scalar-crypto: Fix RV32 sha512 instructions.

These instructions are RV32 only. Previously, they zero-extended
their 32-bit result to 64-bits, to match the Spike implementation detail
that the X registers are always 64-bits long.

This exposed a data dependant problem when the instruction results fed
into the add and sltu instructions. The lack of sign extension on the
sha512*, combined with the presence of sign extension on the add, meant
sltu would (as it is currently implemented) produce the wrong result.

There were two potential fixes:

1) Sign extend from 32-bits to XLEN the result of the SHA512 instructions.

2) Change the SLTU implementation to truncate RS1/RS2 to be XLEN bits
   before it does the comparison.

This patch implements option 1, because I didn't want to mess with a
base ISA instruction. However, this leaves the implementation detail
open to cause problems for people in the future. Fixing this is outside
the scope of this commit.

 On branch scalar-crypto-fix
 Changes to be committed:
	modified:   riscv/insns/sha512sig0h.h
	modified:   riscv/insns/sha512sig0l.h
	modified:   riscv/insns/sha512sig1h.h
	modified:   riscv/insns/sha512sig1l.h
	modified:   riscv/insns/sha512sum0r.h
	modified:   riscv/insns/sha512sum1r.h

riscv/insns/sha512sig0h.h

@@ -2,8 +2,8 @@
 require_rv32;
 require_extension('K');
 
-uint32_t result =
-    ((uint32_t)RS1 >>  1) ^ ((uint32_t)RS1 >>  7) ^ ((uint32_t)RS1 >>  8) ^
-    ((uint32_t)RS2 << 31) ^                         ((uint32_t)RS2 << 24);
+reg_t result =
+    (zext32(RS1) >>  1) ^ (zext32(RS1) >>  7) ^ (zext32(RS1) >>  8) ^
+    (zext32(RS2) << 31) ^                       (zext32(RS2) << 24);
 
-WRITE_RD(zext_xlen(result));
+WRITE_RD(sext_xlen(result));

riscv/insns/sha512sig0l.h

@@ -2,8 +2,8 @@
 require_rv32;
 require_extension('K');
 
-uint32_t result =
-    ((uint32_t)RS1 >>  1) ^ ((uint32_t)RS1 >>  7) ^ ((uint32_t)RS1 >>  8) ^
-    ((uint32_t)RS2 << 31) ^ ((uint32_t)RS2 << 25) ^ ((uint32_t)RS2 << 24);
+reg_t result =
+    (zext32(RS1) >>  1) ^ (zext32(RS1) >>  7) ^ (zext32(RS1) >>  8) ^
+    (zext32(RS2) << 31) ^ (zext32(RS2) << 25) ^ (zext32(RS2) << 24);
 
-WRITE_RD(zext_xlen(result));
+WRITE_RD(sext_xlen(result));

riscv/insns/sha512sig1h.h

@@ -2,8 +2,8 @@
 require_rv32;
 require_extension('K');
 
-uint32_t result =
-    ((uint32_t)RS1 <<  3) ^ ((uint32_t)RS1 >>  6) ^ ((uint32_t)RS1 >> 19) ^
-    ((uint32_t)RS2 >> 29) ^                         ((uint32_t)RS2 << 13);
+reg_t result =
+    (zext32(RS1) <<  3) ^ (zext32(RS1) >>  6) ^ (zext32(RS1) >> 19) ^
+    (zext32(RS2) >> 29) ^                       (zext32(RS2) << 13);
 
-WRITE_RD(zext_xlen(result));
+WRITE_RD(sext_xlen(result));

riscv/insns/sha512sig1l.h

@@ -2,8 +2,8 @@
 require_rv32;
 require_extension('K');
 
-uint32_t result =
-    ((uint32_t)RS1 <<  3) ^ ((uint32_t)RS1 >>  6) ^ ((uint32_t)RS1 >> 19) ^
-    ((uint32_t)RS2 >> 29) ^ ((uint32_t)RS2 << 26) ^ ((uint32_t)RS2 << 13);
+reg_t result =
+    (zext32(RS1) <<  3) ^ (zext32(RS1) >>  6) ^ (zext32(RS1) >> 19) ^
+    (zext32(RS2) >> 29) ^ (zext32(RS2) << 26) ^ (zext32(RS2) << 13);
 
-WRITE_RD(zext_xlen(result));
+WRITE_RD(sext_xlen(result));

riscv/insns/sha512sum0r.h

@@ -2,8 +2,8 @@
 require_rv32;
 require_extension('K');
 
-uint32_t result =
-    ((uint32_t)RS1 << 25) ^ ((uint32_t)RS1 << 30) ^ ((uint32_t)RS1 >> 28) ^
-    ((uint32_t)RS2 >>  7) ^ ((uint32_t)RS2 >>  2) ^ ((uint32_t)RS2 <<  4);
+reg_t result =
+    (zext32(RS1) << 25) ^ (zext32(RS1) << 30) ^ (zext32(RS1) >> 28) ^
+    (zext32(RS2) >>  7) ^ (zext32(RS2) >>  2) ^ (zext32(RS2) <<  4);
 
-WRITE_RD(zext_xlen(result));
+WRITE_RD(sext_xlen(result));

riscv/insns/sha512sum1r.h

@@ -2,8 +2,8 @@
 require_rv32;
 require_extension('K');
 
-uint32_t result =
-    ((uint32_t)RS1 << 23) ^ ((uint32_t)RS1 >> 14) ^ ((uint32_t)RS1 >> 18) ^
-    ((uint32_t)RS2 >>  9) ^ ((uint32_t)RS2 << 18) ^ ((uint32_t)RS2 << 14);
+reg_t result =
+    (zext32(RS1) << 23) ^ (zext32(RS1) >> 14) ^ (zext32(RS1) >> 18) ^
+    (zext32(RS2) >>  9) ^ (zext32(RS2) << 18) ^ (zext32(RS2) << 14);
 
-WRITE_RD(zext_xlen(result));
+WRITE_RD(sext_xlen(result));