* [Qemu-devel] [patch v3 01/18] tcg: Add field extraction primitives
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 02/18] tcg: Minor adjustments to deposit expanders Richard Henderson
` (17 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Adds tcg_gen_extract_* and tcg_gen_sextract_* for extraction of
fixed position bitfields, much like we already have for deposit.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/README | 20 ++-
tcg/aarch64/tcg-target.h | 4 +
tcg/arm/tcg-target.h | 2 +
tcg/i386/tcg-target.h | 4 +
tcg/ia64/tcg-target.h | 4 +
tcg/mips/tcg-target.h | 2 +
tcg/optimize.c | 29 +++++
tcg/ppc/tcg-target.h | 4 +
tcg/s390/tcg-target.h | 4 +
tcg/sparc/tcg-target.h | 4 +
tcg/tcg-op.c | 323 +++++++++++++++++++++++++++++++++++++++++++++++
tcg/tcg-op.h | 12 ++
tcg/tcg-opc.h | 4 +
tcg/tcg.h | 8 ++
tcg/tci/tcg-target.h | 4 +
15 files changed, 426 insertions(+), 2 deletions(-)
diff --git a/tcg/README b/tcg/README
index ae31388..065d9c2 100644
--- a/tcg/README
+++ b/tcg/README
@@ -314,11 +314,27 @@ The bitfield is described by POS/LEN, which are immediate values:
LEN - the length of the bitfield
POS - the position of the first bit, counting from the LSB
-For example, pos=8, len=4 indicates a 4-bit field at bit 8.
-This operation would be equivalent to
+For example, "deposit_i32 dest, t1, t2, 8, 4" indicates a 4-bit field
+at bit 8. This operation would be equivalent to
dest = (t1 & ~0x0f00) | ((t2 << 8) & 0x0f00)
+* extract_i32/i64 dest, t1, pos, len
+* sextract_i32/i64 dest, t1, pos, len
+
+Extract a bitfield from T1, placing the result in DEST.
+The bitfield is described by POS/LEN, which are immediate values,
+as above for deposit. For extract_*, the result will be extended
+to the left with zeros; for sextract_*, the result will be extended
+to the left with copies of the bitfield sign bit at pos + len - 1.
+
+For example, "sextract_i32 dest, t1, 8, 4" indicates a 4-bit field
+at bit 8. This operation would be equivalent to
+
+ dest = (t1 << 20) >> 28
+
+(using an arithmetic right shift).
+
* extrl_i64_i32 t0, t1
For 64-bit hosts only, extract the low 32-bits of input T1 and place it
diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
index a1d101f..410c31b 100644
--- a/tcg/aarch64/tcg-target.h
+++ b/tcg/aarch64/tcg-target.h
@@ -63,6 +63,8 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
#define TCG_TARGET_HAS_sub2_i32 1
@@ -93,6 +95,8 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 1
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
#define TCG_TARGET_HAS_sub2_i64 1
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index a0e1acf..8e724be 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -80,6 +80,8 @@ extern bool use_idiv_instructions;
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_mulu2_i32 1
#define TCG_TARGET_HAS_muls2_i32 1
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index 524cfc6..7625188 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -94,6 +94,8 @@ extern bool have_bmi1;
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
#define TCG_TARGET_HAS_sub2_i32 1
@@ -124,6 +126,8 @@ extern bool have_bmi1;
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 1
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
#define TCG_TARGET_HAS_sub2_i64 1
diff --git a/tcg/ia64/tcg-target.h b/tcg/ia64/tcg-target.h
index 6dddb7f..8856dc8 100644
--- a/tcg/ia64/tcg-target.h
+++ b/tcg/ia64/tcg-target.h
@@ -149,6 +149,10 @@ typedef enum {
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_deposit_i32 1
#define TCG_TARGET_HAS_deposit_i64 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i32 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_add2_i32 0
#define TCG_TARGET_HAS_add2_i64 0
#define TCG_TARGET_HAS_sub2_i32 0
diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h
index 3aeac87..1bcea3b 100644
--- a/tcg/mips/tcg-target.h
+++ b/tcg/mips/tcg-target.h
@@ -123,6 +123,8 @@ extern bool use_mips32r2_instructions;
#define TCG_TARGET_HAS_bswap16_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_bswap32_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_deposit_i32 use_mips32r2_instructions
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_ext8s_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_ext16s_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_rot_i32 use_mips32r2_instructions
diff --git a/tcg/optimize.c b/tcg/optimize.c
index 0f13490..f41ed2c 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -878,6 +878,19 @@ void tcg_optimize(TCGContext *s)
temps[args[2]].mask);
break;
+ CASE_OP_32_64(extract):
+ mask = extract64(temps[args[1]].mask, args[2], args[3]);
+ if (args[2] == 0) {
+ affected = temps[args[1]].mask & ~mask;
+ }
+ break;
+ CASE_OP_32_64(sextract):
+ mask = sextract64(temps[args[1]].mask, args[2], args[3]);
+ if (args[2] == 0 && (tcg_target_long)mask >= 0) {
+ affected = temps[args[1]].mask & ~mask;
+ }
+ break;
+
CASE_OP_32_64(or):
CASE_OP_32_64(xor):
mask = temps[args[1]].mask | temps[args[2]].mask;
@@ -1048,6 +1061,22 @@ void tcg_optimize(TCGContext *s)
}
goto do_default;
+ CASE_OP_32_64(extract):
+ if (temp_is_const(args[1])) {
+ tmp = extract64(temps[args[1]].val, args[2], args[3]);
+ tcg_opt_gen_movi(s, op, args, args[0], tmp);
+ break;
+ }
+ goto do_default;
+
+ CASE_OP_32_64(sextract):
+ if (temp_is_const(args[1])) {
+ tmp = sextract64(temps[args[1]].val, args[2], args[3]);
+ tcg_opt_gen_movi(s, op, args, args[0], tmp);
+ break;
+ }
+ goto do_default;
+
CASE_OP_32_64(setcond):
tmp = do_constant_folding_cond(opc, args[1], args[2], args[3]);
if (tmp != 2) {
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index dd032f2..c765d3e 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -69,6 +69,8 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i32 1
#define TCG_TARGET_HAS_nor_i32 1
#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_mulu2_i32 0
#define TCG_TARGET_HAS_muls2_i32 0
@@ -100,6 +102,8 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i64 1
#define TCG_TARGET_HAS_nor_i64 1
#define TCG_TARGET_HAS_deposit_i64 1
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
#define TCG_TARGET_HAS_sub2_i64 1
diff --git a/tcg/s390/tcg-target.h b/tcg/s390/tcg-target.h
index 0c1af24..9583df4 100644
--- a/tcg/s390/tcg-target.h
+++ b/tcg/s390/tcg-target.h
@@ -66,6 +66,8 @@ typedef enum TCGReg {
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
#define TCG_TARGET_HAS_sub2_i32 1
@@ -95,6 +97,8 @@ typedef enum TCGReg {
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 1
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
#define TCG_TARGET_HAS_sub2_i64 1
diff --git a/tcg/sparc/tcg-target.h b/tcg/sparc/tcg-target.h
index 88f9c90..a212167 100644
--- a/tcg/sparc/tcg-target.h
+++ b/tcg/sparc/tcg-target.h
@@ -111,6 +111,8 @@ extern bool use_vis3_instructions;
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 0
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
#define TCG_TARGET_HAS_sub2_i32 1
@@ -141,6 +143,8 @@ extern bool use_vis3_instructions;
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 0
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
#define TCG_TARGET_HAS_sub2_i64 1
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index 6e2fb35..c185b9c 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -560,6 +560,131 @@ void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
tcg_temp_free_i32(t1);
}
+void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 32);
+ tcg_debug_assert(ofs + len <= 32);
+
+ /* Canonicalize certain special cases, even if extract is supported. */
+ if (ofs + len == 32) {
+ tcg_gen_shri_i32(ret, arg, 32 - len);
+ return;
+ }
+ if (ofs == 0) {
+ tcg_gen_andi_i32(ret, arg, (1u << len) - 1);
+ return;
+ }
+
+ if (TCG_TARGET_HAS_extract_i32
+ && TCG_TARGET_extract_i32_valid(ofs, len)) {
+ tcg_gen_op4ii_i32(INDEX_op_extract_i32, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that zero-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i32) {
+ tcg_gen_ext16u_i32(ret, arg);
+ tcg_gen_shri_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i32) {
+ tcg_gen_ext8u_i32(ret, arg);
+ tcg_gen_shri_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+
+ /* ??? Ideally we'd know what values are available for immediate AND.
