract_v4sf_var"
- [(set (match_operand:SF 0 "gpc_reg_operand" "=wa,wa,?r")
- (unspec:SF [(match_operand:V4SF 1 "input_operand" "v,Q,Q")
- (match_operand:DI 2 "gpc_reg_operand" "r,r,r")]
+ [(set (match_operand:SF 0 "gpc_reg_operand" "=wa")
+ (unspec:SF [(match_operand:V4SF 1 "gpc_reg_operand" "v")
+ (match_operand:DI 2 "gpc_reg_operand" "r")]
UNSPEC_VSX_EXTRACT))
- (clobber (match_scratch:DI 3 "=r,&b,&b"))
- (clobber (match_scratch:V2DI 4 "=&v,X,X"))]
+ (clobber (match_scratch:DI 3 "=r"))
+ (clobber (match_scratch:V2DI 4 "=&v"))]
"VECTOR_MEM_VSX_P (V4SFmode) && TARGET_DIRECT_MOVE_64BIT"
"#"
"&& reload_completed"
@@ -3333,6 +3350,23 @@
DONE;
})
+;; Variable V4SF extract from memory
+(define_insn_and_split "*vsx_extract_v4sf_var_load"
+ [(set (match_operand:SF 0 "gpc_reg_operand" "=wa,?r")
+ (unspec:SF [(match_operand:V4SF 1 "memory_operand" "Q,Q")
+ (match_operand:DI 2 "gpc_reg_operand" "r,r")]
+ UNSPEC_VSX_EXTRACT))
+ (clobber (match_scratch:DI 3 "=&b,&b"))]
+ "VECTOR_MEM_VSX_P (V4SFmode) && TARGET_DIRECT_MOVE_64BIT"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0) (match_dup 4))]
+{
+ operands[4] = rs6000_adjust_vec_address (operands[0], operands[1], operands[2],
+ operands[3], SFmode);
+}
+ [(set_attr "type" "fpload,load")])
+
;; Expand the builtin form of xxpermdi to canonical rtl.
(define_expand "vsx_xxpermdi_<mode>"
[(match_operand:VSX_L 0 "vsx_register_operand")
@@ -3677,15 +3711,15 @@
[(set_attr "type" "load")
(set_attr "length" "8")])
-;; Variable V16QI/V8HI/V4SI extract
+;; Variable V16QI/V8HI/V4SI extract from a register
(define_insn_and_split "vsx_extract_<mode>_var"
- [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=r,r,r")
+ [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=r,r")
(unspec:<VS_scalar>
- [(match_operand:VSX_EXTRACT_I 1 "input_operand" "v,v,Q")
- (match_operand:DI 2 "gpc_reg_operand" "r,r,r")]
+ [(match_operand:VSX_EXTRACT_I 1 "gpc_reg_operand" "v,v")
+ (match_operand:DI 2 "gpc_reg_operand" "r,r")]
UNSPEC_VSX_EXTRACT))
- (clobber (match_scratch:DI 3 "=r,r,&b"))
- (clobber (match_scratch:V2DI 4 "=X,&v,X"))]
+ (clobber (match_scratch:DI 3 "=r,r"))
+ (clobber (match_scratch:V2DI 4 "=X,&v"))]
"VECTOR_MEM_VSX_P (<MODE>mode) && TARGET_DIRECT_MOVE_64BIT"
"#"
"&& reload_completed"
@@ -3695,7 +3729,25 @@
operands[3], operands[4]);
DONE;
}
- [(set_attr "isa" "p9v,*,*")])
+ [(set_attr "isa" "p9v,*")])
+
+;; Variable V16QI/V8HI/V4SI extract from memory
+(define_insn_and_split "*vsx_extract_<mode>_var_load"
+ [(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=r")
+ (unspec:<VS_scalar>
+ [(match_operand:VSX_EXTRACT_I 1 "memory_operand" "Q")
+ (match_operand:DI 2 "gpc_reg_operand" "r")]
+ UNSPEC_VSX_EXTRACT))
+ (clobber (match_scratch:DI 3 "=&b"))]
+ "VECTOR_MEM_VSX_P (<MODE>mode) && TARGET_DIRECT_MOVE_64BIT"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0) (match_dup 4))]
+{
+ operands[4] = rs6000_adjust_vec_address (operands[0], operands[1], operands[2],
+ operands[3], <VS_scalar>mode);
+}
+ [(set_attr "type" "load")])
(define_insn_and_split "*vsx_extract_<mode>_<VS_scalar>mode_var"
[(set (match_operand:<VS_scalar> 0 "gpc_reg_operand" "=r,r,r")
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e606269cfa8..35fd93a18fc 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2020-02-27 Michael Meissner <meissner@linux.ibm.com>
+
+ PR target/93932
+ * gcc.target/powerpc/fold-vec-extract-longlong.p8.c: Adjust
+ instruction counts.
