This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Small multiplier support in Cortex-M0/1/+


Hi,

Some configurations of the Cortex-M0 and Cortex-M1 come with a high latency
multiplier. This patch adds support for such configurations.

Small multiplier means using add/sub/shift instructions to replace the mul
instruction for the MCU that has no fast multiplier.

The following strategies are adopted in this patch:
1. Define new CPUs as
-mcpu=cortex-m0.small-multiply,cortex-m0plus.small-multiply,cortex-m1.small-
multiply to support small multiplier.
2. -Os means size is preferred. A threshold of 5 is set which means it will
prevent spliting if ending up with more than 5 instructions. As for non-OS,
there will be no such a limit.

Some test cases are also added in the testsuite to verify this function.

Is it ok for trunk?

Thanks and Best Regards,
Hale Wang

gcc/ChangeLog:

2014-08-29  Hale Wang  <Hale.Wang@arm.com>

	* config/arm/arm-cores.def: Add support for
	-mcpu=cortex-m0.small-multiply,cortex-m0plus.small-multiply,
	cortex-m1.small-multiply.
	* config/arm/arm-tables.opt: Regenerate.
	* config/arm/arm-tune.md: Regenerate.
	* config/arm/arm.c: Update the rtx-costs for MUL.
	* config/arm/bpabi.h: Handle
	-mcpu=cortex-m0.small-multiply,cortex-m0plus.small-multiply,
	cortex-m1.small-multiply.
	* doc/invoke.texi: Document
	-mcpu=cortex-m0.small-multiply,cortex-m0plus.small-multiply,
	cortex-m1.small-multiply.
	* testsuite/gcc.target/arm/small-multiply-m0-1.c: New test case.
	* testsuite/gcc.target/arm/small-multiply-m0-2.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m0-3.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m0plus-1.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m0plus-2.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m0plus-3.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m1-1.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m1-2.c: Likewise.
	* testsuite/gcc.target/arm/small-multiply-m1-3.c: Likewise.

===================================================================
diff --git a/gcc/config/arm/arm-cores.def b/gcc/config/arm/arm-cores.def
index a830a83..af4b373 100644
--- a/gcc/config/arm/arm-cores.def
+++ b/gcc/config/arm/arm-cores.def
@@ -137,6 +137,11 @@ ARM_CORE("cortex-m1",		cortexm1, cortexm1,
6M, FL_LDSCHED, v6m)
 ARM_CORE("cortex-m0",		cortexm0, cortexm0,		6M,
FL_LDSCHED, v6m)
 ARM_CORE("cortex-m0plus",	cortexm0plus, cortexm0plus,	6M,
FL_LDSCHED, v6m)
 
+/* V6M Architecture Processors for small-multiply implementations.  */
+ARM_CORE("cortex-m1.small-multiply",	cortexm1smallmultiply, cortexm1,
6M, FL_LDSCHED | FL_SMALLMUL, v6m)
+ARM_CORE("cortex-m0.small-multiply",	cortexm0smallmultiply, cortexm0,
6M, FL_LDSCHED | FL_SMALLMUL, v6m)
+ARM_CORE("cortex-m0plus.small-multiply",cortexm0plussmallmultiply,
cortexm0plus,6M, FL_LDSCHED | FL_SMALLMUL, v6m)
+
 /* V7 Architecture Processors */
 ARM_CORE("generic-armv7-a",	genericv7a, genericv7a,		7A,
FL_LDSCHED, cortex)
 ARM_CORE("cortex-a5",		cortexa5, cortexa5,		7A,
FL_LDSCHED, cortex_a5)
diff --git a/gcc/config/arm/arm-tables.opt b/gcc/config/arm/arm-tables.opt
index bc046a0..bd65bd2 100644
--- a/gcc/config/arm/arm-tables.opt
+++ b/gcc/config/arm/arm-tables.opt
@@ -241,6 +241,15 @@ EnumValue
 Enum(processor_type) String(cortex-m0plus) Value(cortexm0plus)
 
 EnumValue
+Enum(processor_type) String(cortex-m1.small-multiply)
Value(cortexm1smallmultiply)
+
+EnumValue
+Enum(processor_type) String(cortex-m0.small-multiply)
Value(cortexm0smallmultiply)
+
+EnumValue
+Enum(processor_type) String(cortex-m0plus.small-multiply)
Value(cortexm0plussmallmultiply)
+
+EnumValue
 Enum(processor_type) String(generic-armv7-a) Value(genericv7a)
 