+ Assume that 8 bits are available, plus the special case of 16,
+ so that we get ext8u, ext16u. */
+ switch (len) {
+ case 1 ... 8: case 16:
+ tcg_gen_shri_i32(ret, arg, ofs);
+ tcg_gen_andi_i32(ret, ret, (1u << len) - 1);
+ break;
+ default:
+ tcg_gen_shli_i32(ret, arg, 32 - len - ofs);
+ tcg_gen_shri_i32(ret, ret, 32 - len);
+ break;
+ }
+}
+
+void tcg_gen_sextract_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 32);
+ tcg_debug_assert(ofs + len <= 32);
+
+ /* Canonicalize certain special cases, even if extract is supported. */
+ if (ofs + len == 32) {
+ tcg_gen_sari_i32(ret, arg, 32 - len);
+ return;
+ }
+ if (ofs == 0) {
+ switch (len) {
+ case 16:
+ tcg_gen_ext16s_i32(ret, arg);
+ return;
+ case 8:
+ tcg_gen_ext8s_i32(ret, arg);
+ return;
+ }
+ }
+
+ if (TCG_TARGET_HAS_sextract_i32
+ && TCG_TARGET_extract_i32_valid(ofs, len)) {
+ tcg_gen_op4ii_i32(INDEX_op_sextract_i32, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that sign-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i32) {
+ tcg_gen_ext16s_i32(ret, arg);
+ tcg_gen_sari_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i32) {
+ tcg_gen_ext8s_i32(ret, arg);
+ tcg_gen_sari_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ switch (len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i32) {
+ tcg_gen_shri_i32(ret, arg, ofs);
+ tcg_gen_ext16s_i32(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i32) {
+ tcg_gen_shri_i32(ret, arg, ofs);
+ tcg_gen_ext8s_i32(ret, ret);
+ return;
+ }
+ break;
+ }
+
+ tcg_gen_shli_i32(ret, arg, 32 - len - ofs);
+ tcg_gen_sari_i32(ret, ret, 32 - len);
+}
+
void tcg_gen_movcond_i32(TCGCond cond, TCGv_i32 ret, TCGv_i32 c1,
TCGv_i32 c2, TCGv_i32 v1, TCGv_i32 v2)
{
@@ -1635,6 +1760,204 @@ void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
tcg_temp_free_i64(t1);
}
+void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 64);
+ tcg_debug_assert(ofs + len <= 64);
+
+ /* Canonicalize certain special cases, even if extract is supported. */
+ if (ofs + len == 64) {
+ tcg_gen_shri_i64(ret, arg, 64 - len);
+ return;
+ }
+ if (ofs == 0) {
+ tcg_gen_andi_i64(ret, arg, (1ull << len) - 1);
+ return;
+ }
+
+ if (TCG_TARGET_REG_BITS == 32) {
+ /* Look for a 32-bit extract within one of the two words. */
+ if (ofs >= 32) {
+ tcg_gen_extract_i32(TCGV_LOW(ret), TCGV_HIGH(arg), ofs - 32, len);
+ tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+ return;
+ }
+ if (ofs + len <= 32) {
+ tcg_gen_extract_i32(TCGV_LOW(ret), TCGV_LOW(arg), ofs, len);
+ tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+ return;
+ }
+ /* The field is split across two words. One double-word
+ shift is better than two double-word shifts. */
+ goto do_shift_and;
+ }
+
+ if (TCG_TARGET_HAS_extract_i64
+ && TCG_TARGET_extract_i64_valid(ofs, len)) {
+ tcg_gen_op4ii_i64(INDEX_op_extract_i64, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that zero-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32u_i64) {
+ tcg_gen_ext32u_i64(ret, arg);
+ tcg_gen_shri_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i64) {
+ tcg_gen_ext16u_i64(ret, arg);
+ tcg_gen_shri_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i64) {
+ tcg_gen_ext8u_i64(ret, arg);
+ tcg_gen_shri_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+
+ /* ??? Ideally we'd know what values are available for immediate AND.
+ Assume that 8 bits are available, plus the special cases of 16 and 32,
+ so that we get ext8u, ext16u, and ext32u. */
+ switch (len) {
+ case 1 ... 8: case 16: case 32:
+ do_shift_and:
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_andi_i64(ret, ret, (1ull << len) - 1);
+ break;
+ default:
+ tcg_gen_shli_i64(ret, arg, 64 - len - ofs);
+ tcg_gen_shri_i64(ret, ret, 64 - len);
+ break;
+ }
+}
+
+void tcg_gen_sextract_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 64);
+ tcg_debug_assert(ofs + len <= 64);
+
+ /* Canonicalize certain special cases, even if sextract is supported. */
+ if (ofs + len == 64) {
+ tcg_gen_sari_i64(ret, arg, 64 - len);
+ return;
+ }
+ if (ofs == 0) {
+ switch (len) {
+ case 32:
+ tcg_gen_ext32s_i64(ret, arg);
+ return;
+ case 16:
+ tcg_gen_ext16s_i64(ret, arg);
+ return;
+ case 8:
+ tcg_gen_ext8s_i64(ret, arg);
+ return;
+ }
+ }
+
+ if (TCG_TARGET_REG_BITS == 32) {
+ /* Look for a 32-bit extract within one of the two words. */
+ if (ofs >= 32) {
+ tcg_gen_sextract_i32(TCGV_LOW(ret), TCGV_HIGH(arg), ofs - 32, len);
+ } else if (ofs + len <= 32) {
+ tcg_gen_sextract_i32(TCGV_LOW(ret), TCGV_LOW(arg), ofs, len);
+ } else if (ofs == 0) {
+ tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+ tcg_gen_sextract_i32(TCGV_HIGH(ret), TCGV_HIGH(arg), 0, len - 32);
+ return;
+ } else if (len > 32) {
+ TCGv_i32 t = tcg_temp_new_i32();
+ /* Extract the bits for the high word normally. */
+ tcg_gen_sextract_i32(t, TCGV_HIGH(arg), ofs + 32, len - 32);
+ /* Shift the field down for the low part. */
+ tcg_gen_shri_i64(ret, arg, ofs);
+ /* Overwrite the shift into the high part. */
+ tcg_gen_mov_i32(TCGV_HIGH(ret), t);
+ tcg_temp_free_i32(t);
+ return;
+ } else {
+ /* Shift the field down for the low part, such that the
+ field sits at the MSB. */
+ tcg_gen_shri_i64(ret, arg, ofs + len - 32);
+ /* Shift the field down from the MSB, sign extending. */
+ tcg_gen_sari_i32(TCGV_LOW(ret), TCGV_LOW(ret), 32 - len);
+ }
+ /* Sign-extend the field from 32 bits. */
+ tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+ return;
+ }
+
+ if (TCG_TARGET_HAS_sextract_i64
+ && TCG_TARGET_extract_i64_valid(ofs, len)) {
+ tcg_gen_op4ii_i64(INDEX_op_sextract_i64, ret, arg, ofs, len);
+ return;
+ }
+
+ /* Assume that sign-extension, if available, is cheaper than a shift. */
+ switch (ofs + len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32s_i64) {
+ tcg_gen_ext32s_i64(ret, arg);
+ tcg_gen_sari_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i64) {
+ tcg_gen_ext16s_i64(ret, arg);
+ tcg_gen_sari_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i64) {
+ tcg_gen_ext8s_i64(ret, arg);
+ tcg_gen_sari_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ switch (len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32s_i64) {
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_ext32s_i64(ret, ret);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16s_i64) {
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_ext16s_i64(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8s_i64) {
+ tcg_gen_shri_i64(ret, arg, ofs);
+ tcg_gen_ext8s_i64(ret, ret);
+ return;
+ }
+ break;
+ }
+ tcg_gen_shli_i64(ret, arg, 64 - len - ofs);
+ tcg_gen_sari_i64(ret, ret, 64 - len);
+}
+
void tcg_gen_movcond_i64(TCGCond cond, TCGv_i64 ret, TCGv_i64 c1,
TCGv_i64 c2, TCGv_i64 v1, TCGv_i64 v2)
{
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index 6d044b7..b515e6f 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -292,6 +292,10 @@ void tcg_gen_rotr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
void tcg_gen_rotri_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
unsigned int ofs, unsigned int len);
+void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len);
+void tcg_gen_sextract_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len);
void tcg_gen_brcond_i32(TCGCond cond, TCGv_i32 arg1, TCGv_i32 arg2, TCGLabel *);
void tcg_gen_brcondi_i32(TCGCond cond, TCGv_i32 arg1, int32_t arg2, TCGLabel *);
void tcg_gen_setcond_i32(TCGCond cond, TCGv_i32 ret,
@@ -469,6 +473,10 @@ void tcg_gen_rotr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
void tcg_gen_rotri_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
unsigned int ofs, unsigned int len);
+void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len);
+void tcg_gen_sextract_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len);
void tcg_gen_brcond_i64(TCGCond cond, TCGv_i64 arg1, TCGv_i64 arg2, TCGLabel *);
void tcg_gen_brcondi_i64(TCGCond cond, TCGv_i64 arg1, int64_t arg2, TCGLabel *);
void tcg_gen_setcond_i64(TCGCond cond, TCGv_i64 ret,
@@ -951,6 +959,8 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp);
#define tcg_gen_rotr_tl tcg_gen_rotr_i64
#define tcg_gen_rotri_tl tcg_gen_rotri_i64
#define tcg_gen_deposit_tl tcg_gen_deposit_i64
+#define tcg_gen_extract_tl tcg_gen_extract_i64
+#define tcg_gen_sextract_tl tcg_gen_sextract_i64
#define tcg_const_tl tcg_const_i64
#define tcg_const_local_tl tcg_const_local_i64
#define tcg_gen_movcond_tl tcg_gen_movcond_i64
@@ -1039,6 +1049,8 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp);
#define tcg_gen_rotr_tl tcg_gen_rotr_i32
#define tcg_gen_rotri_tl tcg_gen_rotri_i32
#define tcg_gen_deposit_tl tcg_gen_deposit_i32
+#define tcg_gen_extract_tl tcg_gen_extract_i32
+#define tcg_gen_sextract_tl tcg_gen_sextract_i32
#define tcg_const_tl tcg_const_i32
#define tcg_const_local_tl tcg_const_local_i32
#define tcg_gen_movcond_tl tcg_gen_movcond_i32
diff --git a/tcg/tcg-opc.h b/tcg/tcg-opc.h
index 45528d2..11563ac 100644
--- a/tcg/tcg-opc.h
+++ b/tcg/tcg-opc.h
@@ -77,6 +77,8 @@ DEF(sar_i32, 1, 2, 0, 0)
DEF(rotl_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_rot_i32))
DEF(rotr_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_rot_i32))
DEF(deposit_i32, 1, 2, 2, IMPL(TCG_TARGET_HAS_deposit_i32))
+DEF(extract_i32, 1, 1, 2, IMPL(TCG_TARGET_HAS_extract_i32))
+DEF(sextract_i32, 1, 1, 2, IMPL(TCG_TARGET_HAS_sextract_i32))
DEF(brcond_i32, 0, 2, 2, TCG_OPF_BB_END)
@@ -139,6 +141,8 @@ DEF(sar_i64, 1, 2, 0, IMPL64)
DEF(rotl_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rot_i64))
DEF(rotr_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rot_i64))
DEF(deposit_i64, 1, 2, 2, IMPL64 | IMPL(TCG_TARGET_HAS_deposit_i64))
+DEF(extract_i64, 1, 1, 2, IMPL64 | IMPL(TCG_TARGET_HAS_extract_i64))
+DEF(sextract_i64, 1, 1, 2, IMPL64 | IMPL(TCG_TARGET_HAS_sextract_i64))
/* size changing ops */
DEF(ext_i32_i64, 1, 1, 0, IMPL64)
diff --git a/tcg/tcg.h b/tcg/tcg.h
index a35e4c4..5fd3733 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -112,6 +112,8 @@ typedef uint64_t TCGRegSet;
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 0
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 0
#define TCG_TARGET_HAS_add2_i64 0
#define TCG_TARGET_HAS_sub2_i64 0
@@ -130,6 +132,12 @@ typedef uint64_t TCGRegSet;
#ifndef TCG_TARGET_deposit_i64_valid
#define TCG_TARGET_deposit_i64_valid(ofs, len) 1
#endif
+#ifndef TCG_TARGET_extract_i32_valid
+#define TCG_TARGET_extract_i32_valid(ofs, len) 1
+#endif
+#ifndef TCG_TARGET_extract_i64_valid
+#define TCG_TARGET_extract_i64_valid(ofs, len) 1
+#endif
/* Only one of DIV or DIV2 should be defined. */
#if defined(TCG_TARGET_HAS_div_i32)
diff --git a/tcg/tci/tcg-target.h b/tcg/tci/tcg-target.h
index 868228b..2065042 100644
--- a/tcg/tci/tcg-target.h
+++ b/tcg/tci/tcg-target.h
@@ -69,6 +69,8 @@
#define TCG_TARGET_HAS_ext16u_i32 1
#define TCG_TARGET_HAS_andc_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_eqv_i32 0
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
@@ -88,6 +90,8 @@
#define TCG_TARGET_HAS_bswap32_i64 1
#define TCG_TARGET_HAS_bswap64_i64 1
#define TCG_TARGET_HAS_deposit_i64 1
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_div_i64 0
#define TCG_TARGET_HAS_rem_i64 0
#define TCG_TARGET_HAS_ext8s_i64 1
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 02/18] tcg: Minor adjustments to deposit expanders
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 01/18] tcg: Add field extraction primitives Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 03/18] tcg: Add deposit_z expander Richard Henderson
` (16 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Assert that len is not 0.