+
2020-02-27 Martin Jambor <mjambor@suse.cz>
Feng Xue <fxue@os.amperecomputing.com>
diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-extract-longlong.p8.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-extract-longlong.p8.c
index 2784d80dabe..56746989f74 100644
--- a/gcc/testsuite/gcc.target/powerpc/fold-vec-extract-longlong.p8.c
+++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-extract-longlong.p8.c
@@ -7,24 +7,23 @@
// Targeting P8LE and P8BE, six tests total.
// P8 (LE) constants: mfvsrd
-// P8 (LE) variables: addi,xxpermdi,mr,stxvd2x|stxvd4x,rldicl,sldi,ldx,blr
-// P8 (BE) constants: mfvsrd
-// P8 (BE) Variables: addi,xxpermdi,rldicl,mr,stxvd2x|stxvd4x,sldi,ldx,blr
+// P8 (LE) variables: xori, rldic, mtvsrd, xxpermdi, vslo, mfvsrd
+// P8 (BE) constants: xxpermdi, mfvsrd
+// P8 (BE) Variables: rldic, mtvsrd, xxpermdi, vslo, mfvsrd
-/* { dg-final { scan-assembler-times {\maddi\M} 6 { target ilp32 } } } */
-/* { dg-final { scan-assembler-times {\maddi\M} 3 { target lp64 } } } */
+/* results. */
+/* { dg-final { scan-assembler-times {\mxori\M} 3 { target le } } } */
+/* { dg-final { scan-assembler-times {\mrldic\M|\mrlwinm\M} 3 } } */
+/* { dg-final { scan-assembler-times {\mstxvd2x\M|\mstxvw4x\M} 4 { target ilp32 } } } */
/* { dg-final { scan-assembler-times {\madd\M} 3 { target ilp32 } } } */
/* { dg-final { scan-assembler-times {\mlwz\M} 11 { target ilp32 } } } */
+/* { dg-final { scan-assembler-times {\maddi\M} 6 { target ilp32 } } } */
+/* { dg-final { scan-assembler-times {\mmfvsrd\M} 6 { target lp64 } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 3 { target lp64 } } } */
/* { dg-final { scan-assembler-times {\mxxpermdi\M} 3 { target le } } } */
+/* { dg-final { scan-assembler-times {\mxxpermdi\M} 6 { target { be && lp64 } } } } */
/* { dg-final { scan-assembler-times {\mxxpermdi\M} 2 { target { be && ilp32 } } } } */
-/* { dg-final { scan-assembler-times {\mxxpermdi\M} 3 { target { be && lp64 } } } } */
-/* { dg-final { scan-assembler-times {\mstxvd2x\M|\mstxvw4x\M} 3 { target lp64 } } } */
-/* { dg-final { scan-assembler-times {\mstxvd2x\M|\mstxvw4x\M} 4 { target ilp32 } } } */
-/* { dg-final { scan-assembler-times {\mrldicl\M|\mrldic\M|\mrlwinm\M} 3 } } */
-/* { dg-final { scan-assembler-times {\mmfvsrd\M} 3 { target { lp64 } } } } */
-/* { dg-final { scan-assembler-times {\mmfvsrd\M} 0 { target { be && ilp32 } } } } */
-/* { dg-final { scan-assembler-times {\mmtvsrd\M} 0 { target { lp64 } } } } */
-/* { dg-final { scan-assembler-times {\mmtvsrd\M} 0 { target { be && ilp32 } } } } */
+/* { dg-final { scan-assembler-times {\mvslo\M} 3 { target lp64 } } } */
#include <altivec.h>
More information about the Gcc-cvs
mailing list