This is the mail archive of the
binutils@sourceware.org
mailing list for the binutils project.
[PATCH] MIPS/gas: Fix order of instructions in LI macro expansion
- From: Faraz Shahbazker <fshahbazker at wavecomp dot com>
- To: "binutils at sourceware dot org" <binutils at sourceware dot org>
- Cc: Faraz Shahbazker <fshahbazker at wavecomp dot com>, Chenghua Xu <paul dot hua dot gm at gmail dot com>
- Date: Wed, 19 Jun 2019 22:55:04 +0000
- Subject: [PATCH] MIPS/gas: Fix order of instructions in LI macro expansion
When MTHC1 instruction is paired with MTC1 to write a value to a
64-bit FPR, the MTC1 must be executed first, because the semantic
definition of MTC1 is not aware that software will be using an MTHC1
to complete the operation, and sets the upper half of the 64-bit FPR
to an UNPREDICTABLE value[1].
Fix the order of MTHC1 and MTC1 instructions in LI macro expansion.
Modify the expansions to exploit moves from $zero directly by-passing
the use of $AT, where ever possible.
[1] "MIPS Architecture for Programmers Volume II-A: The MIPS32
Instruction Set Manual", Wave Computing, Inc., Document
Number: MD00086, Revision 5.04, December 11, 2013, Section 3.2
"Alphabetical List of Instructions", pp. 217.
gas/
* config/tc-mips.c (macro) <M_LI>: Re-order MTHC1 with
respect to MTC1 and use $0 for either part where possible.
* testsuite/gas/mips/li-d.s: Add test cases for non-zero
words in double precision constants.
* testsuite/gas/mips/li-d.d: Update reference output.
* testsuite/gas/mips/micromips@isa-override-1.d: Likewise.
* testsuite/gas/mips/mips32r2@isa-override-1.d: Likewise.
* testsuite/gas/mips/mips64r2@isa-override-1.d: Likewise.
---
Notes:
https://s3-eu-west-1.amazonaws.com/downloads-mips/documents/MD00086-2B-MIPS32BIS-AFP-05.04.pdf
gas/config/tc-mips.c | 40 +++++++++++++-----
gas/testsuite/gas/mips/li-d.d | 51 +++++++++++++++++++----
gas/testsuite/gas/mips/li-d.s | 39 +++++++++++++++++
gas/testsuite/gas/mips/micromips@isa-override-1.d | 12 +++---
gas/testsuite/gas/mips/mips32r2@isa-override-1.d | 12 +++---
gas/testsuite/gas/mips/mips64r2@isa-override-1.d | 12 +++---
6 files changed, 129 insertions(+), 37 deletions(-)
diff --git a/gas/config/tc-mips.c b/gas/config/tc-mips.c
index 0f0ace5..671d74a 100644
--- a/gas/config/tc-mips.c
+++ b/gas/config/tc-mips.c
@@ -12780,20 +12780,28 @@ macro (struct mips_cl_insn *ip, char *str)
OFFSET_EXPR. */
if (imm_expr.X_op == O_constant)
{
- used_at = 1;
- load_register (AT, &imm_expr, FPR_SIZE == 64);
+ tempreg = ZERO;
+ if (((FPR_SIZE == 64 && GPR_SIZE == 64)
+ || !ISA_HAS_MXHC1 (mips_opts.isa))
+ && imm_expr.X_add_number != 0)
+ {
+ used_at = 1;
+ tempreg = AT;
+ load_register (AT, &imm_expr, FPR_SIZE == 64);
+ }
if (FPR_SIZE == 64 && GPR_SIZE == 64)
- macro_build (NULL, "dmtc1", "t,S", AT, op[0]);
+ macro_build (NULL, "dmtc1", "t,S", tempreg, op[0]);
else
{
- if (ISA_HAS_MXHC1 (mips_opts.isa))
- macro_build (NULL, "mthc1", "t,G", AT, op[0]);
- else if (FPR_SIZE != 32)
- as_bad (_("Unable to generate `%s' compliant code "
- "without mthc1"),
- (FPR_SIZE == 64) ? "fp64" : "fpxx");
- else
- macro_build (NULL, "mtc1", "t,G", AT, op[0] + 1);
+ if (!ISA_HAS_MXHC1 (mips_opts.isa))
+ {
+ if (FPR_SIZE != 32)
+ as_bad (_("Unable to generate `%s' compliant code "
+ "without mthc1"),
+ (FPR_SIZE == 64) ? "fp64" : "fpxx");
+ else