Since we have asserted that ofs + len <= N, a later
check for len == N implies that ofs == 0.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/tcg-op.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index c185b9c..b17f03f 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -533,10 +533,11 @@ void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
TCGv_i32 t1;
tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
tcg_debug_assert(len <= 32);
tcg_debug_assert(ofs + len <= 32);
- if (ofs == 0 && len == 32) {
+ if (len == 32) {
tcg_gen_mov_i32(ret, arg2);
return;
}
@@ -1718,10 +1719,11 @@ void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
TCGv_i64 t1;
tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
tcg_debug_assert(len <= 64);
tcg_debug_assert(ofs + len <= 64);
- if (ofs == 0 && len == 64) {
+ if (len == 64) {
tcg_gen_mov_i64(ret, arg2);
return;
}
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 03/18] tcg: Add deposit_z expander
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 01/18] tcg: Add field extraction primitives Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 02/18] tcg: Minor adjustments to deposit expanders Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 04/18] tcg/aarch64: Implement field extraction opcodes Richard Henderson
` (15 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
While we don't require a new opcode, it is handy to have an expander
that knows the first source is zero.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/tcg-op.c | 143 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
tcg/tcg-op.h | 6 +++
2 files changed, 149 insertions(+)
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index b17f03f..1927e53 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -561,6 +561,64 @@ void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
tcg_temp_free_i32(t1);
}
+void tcg_gen_deposit_z_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 32);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 32);
+ tcg_debug_assert(ofs + len <= 32);
+
+ if (ofs + len == 32) {
+ tcg_gen_shli_i32(ret, arg, ofs);
+ } else if (ofs == 0) {
+ tcg_gen_andi_i32(ret, arg, (1u << len) - 1);
+ } else if (TCG_TARGET_HAS_deposit_i32
+ && TCG_TARGET_deposit_i32_valid(ofs, len)) {
+ TCGv_i32 zero = tcg_const_i32(0);
+ tcg_gen_op5ii_i32(INDEX_op_deposit_i32, ret, zero, arg, ofs, len);
+ tcg_temp_free_i32(zero);
+ } else {
+ /* To help two-operand hosts we prefer to zero-extend first,
+ which allows ARG to stay live. */
+ switch (len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i32) {
+ tcg_gen_ext16u_i32(ret, arg);
+ tcg_gen_shli_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i32) {
+ tcg_gen_ext8u_i32(ret, arg);
+ tcg_gen_shli_i32(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ /* Otherwise prefer zero-extension over AND for code size. */
+ switch (ofs + len) {
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i32) {
+ tcg_gen_shli_i32(ret, arg, ofs);
+ tcg_gen_ext16u_i32(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i32) {
+ tcg_gen_shli_i32(ret, arg, ofs);
+ tcg_gen_ext8u_i32(ret, ret);
+ return;
+ }
+ break;
+ }
+ tcg_gen_andi_i32(ret, arg, (1u << len) - 1);
+ tcg_gen_shli_i32(ret, ret, ofs);
+ }
+}
+
void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg,
unsigned int ofs, unsigned int len)
{
@@ -1762,6 +1820,91 @@ void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
tcg_temp_free_i64(t1);
}
+void tcg_gen_deposit_z_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len)
+{
+ tcg_debug_assert(ofs < 64);
+ tcg_debug_assert(len > 0);
+ tcg_debug_assert(len <= 64);
+ tcg_debug_assert(ofs + len <= 64);
+
+ if (ofs + len == 64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ } else if (ofs == 0) {
+ tcg_gen_andi_i64(ret, arg, (1ull << len) - 1);
+ } else if (TCG_TARGET_HAS_deposit_i64
+ && TCG_TARGET_deposit_i64_valid(ofs, len)) {
+ TCGv_i64 zero = tcg_const_i64(0);
+ tcg_gen_op5ii_i64(INDEX_op_deposit_i64, ret, zero, arg, ofs, len);
+ tcg_temp_free_i64(zero);
+ } else {
+ if (TCG_TARGET_REG_BITS == 32) {
+ if (ofs >= 32) {
+ tcg_gen_deposit_z_i32(TCGV_HIGH(ret), TCGV_LOW(arg),
+ ofs - 32, len);
+ tcg_gen_movi_i32(TCGV_LOW(ret), 0);
+ return;
+ }
+ if (ofs + len <= 32) {
+ tcg_gen_deposit_z_i32(TCGV_LOW(ret), TCGV_LOW(arg), ofs, len);
+ tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+ return;
+ }
+ }
+ /* To help two-operand hosts we prefer to zero-extend first,
+ which allows ARG to stay live. */
+ switch (len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32u_i64) {
+ tcg_gen_ext32u_i64(ret, arg);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i64) {
+ tcg_gen_ext16u_i64(ret, arg);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i64) {
+ tcg_gen_ext8u_i64(ret, arg);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ return;
+ }
+ break;
+ }
+ /* Otherwise prefer zero-extension over AND for code size. */
+ switch (ofs + len) {
+ case 32:
+ if (TCG_TARGET_HAS_ext32u_i64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ tcg_gen_ext32u_i64(ret, ret);
+ return;
+ }
+ break;
+ case 16:
+ if (TCG_TARGET_HAS_ext16u_i64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ tcg_gen_ext16u_i64(ret, ret);
+ return;
+ }
+ break;
+ case 8:
+ if (TCG_TARGET_HAS_ext8u_i64) {
+ tcg_gen_shli_i64(ret, arg, ofs);
+ tcg_gen_ext8u_i64(ret, ret);
+ return;
+ }
+ break;
+ }
+ tcg_gen_andi_i64(ret, arg, (1ull << len) - 1);
+ tcg_gen_shli_i64(ret, ret, ofs);
+ }
+}
+
void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg,
unsigned int ofs, unsigned int len)
{
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
index b515e6f..d42fd0d 100644
--- a/tcg/tcg-op.h
+++ b/tcg/tcg-op.h
@@ -292,6 +292,8 @@ void tcg_gen_rotr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
void tcg_gen_rotri_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
unsigned int ofs, unsigned int len);
+void tcg_gen_deposit_z_i32(TCGv_i32 ret, TCGv_i32 arg,
+ unsigned int ofs, unsigned int len);
void tcg_gen_extract_i32(TCGv_i32 ret, TCGv_i32 arg,
unsigned int ofs, unsigned int len);
void tcg_gen_sextract_i32(TCGv_i32 ret, TCGv_i32 arg,
@@ -473,6 +475,8 @@ void tcg_gen_rotr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
void tcg_gen_rotri_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
unsigned int ofs, unsigned int len);
+void tcg_gen_deposit_z_i64(TCGv_i64 ret, TCGv_i64 arg,
+ unsigned int ofs, unsigned int len);
void tcg_gen_extract_i64(TCGv_i64 ret, TCGv_i64 arg,
unsigned int ofs, unsigned int len);
void tcg_gen_sextract_i64(TCGv_i64 ret, TCGv_i64 arg,
@@ -959,6 +963,7 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp);
#define tcg_gen_rotr_tl tcg_gen_rotr_i64
#define tcg_gen_rotri_tl tcg_gen_rotri_i64
#define tcg_gen_deposit_tl tcg_gen_deposit_i64
+#define tcg_gen_deposit_z_tl tcg_gen_deposit_z_i64
#define tcg_gen_extract_tl tcg_gen_extract_i64
#define tcg_gen_sextract_tl tcg_gen_sextract_i64
#define tcg_const_tl tcg_const_i64
@@ -1049,6 +1054,7 @@ void tcg_gen_atomic_xor_fetch_i64(TCGv_i64, TCGv, TCGv_i64, TCGArg, TCGMemOp);
#define tcg_gen_rotr_tl tcg_gen_rotr_i32
#define tcg_gen_rotri_tl tcg_gen_rotri_i32
#define tcg_gen_deposit_tl tcg_gen_deposit_i32
+#define tcg_gen_deposit_z_tl tcg_gen_deposit_z_i32
#define tcg_gen_extract_tl tcg_gen_extract_i32
#define tcg_gen_sextract_tl tcg_gen_sextract_i32
#define tcg_const_tl tcg_const_i32
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 04/18] tcg/aarch64: Implement field extraction opcodes
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (2 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 03/18] tcg: Add deposit_z expander Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 05/18] tcg/arm: Move isa detection to tcg-target.h Richard Henderson
` (14 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, Claudio Fontana
Cc: qemu-arm@nongnu.org
Cc: Claudio Fontana <claudio.fontana@gmail.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/aarch64/tcg-target.h | 8 ++++----
tcg/aarch64/tcg-target.inc.c | 14 ++++++++++++++
2 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
index 410c31b..4a74bd8 100644
--- a/tcg/aarch64/tcg-target.h
+++ b/tcg/aarch64/tcg-target.h
@@ -63,8 +63,8 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
-#define TCG_TARGET_HAS_extract_i32 0
-#define TCG_TARGET_HAS_sextract_i32 0
+#define TCG_TARGET_HAS_extract_i32 1
+#define TCG_TARGET_HAS_sextract_i32 1
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
#define TCG_TARGET_HAS_sub2_i32 1
@@ -95,8 +95,8 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 1
-#define TCG_TARGET_HAS_extract_i64 0
-#define TCG_TARGET_HAS_sextract_i64 0
+#define TCG_TARGET_HAS_extract_i64 1
+#define TCG_TARGET_HAS_sextract_i64 1
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
#define TCG_TARGET_HAS_sub2_i64 1
diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c
index 1939d35..c0e9890 100644
--- a/tcg/aarch64/tcg-target.inc.c
+++ b/tcg/aarch64/tcg-target.inc.c
@@ -1640,6 +1640,16 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
tcg_out_dep(s, ext, a0, REG0(2), args[3], args[4]);
break;
+ case INDEX_op_extract_i64:
+ case INDEX_op_extract_i32:
+ tcg_out_ubfm(s, ext, a0, a1, a2, a2 + args[3] - 1);
+ break;
+
+ case INDEX_op_sextract_i64:
+ case INDEX_op_sextract_i32:
+ tcg_out_sbfm(s, ext, a0, a1, a2, a2 + args[3] - 1);
+ break;
+
case INDEX_op_add2_i32:
tcg_out_addsub2(s, TCG_TYPE_I32, a0, a1, REG0(2), REG0(3),
(int32_t)args[4], args[5], const_args[4],
@@ -1785,6 +1795,10 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
{ INDEX_op_deposit_i32, { "r", "0", "rZ" } },
{ INDEX_op_deposit_i64, { "r", "0", "rZ" } },
+ { INDEX_op_extract_i32, { "r", "r" } },
+ { INDEX_op_extract_i64, { "r", "r" } },
+ { INDEX_op_sextract_i32, { "r", "r" } },
+ { INDEX_op_sextract_i64, { "r", "r" } },
{ INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
