On x86_64, V1TI mode holds a 128-bit integer value in a (vector) SSE
register (where regular TI mode uses a pair of 64-bit general purpose
scalar registers). This patch improves the implementation of AND, IOR,
XOR and NOT on these values.
The benefit is demonstrated by the following simple test program:
typedef unsigned __int128 v1ti __attribute__ ((__vector_size__ (16)));
v1ti and(v1ti x, v1ti y) { return x & y; }
v1ti ior(v1ti x, v1ti y) { return x | y; }
v1ti xor(v1ti x, v1ti y) { return x ^ y; }
v1ti not(v1ti x) { return ~x; }
For which GCC currently generates the rather large:
and: movdqa %xmm0, %xmm2
movq %xmm1, %rdx
movq %xmm0, %rax
andq %rdx, %rax
movhlps %xmm2, %xmm3
movhlps %xmm1, %xmm4
movq %rax, %xmm0
movq %xmm4, %rdx
movq %xmm3, %rax
andq %rdx, %rax
movq %rax, %xmm5
punpcklqdq %xmm5, %xmm0
ret
ior: movdqa %xmm0, %xmm2
movq %xmm1, %rdx
movq %xmm0, %rax
orq %rdx, %rax
movhlps %xmm2, %xmm3
movhlps %xmm1, %xmm4
movq %rax, %xmm0
movq %xmm4, %rdx
movq %xmm3, %rax
orq %rdx, %rax
movq %rax, %xmm5
punpcklqdq %xmm5, %xmm0
ret
xor: movdqa %xmm0, %xmm2
movq %xmm1, %rdx
movq %xmm0, %rax
xorq %rdx, %rax
movhlps %xmm2, %xmm3
movhlps %xmm1, %xmm4
movq %rax, %xmm0
movq %xmm4, %rdx
movq %xmm3, %rax
xorq %rdx, %rax
movq %rax, %xmm5
punpcklqdq %xmm5, %xmm0
ret
not: movdqa %xmm0, %xmm1
movq %xmm0, %rax
notq %rax
movhlps %xmm1, %xmm2
movq %rax, %xmm0
movq %xmm2, %rax
notq %rax
movq %rax, %xmm3
punpcklqdq %xmm3, %xmm0
ret
with this patch we now generate the much more efficient:
and: pand %xmm1, %xmm0
ret
ior: por %xmm1, %xmm0
ret
xor: pxor %xmm1, %xmm0
ret
not: pcmpeqd %xmm1, %xmm1
pxor %xmm1, %xmm0
ret
For my first few attempts at this patch I tried adding V1TI to the
existing VI and VI12_AVX_512F mode iterators, but these then have
dependencies on other iterators (and attributes), and so on until
everything ties itself into a knot, as V1TI mode isn't really a
first-class vector mode on x86_64. Hence I ultimately opted to use
simple stand-alone patterns (as used by the existing TF mode support).
2021-10-23 Roger Sayle <roger@nextmovesoftware.com>
gcc/ChangeLog
* config/i386/sse.md (<any_logic>v1ti3): New define_insn to
implement V1TImode AND, IOR and XOR on TARGET_SSE2 (and above).
(one_cmplv1ti2): New define expand.
gcc/testsuite/ChangeLog
* gcc.target/i386/sse2-v1ti-logic.c: New test case.
* gcc.target/i386/sse2-v1ti-logic-2.c: New test case.
]
(const_string "<sseinsnmode>")))])
+(define_insn "<code>v1ti3"
+ [(set (match_operand:V1TI 0 "register_operand" "=x,x,v")
+ (any_logic:V1TI
+ (match_operand:V1TI 1 "register_operand" "%0,x,v")
+ (match_operand:V1TI 2 "vector_operand" "xBm,xm,vm")))]
+ "TARGET_SSE2"
+ "@
+ p<logic>\t{%2, %0|%0, %2}
+ vp<logic>\t{%2, %1, %0|%0, %1, %2}
+ vp<logic>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "noavx,avx,avx")
+ (set_attr "prefix" "orig,vex,evex")
+ (set_attr "prefix_data16" "1,*,*")
+ (set_attr "type" "sselog")
+ (set_attr "mode" "TI")])
+
+(define_expand "one_cmplv1ti2"
+ [(set (match_operand:V1TI 0 "register_operand")
+ (xor:V1TI (match_operand:V1TI 1 "register_operand")
+ (match_dup 2)))]
+ "TARGET_SSE2"
+{
+ operands[2] = force_reg (V1TImode, CONSTM1_RTX (V1TImode));
+})
+
(define_mode_iterator AVX512ZEXTMASK
[(DI "TARGET_AVX512BW") (SI "TARGET_AVX512BW") HI])
--- /dev/null
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef unsigned __int128 v1ti __attribute__ ((__vector_size__ (16)));
+
+v1ti x;
+v1ti y;
+v1ti z;
+
+void and2()
+{
+ x &= y;
+}
+
+void and3()
+{
+ x = y & z;
+}
+
+void ior2()
+{
+ x |= y;
+}
+
+void ior3()
+{
+ x = y | z;
+}
+
+
+void xor2()
+{
+ x ^= y;
+}
+
+void xor3()
+{
+ x = y ^ z;
+}
+
+void not1()
+{
+ x = ~x;
+}
+
+void not2()
+{
+ x = ~y;
+}
+
+/* { dg-final { scan-assembler-times "pand" 2 } } */
+/* { dg-final { scan-assembler-times "por" 2 } } */
+/* { dg-final { scan-assembler-times "pxor" 4 } } */
--- /dev/null
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2 -msse2" } */
+
+typedef unsigned __int128 v1ti __attribute__ ((__vector_size__ (16)));
+
+v1ti and(v1ti x, v1ti y)
+{
+ return x & y;
+}
+
+v1ti ior(v1ti x, v1ti y)
+{
+ return x | y;
+}
+
+v1ti xor(v1ti x, v1ti y)
+{
+ return x ^ y;
+}
+
+v1ti not(v1ti x)
+{
+ return ~x;
+}
+
+/* { dg-final { scan-assembler "pand" } } */
+/* { dg-final { scan-assembler "por" } } */
+/* { dg-final { scan-assembler-times "pxor" 2 } } */