diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index c91e3809c75ed2ddac812cdacb15888f182be86b..383b68a9bb8a1186f396a5a913aa3f80216b33a4 100644
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -1004,8 +1004,8 @@ BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_roundps_sfix, "__builtin_ia32_
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_roundv4sf2, "__builtin_ia32_roundps_az", IX86_BUILTIN_ROUNDPS_AZ, UNKNOWN, (int) V4SF_FTYPE_V4SF)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_roundv4sf2_sfix, "__builtin_ia32_roundps_az_sfix", IX86_BUILTIN_ROUNDPS_AZ_SFIX, UNKNOWN, (int) V4SI_FTYPE_V4SF)
-BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_ptestv2di, "__builtin_ia32_ptestz128", IX86_BUILTIN_PTESTZ, EQ, (int) INT_FTYPE_V2DI_V2DI_PTEST)
-BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_ptestv2di, "__builtin_ia32_ptestc128", IX86_BUILTIN_PTESTC, LTU, (int) INT_FTYPE_V2DI_V2DI_PTEST)
+BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_ptestzv2di, "__builtin_ia32_ptestz128", IX86_BUILTIN_PTESTZ, EQ, (int) INT_FTYPE_V2DI_V2DI_PTEST)
+BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_ptestcv2di, "__builtin_ia32_ptestc128", IX86_BUILTIN_PTESTC, LTU, (int) INT_FTYPE_V2DI_V2DI_PTEST)
BDESC (OPTION_MASK_ISA_SSE4_1, 0, CODE_FOR_sse4_1_ptestv2di, "__builtin_ia32_ptestnzc128", IX86_BUILTIN_PTESTNZC, GTU, (int) INT_FTYPE_V2DI_V2DI_PTEST)
/* SSE4.2 */
@@ -1164,8 +1164,8 @@ BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_vtestpd256, "__builtin_ia32_vtestnzc
BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_vtestps256, "__builtin_ia32_vtestzps256", IX86_BUILTIN_VTESTZPS256, EQ, (int) INT_FTYPE_V8SF_V8SF_PTEST)
BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_vtestps256, "__builtin_ia32_vtestcps256", IX86_BUILTIN_VTESTCPS256, LTU, (int) INT_FTYPE_V8SF_V8SF_PTEST)
BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_vtestps256, "__builtin_ia32_vtestnzcps256", IX86_BUILTIN_VTESTNZCPS256, GTU, (int) INT_FTYPE_V8SF_V8SF_PTEST)
-BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_ptestv4di, "__builtin_ia32_ptestz256", IX86_BUILTIN_PTESTZ256, EQ, (int) INT_FTYPE_V4DI_V4DI_PTEST)
-BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_ptestv4di, "__builtin_ia32_ptestc256", IX86_BUILTIN_PTESTC256, LTU, (int) INT_FTYPE_V4DI_V4DI_PTEST)
+BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_ptestzv4di, "__builtin_ia32_ptestz256", IX86_BUILTIN_PTESTZ256, EQ, (int) INT_FTYPE_V4DI_V4DI_PTEST)
+BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_ptestcv4di, "__builtin_ia32_ptestc256", IX86_BUILTIN_PTESTC256, LTU, (int) INT_FTYPE_V4DI_V4DI_PTEST)
BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_ptestv4di, "__builtin_ia32_ptestnzc256", IX86_BUILTIN_PTESTNZC256, GTU, (int) INT_FTYPE_V4DI_V4DI_PTEST)
BDESC (OPTION_MASK_ISA_AVX, 0, CODE_FOR_avx_movmskpd256, "__builtin_ia32_movmskpd256", IX86_BUILTIN_MOVMSKPD256, UNKNOWN, (int) INT_FTYPE_V4DF )
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index 70c6971ac03f8525192f2f8b630ea3815c8f871a..ac674418b9600d36304cf9412eab24b562ba8707 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -2370,8 +2370,8 @@ ix86_expand_branch (enum rtx_code code, rtx op0, rtx op1, rtx label)
tmp = gen_reg_rtx (mode);
emit_insn (gen_rtx_SET (tmp, gen_rtx_XOR (mode, op0, op1)));
tmp = gen_lowpart (p_mode, tmp);
- emit_insn (gen_rtx_SET (gen_rtx_REG (CCmode, FLAGS_REG),
- gen_rtx_UNSPEC (CCmode,
+ emit_insn (gen_rtx_SET (gen_rtx_REG (CCZmode, FLAGS_REG),
+ gen_rtx_UNSPEC (CCZmode,
gen_rtvec (2, tmp, tmp),
UNSPEC_PTEST)));
tmp = gen_rtx_fmt_ee (code, VOIDmode, flag, const0_rtx);
diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
index a0a73486d369cd17c0b16ddb72ad0bc963d15f9b..3417f6bd0d13077576b301c3c0f09bfc0946abde 100644