+ macro_build (NULL, "mtc1", "t,G", tempreg, op[0] + 1);
+ }
if (offset_expr.X_op == O_absent)
macro_build (NULL, "mtc1", "t,G", 0, op[0]);
else
@@ -12802,6 +12810,16 @@ macro (struct mips_cl_insn *ip, char *str)
load_register (AT, &offset_expr, 0);
macro_build (NULL, "mtc1", "t,G", AT, op[0]);
}
+ if (ISA_HAS_MXHC1 (mips_opts.isa))
+ {
+ if (imm_expr.X_add_number != 0)
+ {
+ used_at = 1;
+ tempreg = AT;
+ load_register (AT, &imm_expr, 0);
+ }
+ macro_build (NULL, "mthc1", "t,G", tempreg, op[0]);
+ }
}
break;
}
diff --git a/gas/testsuite/gas/mips/li-d.d b/gas/testsuite/gas/mips/li-d.d
index ca24570..9c569a1 100644
--- a/gas/testsuite/gas/mips/li-d.d
+++ b/gas/testsuite/gas/mips/li-d.d
@@ -10,22 +10,57 @@
Disassembly of section \.text:
[0-9a-f]+ <[^>]*> li v(0|1),0
[0-9a-f]+ <[^>]*> move v(1|0),zero
-[0-9a-f]+ <[^>]*> li at,0
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f1
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f1
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
+[0-9a-f]+ <[^>]*> ldc1 \$f0,0\(gp\)
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
+[0-9a-f]+ <[^>]*> mthc1 zero,\$f0
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
+[0-9a-f]+ <[^>]*> mthc1 zero,\$f0
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
+[0-9a-f]+ <[^>]*> mthc1 zero,\$f0
+[0-9a-f]+ <[^>]*> dmtc1 zero,\$f0
+[0-9a-f]+ <[^>]*> lui v[01],0x3ff0
+[0-9a-f]+ <[^>]*> move v[01],zero
+[0-9a-f]+ <[^>]*> lui at,0x3ff0
[0-9a-f]+ <[^>]*> mtc1 at,\$f1
[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
-[0-9a-f]+ <[^>]*> li at,0
+[0-9a-f]+ <[^>]*> lui at,0x3ff0
[0-9a-f]+ <[^>]*> mtc1 at,\$f1
[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
-[0-9a-f]+ <[^>]*> ldc1 \$f0,0\(gp\)
-[0-9a-f]+ <[^>]*> li at,0
-[0-9a-f]+ <[^>]*> mthc1 at,\$f0
+[0-9a-f]+ <[^>]*> ldc1 \$f0,(0|8)\(gp\)
[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
-[0-9a-f]+ <[^>]*> li at,0
+[0-9a-f]+ <[^>]*> lui at,0x3ff0
[0-9a-f]+ <[^>]*> mthc1 at,\$f0
[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
-[0-9a-f]+ <[^>]*> li at,0
+[0-9a-f]+ <[^>]*> lui at,0x3ff0
[0-9a-f]+ <[^>]*> mthc1 at,\$f0
[0-9a-f]+ <[^>]*> mtc1 zero,\$f0
-[0-9a-f]+ <[^>]*> li at,0
+[0-9a-f]+ <[^>]*> lui at,0x3ff0
+[0-9a-f]+ <[^>]*> mthc1 at,\$f0
+[0-9a-f]+ <[^>]*> li at,0xffc0
+[0-9a-f]+ <[^>]*> dsll32 at,at,0xe
+[0-9a-f]+ <[^>]*> dmtc1 at,\$f0
+[0-9a-f]+ <[^>]*> li v[01],0
+[0-9a-f]+ <[^>]*> li v[01],4250
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f1
+[0-9a-f]+ <[^>]*> li at,4250
+[0-9a-f]+ <[^>]*> mtc1 at,\$f0
+[0-9a-f]+ <[^>]*> mtc1 zero,\$f1
+[0-9a-f]+ <[^>]*> li at,4250
+[0-9a-f]+ <[^>]*> mtc1 at,\$f0
+[0-9a-f]+ <[^>]*> ldc1 \$f0,(0|16)\(gp\)
+[0-9a-f]+ <[^>]*> li at,4250
+[0-9a-f]+ <[^>]*> mtc1 at,\$f0
+[0-9a-f]+ <[^>]*> mthc1 zero,\$f0
+[0-9a-f]+ <[^>]*> li at,4250
+[0-9a-f]+ <[^>]*> mtc1 at,\$f0
+[0-9a-f]+ <[^>]*> mthc1 zero,\$f0
+[0-9a-f]+ <[^>]*> li at,4250
+[0-9a-f]+ <[^>]*> mtc1 at,\$f0
+[0-9a-f]+ <[^>]*> mthc1 zero,\$f0
+[0-9a-f]+ <[^>]*> li at,4250
[0-9a-f]+ <[^>]*> dmtc1 at,\$f0
\.\.\.
diff --git a/gas/testsuite/gas/mips/li-d.s b/gas/testsuite/gas/mips/li-d.s
index 8578097..561f2bc 100644
--- a/gas/testsuite/gas/mips/li-d.s
+++ b/gas/testsuite/gas/mips/li-d.s
@@ -1,6 +1,7 @@
# Source file used to test the li macro.
foo:
+ # Both words zero
.set mips1
.set fp=32
li.d $2, 0
@@ -19,6 +20,44 @@ foo:
.set mips3
li.d $f0, 0
+ # Only upper 16 bits of 64 non-zero
+ .set mips1
+ .set fp=32
+ li.d $2, 1.0
+ li.d $f0, 1.0
+ .set mips2
+ li.d $f0, 1.0
+ .set fp=xx
+ li.d $f0, 1.0
+ .set mips32r2
+ .set fp=32
+ li.d $f0, 1.0
+ .set fp=xx
+ li.d $f0, 1.0
+ .set fp=64
+ li.d $f0, 1.0
+ .set mips3
+ li.d $f0, 1.0
+
+ # Only lower 16 bits of 64 non-zero
+ .set mips1
+ .set fp=32
+ li.d $2, 2.1e-320
+ li.d $f0, 2.1e-320
+ .set mips2
+ li.d $f0, 2.1e-320
+ .set fp=xx
+ li.d $f0, 2.1e-320
+ .set mips32r2
+ .set fp=32
+ li.d $f0, 2.1e-320
+ .set fp=xx
+ li.d $f0, 2.1e-320
+ .set fp=64
+ li.d $f0, 2.1e-320
+ .set mips3
+ li.d $f0, 2.1e-320
+
# Force at least 8 (non-delay-slot) zero bytes, to make 'objdump' print ...
.align 2
.space 8
diff --git a/gas/testsuite/gas/mips/micromips@isa-override-1.d b/gas/testsuite/gas/mips/micromips@isa-override-1.d
index e600ff8..3403696 100644
--- a/gas/testsuite/gas/mips/micromips@isa-override-1.d
+++ b/gas/testsuite/gas/mips/micromips@isa-override-1.d
@@ -11,10 +11,10 @@ Disassembly of section \.text:
[0-9a-f]+ <[^>]*> 41a1 89ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 0022 1290 or v0,v0,at
[0-9a-f]+ <[^>]*> bc44 0000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 41a1 3ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 5422 383b mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 41a1 89ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 5422 283b mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 41a1 3ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 5422 383b mthc1 at,\$f2
[0-9a-f]+ <[^>]*> dc44 0000 ld v0,0\(a0\)
[0-9a-f]+ <[^>]*> 5020 89ab li at,0x89ab
[0-9a-f]+ <[^>]*> 5821 8000 dsll at,at,0x10
@@ -34,17 +34,17 @@ Disassembly of section \.text:
[0-9a-f]+ <[^>]*> 41a1 89ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 0022 1290 or v0,v0,at
[0-9a-f]+ <[^>]*> bc44 0000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 41a1 3ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 5422 383b mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 41a1 89ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 5422 283b mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 41a1 3ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 5422 383b mthc1 at,\$f2
[0-9a-f]+ <[^>]*> fc44 0000 lw v0,0\(a0\)
[0-9a-f]+ <[^>]*> fc64 0004 lw v1,4\(a0\)
[0-9a-f]+ <[^>]*> 41a1 89ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 0022 1290 or v0,v0,at
[0-9a-f]+ <[^>]*> bc44 0000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 41a1 3ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 5422 383b mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 41a1 89ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 5422 283b mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 41a1 3ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 5422 383b mthc1 at,\$f2