{ INDEX_op_add2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 05/18] tcg/arm: Move isa detection to tcg-target.h
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (3 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 04/18] tcg/aarch64: Implement field extraction opcodes Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 06/18] tcg/arm: Implement field extraction opcodes Richard Henderson
` (13 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm
Cc: qemu-arm@nongnu.org
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/arm/tcg-target.h | 36 ++++++++++++++++++++++++++++++++----
tcg/arm/tcg-target.inc.c | 41 +----------------------------------------
2 files changed, 33 insertions(+), 44 deletions(-)
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index 8e724be..d1fe12b 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -26,6 +26,37 @@
#ifndef ARM_TCG_TARGET_H
#define ARM_TCG_TARGET_H
+/* The __ARM_ARCH define is provided by gcc 4.8. Construct it otherwise. */
+#ifndef __ARM_ARCH
+# if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \
+ || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) \
+ || defined(__ARM_ARCH_7EM__)
+# define __ARM_ARCH 7
+# elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) \
+ || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) \
+ || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6T2__)
+# define __ARM_ARCH 6
+# elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5E__) \
+ || defined(__ARM_ARCH_5T__) || defined(__ARM_ARCH_5TE__) \
+ || defined(__ARM_ARCH_5TEJ__)
+# define __ARM_ARCH 5
+# else
+# define __ARM_ARCH 4
+# endif
+#endif
+
+extern int arm_arch;
+
+#if defined(__ARM_ARCH_5T__) \
+ || defined(__ARM_ARCH_5TE__) || defined(__ARM_ARCH_5TEJ__)
+# define use_armv5t_instructions 1
+#else
+# define use_armv5t_instructions use_armv6_instructions
+#endif
+
+#define use_armv6_instructions (__ARM_ARCH >= 6 || arm_arch >= 6)
+#define use_armv7_instructions (__ARM_ARCH >= 7 || arm_arch >= 7)
+
#undef TCG_TARGET_STACK_GROWSUP
#define TCG_TARGET_INSN_UNIT_SIZE 4
#define TCG_TARGET_TLB_DISPLACEMENT_BITS 16
@@ -79,7 +110,7 @@ extern bool use_idiv_instructions;
#define TCG_TARGET_HAS_eqv_i32 0
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
-#define TCG_TARGET_HAS_deposit_i32 1
+#define TCG_TARGET_HAS_deposit_i32 use_armv7_instructions
#define TCG_TARGET_HAS_extract_i32 0
#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
@@ -90,9 +121,6 @@ extern bool use_idiv_instructions;
#define TCG_TARGET_HAS_div_i32 use_idiv_instructions
#define TCG_TARGET_HAS_rem_i32 0
-extern bool tcg_target_deposit_valid(int ofs, int len);
-#define TCG_TARGET_deposit_i32_valid tcg_target_deposit_valid
-
enum {
TCG_AREG0 = TCG_REG_R6,
};
diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
index ffa0d40..1415c27 100644
--- a/tcg/arm/tcg-target.inc.c
+++ b/tcg/arm/tcg-target.inc.c
@@ -25,36 +25,7 @@
#include "elf.h"
#include "tcg-be-ldst.h"
-/* The __ARM_ARCH define is provided by gcc 4.8. Construct it otherwise. */
-#ifndef __ARM_ARCH
-# if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \
- || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) \
- || defined(__ARM_ARCH_7EM__)
-# define __ARM_ARCH 7
-# elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) \
- || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) \
- || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6T2__)
-# define __ARM_ARCH 6
-# elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5E__) \
- || defined(__ARM_ARCH_5T__) || defined(__ARM_ARCH_5TE__) \
- || defined(__ARM_ARCH_5TEJ__)
-# define __ARM_ARCH 5
-# else
-# define __ARM_ARCH 4
-# endif
-#endif
-
-static int arm_arch = __ARM_ARCH;
-
-#if defined(__ARM_ARCH_5T__) \
- || defined(__ARM_ARCH_5TE__) || defined(__ARM_ARCH_5TEJ__)
-# define use_armv5t_instructions 1
-#else
-# define use_armv5t_instructions use_armv6_instructions
-#endif
-
-#define use_armv6_instructions (__ARM_ARCH >= 6 || arm_arch >= 6)
-#define use_armv7_instructions (__ARM_ARCH >= 7 || arm_arch >= 7)
+int arm_arch = __ARM_ARCH;
#ifndef use_idiv_instructions
bool use_idiv_instructions;
@@ -730,16 +701,6 @@ static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn)
}
}
-bool tcg_target_deposit_valid(int ofs, int len)
-{
- /* ??? Without bfi, we could improve over generic code by combining
- the right-shift from a non-zero ofs with the orr. We do run into
- problems when rd == rs, and the mask generated from ofs+len doesn't
- fit into an immediate. We would have to be careful not to pessimize
- wrt the optimizations performed on the expanded code. */
- return use_armv7_instructions;
-}
-
static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd,
TCGArg a1, int ofs, int len, bool const_a1)
{
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 06/18] tcg/arm: Implement field extraction opcodes
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (4 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 05/18] tcg/arm: Move isa detection to tcg-target.h Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 07/18] tcg/i386: " Richard Henderson
` (12 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm
Cc: qemu-arm@nongnu.org
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/arm/tcg-target.h | 4 ++--
tcg/arm/tcg-target.inc.c | 22 ++++++++++++++++++++++
2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index d1fe12b..4e30728 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -111,8 +111,8 @@ extern bool use_idiv_instructions;
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 use_armv7_instructions
-#define TCG_TARGET_HAS_extract_i32 0
-#define TCG_TARGET_HAS_sextract_i32 0
+#define TCG_TARGET_HAS_extract_i32 use_armv7_instructions
+#define TCG_TARGET_HAS_sextract_i32 use_armv7_instructions
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_mulu2_i32 1
#define TCG_TARGET_HAS_muls2_i32 1
diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
index 1415c27..6765a9d 100644
--- a/tcg/arm/tcg-target.inc.c
+++ b/tcg/arm/tcg-target.inc.c
@@ -713,6 +713,20 @@ static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd,
| (ofs << 7) | ((ofs + len - 1) << 16));
}
+static inline void tcg_out_extract(TCGContext *s, int cond, TCGReg rd,
+ TCGArg a1, int ofs, int len)
+{
+ tcg_out32(s, 0x07e00050 | (cond << 28) | (rd << 12) | a1
+ | (ofs << 7) | ((len - 1) << 16));
+}
+
+static inline void tcg_out_sextract(TCGContext *s, int cond, TCGReg rd,
+ TCGArg a1, int ofs, int len)
+{
+ tcg_out32(s, 0x07a00050 | (cond << 28) | (rd << 12) | a1
+ | (ofs << 7) | ((len - 1) << 16));
+}
+
/* Note that this routine is used for both LDR and LDRH formats, so we do
not wish to include an immediate shift at this point. */
static void tcg_out_memop_r(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
@@ -1894,6 +1908,12 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
tcg_out_deposit(s, COND_AL, args[0], args[2],
args[3], args[4], const_args[2]);
break;
+ case INDEX_op_extract_i32:
+ tcg_out_extract(s, COND_AL, args[0], args[1], args[2], args[3]);
+ break;
+ case INDEX_op_sextract_i32:
+ tcg_out_sextract(s, COND_AL, args[0], args[1], args[2], args[3]);
+ break;
case INDEX_op_div_i32:
tcg_out_sdiv(s, COND_AL, args[0], args[1], args[2]);
@@ -1976,6 +1996,8 @@ static const TCGTargetOpDef arm_op_defs[] = {
{ INDEX_op_ext16u_i32, { "r", "r" } },
{ INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+ { INDEX_op_extract_i32, { "r", "r" } },
+ { INDEX_op_sextract_i32, { "r", "r" } },
{ INDEX_op_div_i32, { "r", "r", "r" } },
{ INDEX_op_divu_i32, { "r", "r", "r" } },
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 07/18] tcg/i386: Implement field extraction opcodes
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (5 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 06/18] tcg/arm: Implement field extraction opcodes Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 08/18] tcg/mips: " Richard Henderson
` (11 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/i386/tcg-target.h | 12 +++++++++---
tcg/i386/tcg-target.inc.c | 38 ++++++++++++++++++++++++++++++++++++++
2 files changed, 47 insertions(+), 3 deletions(-)
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index 7625188..dc19c47 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -94,8 +94,8 @@ extern bool have_bmi1;
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
-#define TCG_TARGET_HAS_extract_i32 0
-#define TCG_TARGET_HAS_sextract_i32 0
+#define TCG_TARGET_HAS_extract_i32 1
+#define TCG_TARGET_HAS_sextract_i32 1
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
#define TCG_TARGET_HAS_sub2_i32 1
@@ -126,7 +126,7 @@ extern bool have_bmi1;
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 1
-#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_extract_i64 1
#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
@@ -142,6 +142,12 @@ extern bool have_bmi1;
((ofs) == 0 && (len) == 16))
#define TCG_TARGET_deposit_i64_valid TCG_TARGET_deposit_i32_valid
+/* Check for the possibility of high-byte extraction and, for 64-bit,
+ zero-extending 32-bit right-shift. */
+#define TCG_TARGET_extract_i32_valid(ofs, len) ((ofs) == 8 && (len) == 8)
+#define TCG_TARGET_extract_i64_valid(ofs, len) \
+ (((ofs) == 8 && (len) == 8) || ((ofs) + (len)) == 32)
+
#if TCG_TARGET_REG_BITS == 64
# define TCG_AREG0 TCG_REG_R14
#else
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index eeb1777..39f62bd 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -2143,6 +2143,40 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
}
break;
+ case INDEX_op_extract_i64:
+ if (args[2] + args[3] == 32) {
+ /* This is a 32-bit zero-extending right shift. */
+ tcg_out_mov(s, TCG_TYPE_I32, args[0], args[1]);
+ tcg_out_shifti(s, SHIFT_SHR, args[0], args[2]);
+ break;
+ }
+ /* FALLTHRU */
+ case INDEX_op_extract_i32:
+ /* On the off-chance that we can use the high-byte registers.