 EnumValue
diff --git a/gcc/config/arm/arm-tune.md b/gcc/config/arm/arm-tune.md
index 954cab8..8b5c778 100644
--- a/gcc/config/arm/arm-tune.md
+++ b/gcc/config/arm/arm-tune.md
@@ -25,6 +25,7 @@
 	arm1176jzs,arm1176jzfs,mpcorenovfp,
 	mpcore,arm1156t2s,arm1156t2fs,
 	cortexm1,cortexm0,cortexm0plus,
+
cortexm1smallmultiply,cortexm0smallmultiply,cortexm0plussmallmultiply,
 	genericv7a,cortexa5,cortexa7,
 	cortexa8,cortexa9,cortexa12,
 	cortexa15,cortexr4,cortexr4f,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 93b989d..5062c85 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -751,6 +751,8 @@ static int thumb_call_reg_needed;
 #define FL_ARCH8      (1 << 24)       /* Architecture 8.  */
 #define FL_CRC32      (1 << 25)	      /* ARMv8 CRC32 instructions.
*/
 
+#define FL_SMALLMUL   (1 << 26)       /* Small multiply supported.  */
+
 #define FL_IWMMXT     (1 << 29)	      /* XScale v2 or "Intel
Wireless MMX technology".  */
 #define FL_IWMMXT2    (1 << 30)       /* "Intel Wireless MMX2 technology".
*/
 
@@ -914,6 +916,9 @@ int arm_condexec_masklen = 0;
 /* Nonzero if chip supports the ARMv8 CRC instructions.  */
 int arm_arch_crc = 0;
 
+/* Nonzero if the core has a very small, high-latency, multiply unit.  */
+int arm_m_profile_small_mul = 0;
+
 /* The condition codes of the ARM, and the inverse function.  */
 static const char * const arm_condition_codes[] =
 {
@@ -2784,6 +2789,7 @@ arm_option_override (void)
   arm_arch_arm_hwdiv = (insn_flags & FL_ARM_DIV) != 0;
   arm_tune_cortex_a9 = (arm_tune == cortexa9) != 0;
   arm_arch_crc = (insn_flags & FL_CRC32) != 0;
+  arm_m_profile_small_mul = (insn_flags & FL_SMALLMUL) != 0;
   if (arm_restrict_it == 2)
     arm_restrict_it = arm_arch8 && TARGET_THUMB2;
 
@@ -8920,7 +8926,13 @@ thumb1_size_rtx_costs (rtx x, enum rtx_code code,
enum rtx_code outer)
           /* Thumb1 mul instruction can't operate on const. We must Load it
              into a register first.  */
           int const_size = thumb1_size_rtx_costs (XEXP (x, 1), CONST_INT,
SET);
-          return COSTS_N_INSNS (1) + const_size;
+	  /* For the targets which have a very small and high-latency
multiply
+	     unit, we prefer to synthesize the mult with up to 5
instructions,
+	     giving a good balance between size and performance.  */
+	  if (arm_arch6m && arm_m_profile_small_mul)
+	    return COSTS_N_INSNS (5);
+	  else
+	    return COSTS_N_INSNS (1) + const_size;
         }
       return COSTS_N_INSNS (1);
 
@@ -11338,7 +11350,11 @@ arm_9e_rtx_costs (rtx x, enum rtx_code code, enum
rtx_code outer_code,
       switch (code)
 	{
 	case MULT:
-	  *total = COSTS_N_INSNS (3);
+	  /* Small multiply: 32 cycles for an integer multiply inst.  */
+	  if (arm_arch6m && arm_m_profile_small_mul)
+	    *total = COSTS_N_INSNS (32);
+	  else
+	    *total = COSTS_N_INSNS (3);
 	  return true;
 