--- a/gcc/config/i386/i386-features.cc
+++ b/gcc/config/i386/i386-features.cc
@@ -974,7 +974,7 @@ general_scalar_chain::convert_op (rtx *op, rtx_insn *insn)
}
}
-/* Convert COMPARE to vector mode. */
+/* Convert CCZmode COMPARE to vector mode. */
rtx
scalar_chain::convert_compare (rtx op1, rtx op2, rtx_insn *insn)
@@ -1023,7 +1023,7 @@ scalar_chain::convert_compare (rtx op1, rtx op2, rtx_insn *insn)
emit_insn_before (gen_rtx_SET (tmp, op11), insn);
op11 = tmp;
}
- return gen_rtx_UNSPEC (CCmode, gen_rtvec (2, op11, op12),
+ return gen_rtx_UNSPEC (CCZmode, gen_rtvec (2, op11, op12),
UNSPEC_PTEST);
}
else
@@ -1052,7 +1052,7 @@ scalar_chain::convert_compare (rtx op1, rtx op2, rtx_insn *insn)
src = tmp;
}
- return gen_rtx_UNSPEC (CCmode, gen_rtvec (2, src, src), UNSPEC_PTEST);
+ return gen_rtx_UNSPEC (CCZmode, gen_rtvec (2, src, src), UNSPEC_PTEST);
}
/* Helper function for converting INSN to vector mode. */
@@ -1219,7 +1219,7 @@ general_scalar_chain::convert_insn (rtx_insn *insn)
break;
case COMPARE:
- dst = gen_rtx_REG (CCmode, FLAGS_REG);
+ dst = gen_rtx_REG (CCZmode, FLAGS_REG);
src = convert_compare (XEXP (src, 0), XEXP (src, 1), insn);
break;
@@ -1726,7 +1726,7 @@ timode_scalar_chain::convert_insn (rtx_insn *insn)
break;
case COMPARE:
- dst = gen_rtx_REG (CCmode, FLAGS_REG);
+ dst = gen_rtx_REG (CCZmode, FLAGS_REG);
src = convert_compare (XEXP (src, 0), XEXP (src, 1), insn);
break;
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index d0f5783173ee9f557bb406351ef8304089d1e6c7..af01299c1303228416264283bc30327e50d1a735 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -140,6 +140,7 @@ extern void ix86_expand_copysign (rtx []);
extern void ix86_expand_xorsign (rtx []);
extern bool ix86_unary_operator_ok (enum rtx_code, machine_mode, rtx[2]);
extern bool ix86_match_ccmode (rtx, machine_mode);
+extern bool ix86_match_ptest_ccmode (rtx);
extern void ix86_expand_branch (enum rtx_code, rtx, rtx, rtx);
extern void ix86_expand_setcc (rtx, enum rtx_code, rtx, rtx);
extern bool ix86_expand_int_movcc (rtx[]);
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index e548d6588289ba01cd00adc4ee9ff61f75092ba7..d4ff56ee8dd81dfb8219c00ada60cc9529841ad2 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -15987,6 +15987,29 @@ ix86_cc_mode (enum rtx_code code, rtx op0, rtx op1)
}
}
+/* Return TRUE or FALSE depending on whether the ptest instruction
+ INSN has source and destination with suitable matching CC modes. */
+
+bool
+ix86_match_ptest_ccmode (rtx insn)
+{
+ rtx set, src;
+ machine_mode set_mode;
+
+ set = PATTERN (insn);
+ gcc_assert (GET_CODE (set) == SET);
+ src = SET_SRC (set);
+ gcc_assert (GET_CODE (src) == UNSPEC
+ && XINT (src, 1) == UNSPEC_PTEST);
+
+ set_mode = GET_MODE (src);
+ if (set_mode != CCZmode
+ && set_mode != CCCmode
+ && set_mode != CCmode)
+ return false;
+ return GET_MODE (SET_DEST (set)) == set_mode;
+}
+
/* Return the fixed registers used for condition codes. */
static bool
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index a92f50e96b592232056d582bfbbacd97fa8e7036..9bec09d354aaa3cd49c14b8d2f290fe84d17e412 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -20423,10 +20423,10 @@
UNSPEC_MOVMSK)
(match_operand 2 "const_int_operand")))]
"TARGET_SSE4_1 && (INTVAL (operands[2]) == (int) (<vi1avx2const>))"
- [(set (reg:CC FLAGS_REG)
- (unspec:CC [(match_dup 0)
- (match_dup 0)]
- UNSPEC_PTEST))])
+ [(set (reg:CCZ FLAGS_REG)
+ (unspec:CCZ [(match_dup 0)
+ (match_dup 0)]
+ UNSPEC_PTEST))])
(define_expand "sse2_maskmovdqu"
[(set (match_operand:V16QI 0 "memory_operand")
@@ -23078,13 +23078,13 @@
(set_attr "mode" "<MODE>")])
;; ptest is very similar to comiss and ucomiss when setting FLAGS_REG.
-;; But it is not a really compare instruction.