+ Otherwise we emit the same ext16 + shift pattern that we
+ would have gotten from the normal tcg-op.c expansion. */
+ tcg_debug_assert(args[2] == 8 && args[3] == 8);
+ if (args[1] < 4 && args[0] < 8) {
+ tcg_out_modrm(s, OPC_MOVZBL, args[0], args[1] + 4);
+ } else {
+ tcg_out_ext16u(s, args[0], args[1]);
+ tcg_out_shifti(s, SHIFT_SHR, args[0], 8);
+ }
+ break;
+
+ case INDEX_op_sextract_i32:
+ /* We don't implement sextract_i64, as we cannot sign-extend to
+ 64-bits without using the REX prefix that explicitly excludes
+ access to the high-byte registers. */
+ tcg_debug_assert(args[2] == 8 && args[3] == 8);
+ if (args[1] < 4 && args[0] < 8) {
+ tcg_out_modrm(s, OPC_MOVSBL, args[0], args[1] + 4);
+ } else {
+ tcg_out_ext16s(s, args[0], args[1], 0);
+ tcg_out_shifti(s, SHIFT_SAR, args[0], 8);
+ }
+ break;
+
case INDEX_op_mb:
tcg_out_mb(s, args[0]);
break;
@@ -2204,6 +2238,9 @@ static const TCGTargetOpDef x86_op_defs[] = {
{ INDEX_op_setcond_i32, { "q", "r", "ri" } },
{ INDEX_op_deposit_i32, { "Q", "0", "Q" } },
+ { INDEX_op_extract_i32, { "r", "r" } },
+ { INDEX_op_sextract_i32, { "r", "r" } },
+
{ INDEX_op_movcond_i32, { "r", "r", "ri", "r", "0" } },
{ INDEX_op_mulu2_i32, { "a", "d", "a", "r" } },
@@ -2265,6 +2302,7 @@ static const TCGTargetOpDef x86_op_defs[] = {
{ INDEX_op_extu_i32_i64, { "r", "r" } },
{ INDEX_op_deposit_i64, { "Q", "0", "Q" } },
+ { INDEX_op_extract_i64, { "r", "r" } },
{ INDEX_op_movcond_i64, { "r", "r", "re", "r", "0" } },
{ INDEX_op_mulu2_i64, { "a", "d", "a", "r" } },
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 08/18] tcg/mips: Implement field extraction opcodes
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (6 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 07/18] tcg/i386: " Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 09/18] tcg/ppc: " Richard Henderson
` (10 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel; +Cc: Aurelien Jarno, Yongbok Kim
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Yongbok Kim <yongbok.kim@imgtec.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/mips/tcg-target.h | 2 +-
tcg/mips/tcg-target.inc.c | 4 ++++
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h
index 1bcea3b..f1c3137 100644
--- a/tcg/mips/tcg-target.h
+++ b/tcg/mips/tcg-target.h
@@ -123,7 +123,7 @@ extern bool use_mips32r2_instructions;
#define TCG_TARGET_HAS_bswap16_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_bswap32_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_deposit_i32 use_mips32r2_instructions
-#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_extract_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_ext8s_i32 use_mips32r2_instructions
#define TCG_TARGET_HAS_ext16s_i32 use_mips32r2_instructions
diff --git a/tcg/mips/tcg-target.inc.c b/tcg/mips/tcg-target.inc.c
index abce602..1ecae08 100644
--- a/tcg/mips/tcg-target.inc.c
+++ b/tcg/mips/tcg-target.inc.c
@@ -1637,6 +1637,9 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
case INDEX_op_deposit_i32:
tcg_out_opc_bf(s, OPC_INS, a0, a2, args[3] + args[4] - 1, args[3]);
break;
+ case INDEX_op_extract_i32:
+ tcg_out_opc_bf(s, OPC_EXT, a0, a1, a2 + args[3] - 1, a2);
+ break;
case INDEX_op_brcond_i32:
tcg_out_brcond(s, a2, a0, a1, arg_label(args[3]));
@@ -1736,6 +1739,7 @@ static const TCGTargetOpDef mips_op_defs[] = {
{ INDEX_op_ext16s_i32, { "r", "rZ" } },
{ INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+ { INDEX_op_extract_i32, { "r", "r" } },
{ INDEX_op_brcond_i32, { "rZ", "rZ" } },
#if use_mips32r6_instructions
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 09/18] tcg/ppc: Implement field extraction opcodes
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (7 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 08/18] tcg/mips: " Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 10/18] tcg/s390: Expose host facilities to tcg-target.h Richard Henderson
` (9 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/ppc/tcg-target.h | 4 ++--
tcg/ppc/tcg-target.inc.c | 10 ++++++++++
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index c765d3e..b42c57a 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -69,7 +69,7 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i32 1
#define TCG_TARGET_HAS_nor_i32 1
#define TCG_TARGET_HAS_deposit_i32 1
-#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_extract_i32 1
#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_mulu2_i32 0
@@ -102,7 +102,7 @@ typedef enum {
#define TCG_TARGET_HAS_nand_i64 1
#define TCG_TARGET_HAS_nor_i64 1
#define TCG_TARGET_HAS_deposit_i64 1
-#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_extract_i64 1
#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index a3262cf..7ec54a2 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -2396,6 +2396,14 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
}
break;
+ case INDEX_op_extract_i32:
+ tcg_out_rlw(s, RLWINM, args[0], args[1],
+ 32 - args[2], 32 - args[3], 31);
+ break;
+ case INDEX_op_extract_i64:
+ tcg_out_rld(s, RLDICL, args[0], args[1], 64 - args[2], 64 - args[3]);
+ break;
+
case INDEX_op_movcond_i32:
tcg_out_movcond(s, TCG_TYPE_I32, args[5], args[0], args[1], args[2],
args[3], args[4], const_args[2]);
@@ -2530,6 +2538,7 @@ static const TCGTargetOpDef ppc_op_defs[] = {
{ INDEX_op_movcond_i32, { "r", "r", "ri", "rZ", "rZ" } },
{ INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+ { INDEX_op_extract_i32, { "r", "r" } },
{ INDEX_op_muluh_i32, { "r", "r", "r" } },
{ INDEX_op_mulsh_i32, { "r", "r", "r" } },
@@ -2585,6 +2594,7 @@ static const TCGTargetOpDef ppc_op_defs[] = {
{ INDEX_op_movcond_i64, { "r", "r", "ri", "rZ", "rZ" } },
{ INDEX_op_deposit_i64, { "r", "0", "rZ" } },
+ { INDEX_op_extract_i64, { "r", "r" } },
{ INDEX_op_mulsh_i64, { "r", "r", "r" } },
{ INDEX_op_muluh_i64, { "r", "r", "r" } },
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 10/18] tcg/s390: Expose host facilities to tcg-target.h
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (8 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 09/18] tcg/ppc: " Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 11/18] tcg/s390: Implement field extraction opcodes Richard Henderson
` (8 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
This lets us expose facilities to TCG_TARGET_HAS_* defines
directly, rather than hiding behind function calls.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/s390/tcg-target.h | 126 ++++++++++++++++++++++++----------------------
tcg/s390/tcg-target.inc.c | 74 +++++++++++----------------
2 files changed, 96 insertions(+), 104 deletions(-)
diff --git a/tcg/s390/tcg-target.h b/tcg/s390/tcg-target.h
index 9583df4..d650a72 100644
--- a/tcg/s390/tcg-target.h
+++ b/tcg/s390/tcg-target.h
@@ -49,67 +49,75 @@ typedef enum TCGReg {
#define TCG_TARGET_NB_REGS 16
-/* optional instructions */
-#define TCG_TARGET_HAS_div2_i32 1
-#define TCG_TARGET_HAS_rot_i32 1
-#define TCG_TARGET_HAS_ext8s_i32 1
-#define TCG_TARGET_HAS_ext16s_i32 1
-#define TCG_TARGET_HAS_ext8u_i32 1
-#define TCG_TARGET_HAS_ext16u_i32 1
-#define TCG_TARGET_HAS_bswap16_i32 1
-#define TCG_TARGET_HAS_bswap32_i32 1
-#define TCG_TARGET_HAS_not_i32 0
-#define TCG_TARGET_HAS_neg_i32 1
-#define TCG_TARGET_HAS_andc_i32 0
-#define TCG_TARGET_HAS_orc_i32 0
-#define TCG_TARGET_HAS_eqv_i32 0
-#define TCG_TARGET_HAS_nand_i32 0
-#define TCG_TARGET_HAS_nor_i32 0
-#define TCG_TARGET_HAS_deposit_i32 1
-#define TCG_TARGET_HAS_extract_i32 0
-#define TCG_TARGET_HAS_sextract_i32 0
-#define TCG_TARGET_HAS_movcond_i32 1
-#define TCG_TARGET_HAS_add2_i32 1
-#define TCG_TARGET_HAS_sub2_i32 1
-#define TCG_TARGET_HAS_mulu2_i32 0
-#define TCG_TARGET_HAS_muls2_i32 0
-#define TCG_TARGET_HAS_muluh_i32 0
-#define TCG_TARGET_HAS_mulsh_i32 0
-#define TCG_TARGET_HAS_extrl_i64_i32 0
-#define TCG_TARGET_HAS_extrh_i64_i32 0
+/* A list of relevant facilities used by this translator. Some of these
+ are required for proper operation, and these are checked at startup. */
+
+#define FACILITY_ZARCH_ACTIVE (1ULL << (63 - 2))
+#define FACILITY_LONG_DISP (1ULL << (63 - 18))