 	default:
diff --git a/gcc/config/arm/bpabi.h b/gcc/config/arm/bpabi.h
index 7a576ac..06b9805 100644
--- a/gcc/config/arm/bpabi.h
+++ b/gcc/config/arm/bpabi.h
@@ -70,6 +70,9 @@
    |mcpu=cortex-a53					\
    |mcpu=cortex-a57					\
    |mcpu=cortex-a57.cortex-a53				\
+   |mcpu=cortex-m1.small-multiply                       \
+   |mcpu=cortex-m0.small-multiply                       \
+   |mcpu=cortex-m0plus.small-multiply			\
    |mcpu=generic-armv7-a                                \
    |march=armv7ve	                                \
    |march=armv7-m|mcpu=cortex-m3                        \
@@ -87,6 +90,9 @@
    |mcpu=cortex-a53					\
    |mcpu=cortex-a57					\
    |mcpu=cortex-a57.cortex-a53				\
+   |mcpu=cortex-m1.small-multiply                       \
+   |mcpu=cortex-m0.small-multiply                       \
+   |mcpu=cortex-m0plus.small-multiply                   \
    |mcpu=marvell-pj4					\
    |mcpu=generic-armv7-a                                \
    |march=armv7ve	                                \
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index eae4ab1..5dc8f26 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -12632,6 +12632,9 @@ Permissible names are: @samp{arm2}, @samp{arm250},
 @samp{cortex-m1},
 @samp{cortex-m0},
 @samp{cortex-m0plus},
+@samp{cortex-m1.small-multiply},
+@samp{cortex-m0.small-multiply},
+@samp{cortex-m0plus.small-multiply},
 @samp{marvell-pj4},
 @samp{xscale}, @samp{iwmmxt}, @samp{iwmmxt2}, @samp{ep9312},
 @samp{fa526}, @samp{fa626},
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m0-1.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m0-1.c
new file mode 100644
index 0000000..77ec603
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m0-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m0.small-multiply" { arm*-*-* }
{ "-mcpu=*" } { "-mcpu=cortex-m0.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m0.small-multiply -mthumb -O2" } */
+
+int
+test (int a)
+{
+  return a * 0x123456;
+}
+
+/* { dg-final { scan-assembler-not "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m0-2.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m0-2.c
new file mode 100644
index 0000000..c89b3ba
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m0-2.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m0.small-multiply" { arm*-*-* }
{ "-mcpu=*" } { "-mcpu=cortex-m0.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m0.small-multiply -mthumb -Os" } */
+
+int
+test (int a)
+{
+  return a * 0x123456;
+}
+
+/* { dg-final { scan-assembler "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m0-3.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m0-3.c
new file mode 100644
index 0000000..b2df109
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m0-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m0.small-multiply" { arm*-*-* }
{ "-mcpu=*" } { "-mcpu=cortex-m0.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m0.small-multiply -mthumb -Os" } */
+
+int
+test (int a)
+{
+  return a * 0x13;
+}
+
+/* { dg-final { scan-assembler-not "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-1.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-1.c
new file mode 100644
index 0000000..08a450b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m0plus.small-multiply" {
arm*-*-* } { "-mcpu=*" } { "-mcpu=cortex-m0plus.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m0plus.small-multiply -mthumb -O2" } */
+
+int
+test (int a)
+{
+  return a * 0x123456;
+}
+
+/* { dg-final { scan-assembler-not "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-2.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-2.c
new file mode 100644
index 0000000..17b52d3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-2.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m0plus.small-multiply" {
arm*-*-* } { "-mcpu=*" } { "-mcpu=cortex-m0plus.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m0plus.small-multiply -mthumb -Os" } */
+
+int
+test (int a)
+{
+  return a * 0x123456;
+}
+
+/* { dg-final { scan-assembler "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-3.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-3.c
new file mode 100644
index 0000000..af69c75
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m0plus-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m0plus.small-multiply" {
arm*-*-* } { "-mcpu=*" } { "-mcpu=cortex-m0plus.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m0plus.small-multiply -mthumb -Os" } */
+
+int
+test (int a)
+{
+  return a * 0x13;
+}
+
+/* { dg-final { scan-assembler-not "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m1-1.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m1-1.c
new file mode 100644
index 0000000..d265aaf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m1-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m1.small-multiply" { arm*-*-* }
{ "-mcpu=*" } { "-mcpu=cortex-m1.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m1.small-multiply -mthumb -O2" } */
+
+int
+test (int a)
+{
+  return a * 0x123456;
+}
+
+/* { dg-final { scan-assembler-not "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m1-2.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m1-2.c
new file mode 100644
index 0000000..c50891c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m1-2.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m1.small-multiply" { arm*-*-* }
{ "-mcpu=*" } { "-mcpu=cortex-m1.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m1.small-multiply -mthumb -Os" } */
+
+int
+test (int a)
+{
+  return a * 0x123456;
+}
+
+/* { dg-final { scan-assembler "\[\\t \]+mul" } } */
diff --git a/gcc/testsuite/gcc.target/arm/small-multiply-m1-3.c
b/gcc/testsuite/gcc.target/arm/small-multiply-m1-3.c
new file mode 100644
index 0000000..1da21a6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/small-multiply-m1-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target arm_thumb1_ok } */
+/* { dg-skip-if "Test is specific to cortex-m1.small-multiply" { arm*-*-* }
{ "-mcpu=*" } { "-mcpu=cortex-m1.small-multiply" } } */
+/* { dg-options "-mcpu=cortex-m1.small-multiply -mthumb -Os" } */
+
+int
+test (int a)
+{
+  return a * 0x13;
+}
+
+/* { dg-final { scan-assembler-not "\[\\t \]+mul" } } */

Attachment: small-multiply-8.patch
Description: Binary data


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]