-(define_insn "<sse4_1>_ptest<mode>"
- [(set (reg:CC FLAGS_REG)
- (unspec:CC [(match_operand:V_AVX 0 "register_operand" "Yr, *x, x")
- (match_operand:V_AVX 1 "vector_operand" "YrBm, *xBm, xm")]
- UNSPEC_PTEST))]
- "TARGET_SSE4_1"
+;; But it is not really a compare instruction.
+(define_insn "*<sse4_1>_ptest<mode>"
+ [(set (reg FLAGS_REG)
+ (unspec [(match_operand:V_AVX 0 "register_operand" "Yr, *x, x")
+ (match_operand:V_AVX 1 "vector_operand" "YrBm, *xBm, xm")]
+ UNSPEC_PTEST))]
+ "TARGET_SSE4_1 && ix86_match_ptest_ccmode (insn)"
"%vptest\t{%1, %0|%0, %1}"
[(set_attr "isa" "noavx,noavx,avx")
(set_attr "type" "ssecomi")
@@ -23097,6 +23097,30 @@
(const_string "*")))
(set_attr "mode" "<sseinsnmode>")])
+;; Expand a ptest to set the Z flag.
+(define_expand "<sse4_1>_ptestz<mode>"
+ [(set (reg:CCZ FLAGS_REG)
+ (unspec:CCZ [(match_operand:V_AVX 0 "register_operand")
+ (match_operand:V_AVX 1 "vector_operand")]
+ UNSPEC_PTEST))]
+ "TARGET_SSE4_1")
+
+;; Expand a ptest to set the C flag
+(define_expand "<sse4_1>_ptestc<mode>"
+ [(set (reg:CCC FLAGS_REG)
+ (unspec:CCC [(match_operand:V_AVX 0 "register_operand")
+ (match_operand:V_AVX 1 "vector_operand")]
+ UNSPEC_PTEST))]
+ "TARGET_SSE4_1")
+
+;; Expand a ptest to set both the Z and C flags
+(define_expand "<sse4_1>_ptest<mode>"
+ [(set (reg:CC FLAGS_REG)
+ (unspec:CC [(match_operand:V_AVX 0 "register_operand")
+ (match_operand:V_AVX 1 "vector_operand")]
+ UNSPEC_PTEST))]
+ "TARGET_SSE4_1")
+
(define_insn "ptesttf2"
[(set (reg:CC FLAGS_REG)
(unspec:CC [(match_operand:TF 0 "register_operand" "Yr, *x, x")
@@ -23111,17 +23135,17 @@
(set_attr "mode" "TI")])
(define_insn_and_split "*ptest<mode>_and"
- [(set (reg:CC FLAGS_REG)
- (unspec:CC [(and:V_AVX (match_operand:V_AVX 0 "register_operand")
- (match_operand:V_AVX 1 "vector_operand"))
- (and:V_AVX (match_dup 0) (match_dup 1))]
+ [(set (reg:CCZ FLAGS_REG)
+ (unspec:CCZ [(and:V_AVX (match_operand:V_AVX 0 "register_operand")
+ (match_operand:V_AVX 1 "vector_operand"))
+ (and:V_AVX (match_dup 0) (match_dup 1))]
UNSPEC_PTEST))]
"TARGET_SSE4_1
&& ix86_pre_reload_split ()"
"#"
"&& 1"
- [(set (reg:CC FLAGS_REG)
- (unspec:CC [(match_dup 0) (match_dup 1)] UNSPEC_PTEST))])
+ [(set (reg:CCZ FLAGS_REG)
+ (unspec:CCZ [(match_dup 0) (match_dup 1)] UNSPEC_PTEST))])
(define_expand "nearbyint<mode>2"
[(set (match_operand:VFH 0 "register_operand")
diff --git a/gcc/testsuite/gcc.target/i386/pr109973-1.c b/gcc/testsuite/gcc.target/i386/pr109973-1.c
new file mode 100644
index 0000000000000000000000000000000000000000..a1b6136bfeaa3581a8f7cb39b85c58f7e61de10a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr109973-1.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx2" } */
+
+typedef long long __m256i __attribute__ ((__vector_size__ (32)));
+
+int
+foo (__m256i x, __m256i y)
+{
+ __m256i a = x & y;
+ return __builtin_ia32_ptestc256 (a, a);
+}
+
+/* { dg-final { scan-assembler "vpand" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr109973-2.c b/gcc/testsuite/gcc.target/i386/pr109973-2.c
new file mode 100644
index 0000000000000000000000000000000000000000..167f6ee02e25f05515e9bd60697d9cda3e3c3576
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr109973-2.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -msse4.1" } */
+
+typedef long long __m128i __attribute__ ((__vector_size__ (16)));
+
+int
+foo (__m128i x, __m128i y)
+{
+ __m128i a = x & y;
+ return __builtin_ia32_ptestc128 (a, a);
+}
+
+/* { dg-final { scan-assembler "pand" } } */