+#define FACILITY_EXT_IMM (1ULL << (63 - 21))
+#define FACILITY_GEN_INST_EXT (1ULL << (63 - 34))
+#define FACILITY_LOAD_ON_COND (1ULL << (63 - 45))
+#define FACILITY_FAST_BCR_SER FACILITY_LOAD_ON_COND
-#define TCG_TARGET_HAS_div2_i64 1
-#define TCG_TARGET_HAS_rot_i64 1
-#define TCG_TARGET_HAS_ext8s_i64 1
-#define TCG_TARGET_HAS_ext16s_i64 1
-#define TCG_TARGET_HAS_ext32s_i64 1
-#define TCG_TARGET_HAS_ext8u_i64 1
-#define TCG_TARGET_HAS_ext16u_i64 1
-#define TCG_TARGET_HAS_ext32u_i64 1
-#define TCG_TARGET_HAS_bswap16_i64 1
-#define TCG_TARGET_HAS_bswap32_i64 1
-#define TCG_TARGET_HAS_bswap64_i64 1
-#define TCG_TARGET_HAS_not_i64 0
-#define TCG_TARGET_HAS_neg_i64 1
-#define TCG_TARGET_HAS_andc_i64 0
-#define TCG_TARGET_HAS_orc_i64 0
-#define TCG_TARGET_HAS_eqv_i64 0
-#define TCG_TARGET_HAS_nand_i64 0
-#define TCG_TARGET_HAS_nor_i64 0
-#define TCG_TARGET_HAS_deposit_i64 1
-#define TCG_TARGET_HAS_extract_i64 0
-#define TCG_TARGET_HAS_sextract_i64 0
-#define TCG_TARGET_HAS_movcond_i64 1
-#define TCG_TARGET_HAS_add2_i64 1
-#define TCG_TARGET_HAS_sub2_i64 1
-#define TCG_TARGET_HAS_mulu2_i64 1
-#define TCG_TARGET_HAS_muls2_i64 0
-#define TCG_TARGET_HAS_muluh_i64 0
-#define TCG_TARGET_HAS_mulsh_i64 0
+extern uint64_t s390_facilities;
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div2_i32 1
+#define TCG_TARGET_HAS_rot_i32 1
+#define TCG_TARGET_HAS_ext8s_i32 1
+#define TCG_TARGET_HAS_ext16s_i32 1
+#define TCG_TARGET_HAS_ext8u_i32 1
+#define TCG_TARGET_HAS_ext16u_i32 1
+#define TCG_TARGET_HAS_bswap16_i32 1
+#define TCG_TARGET_HAS_bswap32_i32 1
+#define TCG_TARGET_HAS_not_i32 0
+#define TCG_TARGET_HAS_neg_i32 1
+#define TCG_TARGET_HAS_andc_i32 0
+#define TCG_TARGET_HAS_orc_i32 0
+#define TCG_TARGET_HAS_eqv_i32 0
+#define TCG_TARGET_HAS_nand_i32 0
+#define TCG_TARGET_HAS_nor_i32 0
+#define TCG_TARGET_HAS_deposit_i32 (s390_facilities & FACILITY_GEN_INST_EXT)
+#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_sextract_i32 0
+#define TCG_TARGET_HAS_movcond_i32 1
+#define TCG_TARGET_HAS_add2_i32 1
+#define TCG_TARGET_HAS_sub2_i32 1
+#define TCG_TARGET_HAS_mulu2_i32 0
+#define TCG_TARGET_HAS_muls2_i32 0
+#define TCG_TARGET_HAS_muluh_i32 0
+#define TCG_TARGET_HAS_mulsh_i32 0
+#define TCG_TARGET_HAS_extrl_i64_i32 0
+#define TCG_TARGET_HAS_extrh_i64_i32 0
-extern bool tcg_target_deposit_valid(int ofs, int len);
-#define TCG_TARGET_deposit_i32_valid tcg_target_deposit_valid
-#define TCG_TARGET_deposit_i64_valid tcg_target_deposit_valid
+#define TCG_TARGET_HAS_div2_i64 1
+#define TCG_TARGET_HAS_rot_i64 1
+#define TCG_TARGET_HAS_ext8s_i64 1
+#define TCG_TARGET_HAS_ext16s_i64 1
+#define TCG_TARGET_HAS_ext32s_i64 1
+#define TCG_TARGET_HAS_ext8u_i64 1
+#define TCG_TARGET_HAS_ext16u_i64 1
+#define TCG_TARGET_HAS_ext32u_i64 1
+#define TCG_TARGET_HAS_bswap16_i64 1
+#define TCG_TARGET_HAS_bswap32_i64 1
+#define TCG_TARGET_HAS_bswap64_i64 1
+#define TCG_TARGET_HAS_not_i64 0
+#define TCG_TARGET_HAS_neg_i64 1
+#define TCG_TARGET_HAS_andc_i64 0
+#define TCG_TARGET_HAS_orc_i64 0
+#define TCG_TARGET_HAS_eqv_i64 0
+#define TCG_TARGET_HAS_nand_i64 0
+#define TCG_TARGET_HAS_nor_i64 0
+#define TCG_TARGET_HAS_deposit_i64 (s390_facilities & FACILITY_GEN_INST_EXT)
+#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_sextract_i64 0
+#define TCG_TARGET_HAS_movcond_i64 1
+#define TCG_TARGET_HAS_add2_i64 1
+#define TCG_TARGET_HAS_sub2_i64 1
+#define TCG_TARGET_HAS_mulu2_i64 1
+#define TCG_TARGET_HAS_muls2_i64 0
+#define TCG_TARGET_HAS_muluh_i64 0
+#define TCG_TARGET_HAS_mulsh_i64 0
/* used for function call generation */
#define TCG_REG_CALL_STACK TCG_REG_R15
diff --git a/tcg/s390/tcg-target.inc.c b/tcg/s390/tcg-target.inc.c
index 253d4a0..9f51133 100644
--- a/tcg/s390/tcg-target.inc.c
+++ b/tcg/s390/tcg-target.inc.c
@@ -334,18 +334,7 @@ static void * const qemu_st_helpers[16] = {
#endif
static tcg_insn_unit *tb_ret_addr;
-
-/* A list of relevant facilities used by this translator. Some of these
- are required for proper operation, and these are checked at startup. */
-
-#define FACILITY_ZARCH_ACTIVE (1ULL << (63 - 2))
-#define FACILITY_LONG_DISP (1ULL << (63 - 18))
-#define FACILITY_EXT_IMM (1ULL << (63 - 21))
-#define FACILITY_GEN_INST_EXT (1ULL << (63 - 34))
-#define FACILITY_LOAD_ON_COND (1ULL << (63 - 45))
-#define FACILITY_FAST_BCR_SER FACILITY_LOAD_ON_COND
-
-static uint64_t facilities;
+uint64_t s390_facilities;
static void patch_reloc(tcg_insn_unit *code_ptr, int type,
intptr_t value, intptr_t addend)
@@ -432,7 +421,7 @@ static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
static int tcg_match_ori(TCGType type, tcg_target_long val)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if (type == TCG_TYPE_I32) {
/* All 32-bit ORs can be performed with 1 48-bit insn. */
return 1;
@@ -444,7 +433,7 @@ static int tcg_match_ori(TCGType type, tcg_target_long val)
if (val == (int16_t)val) {
return 0;
}
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if (val == (int32_t)val) {
return 0;
}
@@ -461,7 +450,7 @@ static int tcg_match_ori(TCGType type, tcg_target_long val)
static int tcg_match_xori(TCGType type, tcg_target_long val)
{
- if ((facilities & FACILITY_EXT_IMM) == 0) {
+ if ((s390_facilities & FACILITY_EXT_IMM) == 0) {
return 0;
}
@@ -482,7 +471,7 @@ static int tcg_match_xori(TCGType type, tcg_target_long val)
static int tcg_match_cmpi(TCGType type, tcg_target_long val)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
/* The COMPARE IMMEDIATE instruction is available. */
if (type == TCG_TYPE_I32) {
/* We have a 32-bit immediate and can compare against anything. */
@@ -511,7 +500,7 @@ static int tcg_match_cmpi(TCGType type, tcg_target_long val)
static int tcg_match_add2i(TCGType type, tcg_target_long val)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if (type == TCG_TYPE_I32) {
return 1;
} else if (val >= -0xffffffffll && val <= 0xffffffffll) {
@@ -541,7 +530,7 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
general-instruction-extensions, then we have MULTIPLY SINGLE
IMMEDIATE with a signed 32-bit, otherwise we have only
MULTIPLY HALFWORD IMMEDIATE, with a signed 16-bit. */
- if (facilities & FACILITY_GEN_INST_EXT) {
+ if (s390_facilities & FACILITY_GEN_INST_EXT) {
return val == (int32_t)val;
} else {
return val == (int16_t)val;
@@ -668,7 +657,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type,
}
/* Try all 48-bit insns that can load it in one go. */
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if (sval == (int32_t)sval) {
tcg_out_insn(s, RIL, LGFI, ret, sval);
return;
@@ -694,7 +683,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type,
/* If extended immediates are not present, then we may have to issue
several instructions to load the low 32 bits. */
- if (!(facilities & FACILITY_EXT_IMM)) {
+ if (!(s390_facilities & FACILITY_EXT_IMM)) {
/* A 32-bit unsigned value can be loaded in 2 insns. And given
that the lli_insns loop above did not succeed, we know that
both insns are required. */
@@ -727,7 +716,7 @@ static void tcg_out_movi(TCGContext *s, TCGType type,
/* Insert data into the high 32-bits. */
uval = uval >> 31 >> 1;
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if (uval < 0x10000) {
tcg_out_insn(s, RI, IIHL, ret, uval);
} else if ((uval & 0xffff) == 0) {
@@ -810,7 +799,7 @@ static void tcg_out_ld_abs(TCGContext *s, TCGType type, TCGReg dest, void *abs)
{
intptr_t addr = (intptr_t)abs;
- if ((facilities & FACILITY_GEN_INST_EXT) && !(addr & 1)) {
+ if ((s390_facilities & FACILITY_GEN_INST_EXT) && !(addr & 1)) {
ptrdiff_t disp = tcg_pcrel_diff(s, abs) >> 1;
if (disp == (int32_t)disp) {
if (type == TCG_TYPE_I32) {
@@ -837,7 +826,7 @@ static inline void tcg_out_risbg(TCGContext *s, TCGReg dest, TCGReg src,
static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
tcg_out_insn(s, RRE, LGBR, dest, src);
return;
}
@@ -857,7 +846,7 @@ static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
tcg_out_insn(s, RRE, LLGCR, dest, src);
return;
}
@@ -877,7 +866,7 @@ static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
tcg_out_insn(s, RRE, LGHR, dest, src);
