Increase move cost between mask and gpr.

kmovd only uses port5 which is often the bottleneck of
performance. Also from latency perspective, spill and reload mostly
could be STLF or even MRN which only take 1 cycle.

So the patch increase move cost between gpr and mask to be the same as
gpr <-> sse register.

gcc/ChangeLog:

	* config/i386/x86-tune-costs.h (skylake_cost): Increase gpr
	<-> mask cost from 5 to 6.
	(icelake_cost): Ditto.

gcc/testsuite/ChangeLog:
	* gcc.target/i386/spill_to_mask-1.c: New test.

diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
index 017ffa699585b2c4e93784fc83c4e0f489a29424..05cbd49ec870a39fd5a989e4c0bbfc5acd38dbb1 100644 (file)
--- a/gcc/config/i386/x86-tune-costs.h
+++ b/gcc/config/i386/x86-tune-costs.h
@@ -1866,7 +1866,7 @@ struct processor_costs skylake_cost = {
   {8, 8, 8, 12, 24},                   /* cost of storing SSE registers
                                           in 32,64,128,256 and 512-bit */
   6, 6,                                /* SSE->integer and integer->SSE moves */
-  5, 5,                                /* mask->integer and integer->mask moves */
+  6, 6,                                /* mask->integer and integer->mask moves */
   {8, 8, 8},                           /* cost of loading mask register
                                           in QImode, HImode, SImode.  */
   {6, 6, 6},                           /* cost if storing mask register
@@ -1992,7 +1992,7 @@ struct processor_costs icelake_cost = {
   {8, 8, 8, 12, 24},                   /* cost of storing SSE registers
                                           in 32,64,128,256 and 512-bit */
   6, 6,                                /* SSE->integer and integer->SSE moves */
-  5, 5,                                /* mask->integer and integer->mask moves */
+  6, 6,                                /* mask->integer and integer->mask moves */
   {8, 8, 8},                           /* cost of loading mask register
                                           in QImode, HImode, SImode.  */
   {6, 6, 6},                           /* cost if storing mask register

diff --git a/gcc/testsuite/gcc.target/i386/spill_to_mask-1.c b/gcc/testsuite/gcc.target/i386/spill_to_mask-1.c
index 94d6764fc56f5f3c161563257debb96e9916554d..be19239a685a0c3086ff6c03fab66d7321153950 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/spill_to_mask-1.c
+++ b/gcc/testsuite/gcc.target/i386/spill_to_mask-1.c
@@ -120,7 +120,7 @@ void foo (DTYPE in[16], DTYPE out[8], const DTYPE C[16])
     out[7] += h;
 }
 
-/* { dg-final { scan-assembler "kmovd" } } */
+/* { dg-final { scan-assembler "kmovd" { xfail *-*-* } } } */
 /* { dg-final { scan-assembler-not "knot" } } */
 /* { dg-final { scan-assembler-not "kxor" } } */
 /* { dg-final { scan-assembler-not "kor" } } */