\.\.\.
diff --git a/gas/testsuite/gas/mips/mips32r2@isa-override-1.d b/gas/testsuite/gas/mips/mips32r2@isa-override-1.d
index 0ab21b9..0dc753a 100644
--- a/gas/testsuite/gas/mips/mips32r2@isa-override-1.d
+++ b/gas/testsuite/gas/mips/mips32r2@isa-override-1.d
@@ -11,10 +11,10 @@ Disassembly of section \.text:
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 00411025 or v0,v0,at
[0-9a-f]+ <[^>]*> d4820000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 44811000 mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> dc820000 ldc3 \$2,0\(a0\)
[0-9a-f]+ <[^>]*> 340189ab li at,0x89ab
[0-9a-f]+ <[^>]*> 00010c38 0x10c38
@@ -34,17 +34,17 @@ Disassembly of section \.text:
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 00411025 or v0,v0,at
[0-9a-f]+ <[^>]*> d4820000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 44811000 mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 8c820000 lw v0,0\(a0\)
[0-9a-f]+ <[^>]*> 8c830004 lw v1,4\(a0\)
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 00411025 or v0,v0,at
[0-9a-f]+ <[^>]*> d4820000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 44811000 mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
\.\.\.
diff --git a/gas/testsuite/gas/mips/mips64r2@isa-override-1.d b/gas/testsuite/gas/mips/mips64r2@isa-override-1.d
index d53fb2c..1e81c4e 100644
--- a/gas/testsuite/gas/mips/mips64r2@isa-override-1.d
+++ b/gas/testsuite/gas/mips/mips64r2@isa-override-1.d
@@ -11,10 +11,10 @@ Disassembly of section \.text:
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 00411025 or v0,v0,at
[0-9a-f]+ <[^>]*> d4820000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 44811000 mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> dc820000 ld v0,0\(a0\)
[0-9a-f]+ <[^>]*> 340189ab li at,0x89ab
[0-9a-f]+ <[^>]*> 00010c38 dsll at,at,0x10
@@ -34,17 +34,17 @@ Disassembly of section \.text:
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 00411025 or v0,v0,at
[0-9a-f]+ <[^>]*> d4820000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 44811000 mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 8c820000 lw v0,0\(a0\)
[0-9a-f]+ <[^>]*> 8c830004 lw v1,4\(a0\)
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 00411025 or v0,v0,at
[0-9a-f]+ <[^>]*> d4820000 ldc1 \$f2,0\(a0\)
-[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
-[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
[0-9a-f]+ <[^>]*> 3c0189ab lui at,0x89ab
[0-9a-f]+ <[^>]*> 44811000 mtc1 at,\$f2
+[0-9a-f]+ <[^>]*> 3c013ff0 lui at,0x3ff0
+[0-9a-f]+ <[^>]*> 44e11000 mthc1 at,\$f2
\.\.\.
--
2.7.4