return;
}
@@ -897,7 +886,7 @@ static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
static void tgen_ext16u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
{
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
tcg_out_insn(s, RRE, LLGHR, dest, src);
return;
}
@@ -985,7 +974,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val)
tgen_ext32u(s, dest, dest);
return;
}
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if ((val & valid) == 0xff) {
tgen_ext8u(s, TCG_TYPE_I64, dest, dest);
return;
@@ -1006,7 +995,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val)
}
/* Try all 48-bit insns that can perform it in one go. */
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
for (i = 0; i < 2; i++) {
tcg_target_ulong mask = ~(0xffffffffull << i*32);
if (((val | ~valid) & mask) == mask) {
@@ -1015,7 +1004,7 @@ static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val)
}
}
}
- if ((facilities & FACILITY_GEN_INST_EXT) && risbg_mask(val)) {
+ if ((s390_facilities & FACILITY_GEN_INST_EXT) && risbg_mask(val)) {
tgen_andi_risbg(s, dest, dest, val);
return;
}
@@ -1045,7 +1034,7 @@ static void tgen64_ori(TCGContext *s, TCGReg dest, tcg_target_ulong val)
return;
}
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
/* Try all 32-bit insns that can perform it in one go. */
for (i = 0; i < 4; i++) {
tcg_target_ulong mask = (0xffffull << i*16);
@@ -1220,7 +1209,7 @@ static void tgen_setcond(TCGContext *s, TCGType type, TCGCond cond,
}
cc = tgen_cmp(s, type, cond, c1, c2, c2const);
- if (facilities & FACILITY_LOAD_ON_COND) {
+ if (s390_facilities & FACILITY_LOAD_ON_COND) {
/* Emit: d = 0, t = 1, d = (cc ? t : d). */
tcg_out_movi(s, TCG_TYPE_I64, dest, 0);
tcg_out_movi(s, TCG_TYPE_I64, TCG_TMP0, 1);
@@ -1237,7 +1226,7 @@ static void tgen_movcond(TCGContext *s, TCGType type, TCGCond c, TCGReg dest,
TCGReg c1, TCGArg c2, int c2const, TCGReg r3)
{
int cc;
- if (facilities & FACILITY_LOAD_ON_COND) {
+ if (s390_facilities & FACILITY_LOAD_ON_COND) {
cc = tgen_cmp(s, type, c, c1, c2, c2const);
tcg_out_insn(s, RRF, LOCGR, dest, r3, cc);
} else {
@@ -1250,11 +1239,6 @@ static void tgen_movcond(TCGContext *s, TCGType type, TCGCond c, TCGReg dest,
}
}
-bool tcg_target_deposit_valid(int ofs, int len)
-{
- return (facilities & FACILITY_GEN_INST_EXT) != 0;
-}
-
static void tgen_deposit(TCGContext *s, TCGReg dest, TCGReg src,
int ofs, int len)
{
@@ -1332,7 +1316,7 @@ static void tgen_brcond(TCGContext *s, TCGType type, TCGCond c,
{
int cc;
- if (facilities & FACILITY_GEN_INST_EXT) {
+ if (s390_facilities & FACILITY_GEN_INST_EXT) {
bool is_unsigned = is_unsigned_cond(c);
bool in_range;
S390Opcode opc;
@@ -1519,7 +1503,7 @@ static TCGReg tcg_out_tlb_read(TCGContext* s, TCGReg addr_reg, TCGMemOp opc,
a_off = (a_bits >= s_bits ? 0 : s_mask - a_mask);
tlb_mask = (uint64_t)TARGET_PAGE_MASK | a_mask;
- if (facilities & FACILITY_GEN_INST_EXT) {
+ if (s390_facilities & FACILITY_GEN_INST_EXT) {
tcg_out_risbg(s, TCG_REG_R2, addr_reg,
64 - CPU_TLB_BITS - CPU_TLB_ENTRY_BITS,
63 - CPU_TLB_ENTRY_BITS,
@@ -1790,7 +1774,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
tcg_out_insn(s, RI, AHI, a0, a2);
break;
}
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
tcg_out_insn(s, RIL, AFI, a0, a2);
break;
}
@@ -1986,7 +1970,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
tcg_out_insn(s, RI, AGHI, a0, a2);
break;
}
- if (facilities & FACILITY_EXT_IMM) {
+ if (s390_facilities & FACILITY_EXT_IMM) {
if (a2 == (int32_t)a2) {
tcg_out_insn(s, RIL, AGFI, a0, a2);
break;
@@ -2175,7 +2159,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
serialize the instruction stream. */
if (args[0] & TCG_MO_ST_LD) {
tcg_out_insn(s, RR, BCR,
- facilities & FACILITY_FAST_BCR_SER ? 14 : 15, 0);
+ s390_facilities & FACILITY_FAST_BCR_SER ? 14 : 15, 0);
}
break;
@@ -2304,7 +2288,7 @@ static const TCGTargetOpDef s390_op_defs[] = {
{ -1 },
};
-static void query_facilities(void)
+static void query_s390_facilities(void)
{
unsigned long hwcap = qemu_getauxval(AT_HWCAP);
@@ -2315,7 +2299,7 @@ static void query_facilities(void)
register void *r1 __asm__("1");
/* stfle 0(%r1) */
- r1 = &facilities;
+ r1 = &s390_facilities;
asm volatile(".word 0xb2b0,0x1000"
: "=r"(r0) : "0"(0), "r"(r1) : "memory", "cc");
}
@@ -2323,7 +2307,7 @@ static void query_facilities(void)
static void tcg_target_init(TCGContext *s)
{
- query_facilities();
+ query_s390_facilities();
tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffff);
tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffff);
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 11/18] tcg/s390: Implement field extraction opcodes
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (9 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 10/18] tcg/s390: Expose host facilities to tcg-target.h Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 12/18] tcg/s390: Support deposit into zero Richard Henderson
` (7 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/s390/tcg-target.h | 4 ++--
tcg/s390/tcg-target.inc.c | 11 +++++++++++
2 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/tcg/s390/tcg-target.h b/tcg/s390/tcg-target.h
index d650a72..e9ac12e 100644
--- a/tcg/s390/tcg-target.h
+++ b/tcg/s390/tcg-target.h
@@ -78,7 +78,7 @@ extern uint64_t s390_facilities;
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 (s390_facilities & FACILITY_GEN_INST_EXT)
-#define TCG_TARGET_HAS_extract_i32 0
+#define TCG_TARGET_HAS_extract_i32 (s390_facilities & FACILITY_GEN_INST_EXT)
#define TCG_TARGET_HAS_sextract_i32 0
#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_TARGET_HAS_add2_i32 1
@@ -109,7 +109,7 @@ extern uint64_t s390_facilities;
#define TCG_TARGET_HAS_nand_i64 0
#define TCG_TARGET_HAS_nor_i64 0
#define TCG_TARGET_HAS_deposit_i64 (s390_facilities & FACILITY_GEN_INST_EXT)
-#define TCG_TARGET_HAS_extract_i64 0
+#define TCG_TARGET_HAS_extract_i64 (s390_facilities & FACILITY_GEN_INST_EXT)
#define TCG_TARGET_HAS_sextract_i64 0
#define TCG_TARGET_HAS_movcond_i64 1
#define TCG_TARGET_HAS_add2_i64 1
diff --git a/tcg/s390/tcg-target.inc.c b/tcg/s390/tcg-target.inc.c
index 9f51133..083c992 100644
--- a/tcg/s390/tcg-target.inc.c
+++ b/tcg/s390/tcg-target.inc.c
@@ -1247,6 +1247,12 @@ static void tgen_deposit(TCGContext *s, TCGReg dest, TCGReg src,
tcg_out_risbg(s, dest, src, msb, lsb, ofs, 0);
}
+static void tgen_extract(TCGContext *s, TCGReg dest, TCGReg src,
+ int ofs, int len)
+{
+ tcg_out_risbg(s, dest, src, 64 - len, 63, 64 - ofs, 1);
+}
+
static void tgen_gotoi(TCGContext *s, int cc, tcg_insn_unit *dest)
{
ptrdiff_t off = dest - s->code_ptr;
@@ -2153,6 +2159,9 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
OP_32_64(deposit):
tgen_deposit(s, args[0], args[2], args[3], args[4]);
break;
+ OP_32_64(extract):
+ tgen_extract(s, args[0], args[1], args[2], args[3]);
+ break;
case INDEX_op_mb:
/* The host memory model is quite strong, we simply need to
@@ -2222,6 +2231,7 @@ static const TCGTargetOpDef s390_op_defs[] = {
{ INDEX_op_setcond_i32, { "r", "r", "rC" } },
{ INDEX_op_movcond_i32, { "r", "r", "rC", "r", "0" } },
{ INDEX_op_deposit_i32, { "r", "0", "r" } },
+ { INDEX_op_extract_i32, { "r", "r" } },
{ INDEX_op_qemu_ld_i32, { "r", "L" } },
{ INDEX_op_qemu_ld_i64, { "r", "L" } },
@@ -2283,6 +2293,7 @@ static const TCGTargetOpDef s390_op_defs[] = {
{ INDEX_op_setcond_i64, { "r", "r", "rC" } },
{ INDEX_op_movcond_i64, { "r", "r", "rC", "r", "0" } },
{ INDEX_op_deposit_i64, { "r", "0", "r" } },
+ { INDEX_op_extract_i64, { "r", "r" } },
{ INDEX_op_mb, { } },
{ -1 },
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 12/18] tcg/s390: Support deposit into zero
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (10 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 11/18] tcg/s390: Implement field extraction opcodes Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 13/18] target-alpha: Use deposit and extract ops Richard Henderson
` (6 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Since we can no longer use matching constraints, this does
