Hi,
As mentioned in PR108338, on p9, we could use mtvsrws to implement
the conversion from SI#0 to SF (or lowpart DI to SF). And we find
we can also enhance the conversion from highpart DI to SF (as the
case in this patch).
This patch enhances these conversions accordingly.
Bootstrap and regtests pass on ppc64{,le}.
Is this ok for trunk?
BR,
Jeff (Jiufu)
PR target/108338
gcc/ChangeLog:
* config/rs6000/rs6000.md (any_rshift): New code_iterator.
(movsf_from_si2): Rename to...
(movsf_from_si2_<any_rshift:code>): ... this.
(p9_mtvsrws): New define_insn.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/pr108338.c: New test.
---
gcc/config/rs6000/rs6000.md | 32 +++++++++++++---
gcc/testsuite/gcc.target/powerpc/pr108338.c | 41 +++++++++++++++++++++
2 files changed, 67 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/powerpc/pr108338.c
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 3cae64a264a..9025a912141 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -158,6 +158,7 @@ (define_c_enum "unspec"
UNSPEC_HASHCHK
UNSPEC_XXSPLTIDP_CONST
UNSPEC_XXSPLTIW_CONST
+ UNSPEC_P9V_MTVSRWS
])
;;
@@ -8203,10 +8204,19 @@ (define_insn_and_split "movsf_from_si"
rtx op2 = operands[2];
rtx op1_di = gen_rtx_REG (DImode, REGNO (op1));
- /* Move SF value to upper 32-bits for xscvspdpn. */
- emit_insn (gen_ashldi3 (op2, op1_di, GEN_INT (32)));
- emit_insn (gen_p8_mtvsrd_sf (op0, op2));
- emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+ if (TARGET_P9_VECTOR && TARGET_POWERPC64 && TARGET_DIRECT_MOVE)
+ {
+ emit_insn (gen_p9_mtvsrws (op0, op1_di));
+ emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+ }
+ else
+ {
+ /* Move SF value to upper 32-bits for xscvspdpn. */
+ emit_insn (gen_ashldi3 (op2, op1_di, GEN_INT (32)));
+ emit_insn (gen_p8_mtvsrd_sf (op0, op2));
+ emit_insn (gen_vsx_xscvspdpn_directmove (op0, op0));
+ }
+
DONE;
}
[(set_attr "length"
@@ -8219,15 +8229,17 @@ (define_insn_and_split "movsf_from_si"
"*, *, p9v, p8v, *, *,
p8v, p8v, p8v, *")])
+(define_code_iterator any_rshift [ashiftrt lshiftrt])
+
;; For extracting high part element from DImode register like:
;; {%1:SF=unspec[r122:DI>>0x20#0] 86;clobber scratch;}
;; split it before reload with "and mask" to avoid generating shift right
;; 32 bit then shift left 32 bit.
-(define_insn_and_split "movsf_from_si2"
+(define_insn_and_split "movsf_from_si2_<any_rshift:code>"
[(set (match_operand:SF 0 "gpc_reg_operand" "=wa")
(unspec:SF
[(subreg:SI
- (ashiftrt:DI
+ (any_rshift:DI
(match_operand:DI 1 "input_operand" "r")
(const_int 32))
0)]
@@ -9475,6 +9487,14 @@ (define_insn "p8_mtvsrd_sf"
"mtvsrd %x0,%1"
[(set_attr "type" "mtvsr")])
+(define_insn "p9_mtvsrws"
+ [(set (match_operand:SF 0 "register_operand" "=wa")
+ (unspec:SF [(match_operand:DI 1 "register_operand" "r")]
+ UNSPEC_P9V_MTVSRWS))]
+ "TARGET_P9_VECTOR && TARGET_POWERPC64 && TARGET_DIRECT_MOVE"
+ "mtvsrws %x0,%1"
+ [(set_attr "type" "mtvsr")])
+
(define_insn_and_split "reload_vsx_from_gprsf"
[(set (match_operand:SF 0 "register_operand" "=wa")
(unspec:SF [(match_operand:SF 1 "register_operand" "r")]
diff --git a/gcc/testsuite/gcc.target/powerpc/pr108338.c
b/gcc/testsuite/gcc.target/powerpc/pr108338.c
new file mode 100644
index 00000000000..2afac79ea4f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr108338.c
@@ -0,0 +1,41 @@
+// { dg-do run }
+// { dg-options "-O2 -save-temps" }
+
+float __attribute__ ((noipa)) sf_from_di_off0 (long long l)
+{
+ char buff[16];
+ *(long long*)buff = l;
+ float f = *(float*)(buff);
+ return f;
+}
+
+float __attribute__ ((noipa)) sf_from_di_off4 (long long l)
+{
+ char buff[16];
+ *(long long*)buff = l;
+ float f = *(float*)(buff + 4);
+ return f;
+}
+
+/* { dg-final { scan-assembler-times {\mmtvsrws\M} 1 { target { has_arch_ppc64
&& has_arch_pwr9 } } } } */
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 1 { target { has_arch_ppc64
&& has_arch_pwr9 } } } } */
+/* { dg-final { scan-assembler-times {\mrldicr\M} 1 { target { has_arch_ppc64
&& has_arch_pwr9 } } } } */
+/* { dg-final { scan-assembler-times {\mxscvspdpn\M} 2 { target {
has_arch_pwr8 && has_arch_ppc64 } } } } */
+
+/* { dg-final { scan-assembler-times {\mmtvsrd\M} 2 { target { has_arch_pwr8
&& { has_arch_ppc64 && { ! has_arch_pwr9 } } } } } } */
+
+union di_sf_sf
+{
+ struct {float f1; float f2;};
+ long long l;
+};
+
+int main()
+{
+ union di_sf_sf v;
+ v.f1 = 1.0f;
+ v.f2 = 2.0f;
+ if (sf_from_di_off0 (v.l) != 1.0f || sf_from_di_off4 (v.l) != 2.0f )
+ __builtin_abort ();
+ return 0;
+}
--
2.17.1