mean we must handle that data movement by hand.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
tcg/s390/tcg-target.inc.c | 30 ++++++++++++++++++++++++++----
1 file changed, 26 insertions(+), 4 deletions(-)
diff --git a/tcg/s390/tcg-target.inc.c b/tcg/s390/tcg-target.inc.c
index 083c992..f4c510e 100644
--- a/tcg/s390/tcg-target.inc.c
+++ b/tcg/s390/tcg-target.inc.c
@@ -43,6 +43,7 @@
#define TCG_CT_CONST_XORI 0x400
#define TCG_CT_CONST_CMPI 0x800
#define TCG_CT_CONST_ADLI 0x1000
+#define TCG_CT_CONST_ZERO 0x2000
/* Several places within the instruction set 0 means "no register"
rather than TCG_REG_R0. */
@@ -404,6 +405,9 @@ static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
case 'C':
ct->ct |= TCG_CT_CONST_CMPI;
break;
+ case 'Z':
+ ct->ct |= TCG_CT_CONST_ZERO;
+ break;
default:
return -1;
}
@@ -543,6 +547,8 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
return tcg_match_xori(type, val);
} else if (ct & TCG_CT_CONST_CMPI) {
return tcg_match_cmpi(type, val);
+ } else if (ct & TCG_CT_CONST_ZERO) {
+ return val == 0;
}
return 0;
@@ -1240,11 +1246,11 @@ static void tgen_movcond(TCGContext *s, TCGType type, TCGCond c, TCGReg dest,
}
static void tgen_deposit(TCGContext *s, TCGReg dest, TCGReg src,
- int ofs, int len)
+ int ofs, int len, int z)
{
int lsb = (63 - ofs);
int msb = lsb - (len - 1);
- tcg_out_risbg(s, dest, src, msb, lsb, ofs, 0);
+ tcg_out_risbg(s, dest, src, msb, lsb, ofs, z);
}
static void tgen_extract(TCGContext *s, TCGReg dest, TCGReg src,
@@ -2157,8 +2163,24 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
break;
OP_32_64(deposit):
- tgen_deposit(s, args[0], args[2], args[3], args[4]);
+ a0 = args[0], a1 = args[1], a2 = args[2];
+ if (const_args[1]) {
+ tgen_deposit(s, a0, a2, args[3], args[4], 1);
+ } else {
+ /* Since we can't support "0Z" as a constraint, we allow a1 in
+ any register. Fix things up as if a matching constraint. */
+ if (a0 != a1) {
+ TCGType type = (opc == INDEX_op_deposit_i64);
+ if (a0 == a2) {
+ tcg_out_mov(s, type, TCG_TMP0, a2);
+ a2 = TCG_TMP0;
+ }
+ tcg_out_mov(s, type, a0, a1);
+ }
+ tgen_deposit(s, a0, a2, args[3], args[4], 0);
+ }
break;
+
OP_32_64(extract):
tgen_extract(s, args[0], args[1], args[2], args[3]);
break;
@@ -2230,7 +2252,7 @@ static const TCGTargetOpDef s390_op_defs[] = {
{ INDEX_op_brcond_i32, { "r", "rC" } },
{ INDEX_op_setcond_i32, { "r", "r", "rC" } },
{ INDEX_op_movcond_i32, { "r", "r", "rC", "r", "0" } },
- { INDEX_op_deposit_i32, { "r", "0", "r" } },
+ { INDEX_op_deposit_i32, { "r", "rZ", "r" } },
{ INDEX_op_extract_i32, { "r", "r" } },
{ INDEX_op_qemu_ld_i32, { "r", "L" } },
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 13/18] target-alpha: Use deposit and extract ops
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (11 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 12/18] tcg/s390: Support deposit into zero Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 14/18] target-arm: Use new " Richard Henderson
` (5 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-alpha/translate.c | 67 ++++++++++++++++++++++++++++++------------------
1 file changed, 42 insertions(+), 25 deletions(-)
diff --git a/target-alpha/translate.c b/target-alpha/translate.c
index 114927b..5ac2277 100644
--- a/target-alpha/translate.c
+++ b/target-alpha/translate.c
@@ -949,7 +949,13 @@ static void gen_ext_h(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
if (islit) {
- tcg_gen_shli_i64(vc, va, (64 - lit * 8) & 0x3f);
+ int pos = (64 - lit * 8) & 0x3f;
+ int len = cto32(byte_mask) * 8;
+ if (pos < len) {
+ tcg_gen_deposit_z_i64(vc, va, pos, len - pos);
+ } else {
+ tcg_gen_movi_i64(vc, 0);
+ }
} else {
TCGv tmp = tcg_temp_new();
tcg_gen_shli_i64(tmp, load_gpr(ctx, rb), 3);
@@ -966,38 +972,44 @@ static void gen_ext_l(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
if (islit) {
- tcg_gen_shri_i64(vc, va, (lit & 7) * 8);
+ int pos = (lit & 7) * 8;
+ int len = cto32(byte_mask) * 8;
+ if (pos + len >= 64) {
+ len = 64 - pos;
+ }
+ tcg_gen_extract_i64(vc, va, pos, len);
} else {
TCGv tmp = tcg_temp_new();
tcg_gen_andi_i64(tmp, load_gpr(ctx, rb), 7);
tcg_gen_shli_i64(tmp, tmp, 3);
tcg_gen_shr_i64(vc, va, tmp);
tcg_temp_free(tmp);
+ gen_zapnoti(vc, vc, byte_mask);
}
- gen_zapnoti(vc, vc, byte_mask);
}
/* INSWH, INSLH, INSQH */
static void gen_ins_h(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
- TCGv tmp = tcg_temp_new();
-
- /* The instruction description has us left-shift the byte mask and extract
- bits <15:8> and apply that zap at the end. This is equivalent to simply
- performing the zap first and shifting afterward. */
- gen_zapnoti(tmp, va, byte_mask);
-
if (islit) {
- lit &= 7;
- if (unlikely(lit == 0)) {
- tcg_gen_movi_i64(vc, 0);
+ int pos = 64 - (lit & 7) * 8;
+ int len = cto32(byte_mask) * 8;
+ if (pos < len) {
+ tcg_gen_extract_i64(vc, va, pos, len - pos);
} else {
- tcg_gen_shri_i64(vc, tmp, 64 - lit * 8);
+ tcg_gen_movi_i64(vc, 0);
}
} else {
+ TCGv tmp = tcg_temp_new();
TCGv shift = tcg_temp_new();
+ /* The instruction description has us left-shift the byte mask
+ and extract bits <15:8> and apply that zap at the end. This
+ is equivalent to simply performing the zap first and shifting
+ afterward. */
+ gen_zapnoti(tmp, va, byte_mask);
+
/* If (B & 7) == 0, we need to shift by 64 and leave a zero. Do this
portably by splitting the shift into two parts: shift_count-1 and 1.
Arrange for the -1 by using ones-complement instead of
@@ -1010,32 +1022,37 @@ static void gen_ins_h(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
tcg_gen_shr_i64(vc, tmp, shift);
tcg_gen_shri_i64(vc, vc, 1);
tcg_temp_free(shift);
+ tcg_temp_free(tmp);
}
- tcg_temp_free(tmp);
}
/* INSBL, INSWL, INSLL, INSQL */
static void gen_ins_l(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
uint8_t lit, uint8_t byte_mask)
{
- TCGv tmp = tcg_temp_new();
-
- /* The instruction description has us left-shift the byte mask
- the same number of byte slots as the data and apply the zap
- at the end. This is equivalent to simply performing the zap
- first and shifting afterward. */
- gen_zapnoti(tmp, va, byte_mask);
-
if (islit) {
- tcg_gen_shli_i64(vc, tmp, (lit & 7) * 8);
+ int pos = (lit & 7) * 8;
+ int len = cto32(byte_mask) * 8;
+ if (pos + len > 64) {
+ len = 64 - pos;
+ }
+ tcg_gen_deposit_z_i64(vc, va, pos, len);
} else {
+ TCGv tmp = tcg_temp_new();
TCGv shift = tcg_temp_new();
+
+ /* The instruction description has us left-shift the byte mask
+ and extract bits <15:8> and apply that zap at the end. This
+ is equivalent to simply performing the zap first and shifting
+ afterward. */
+ gen_zapnoti(tmp, va, byte_mask);
+
tcg_gen_andi_i64(shift, load_gpr(ctx, rb), 7);
tcg_gen_shli_i64(shift, shift, 3);
tcg_gen_shl_i64(vc, tmp, shift);
tcg_temp_free(shift);
+ tcg_temp_free(tmp);
}
- tcg_temp_free(tmp);
}
/* MSKWH, MSKLH, MSKQH */
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 14/18] target-arm: Use new deposit and extract ops
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (12 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 13/18] target-alpha: Use deposit and extract ops Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 15/18] target-i386: " Richard Henderson
` (4 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm
Use the new primitives for UBFX and SBFX.
Cc: qemu-arm@nongnu.org
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-arm/translate-a64.c | 79 +++++++++++++++-------------------------------
target-arm/translate.c | 37 +++++-----------------
2 files changed, 34 insertions(+), 82 deletions(-)
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index de48747..e90487b 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -3219,67 +3219,40 @@ static void disas_bitfield(DisasContext *s, uint32_t insn)
low 32-bits anyway. */
tcg_tmp = read_cpu_reg(s, rn, 1);
- /* Recognize the common aliases. */
- if (opc == 0) { /* SBFM */
- if (ri == 0) {
- if (si == 7) { /* SXTB */
- tcg_gen_ext8s_i64(tcg_rd, tcg_tmp);
- goto done;
- } else if (si == 15) { /* SXTH */
- tcg_gen_ext16s_i64(tcg_rd, tcg_tmp);
- goto done;
- } else if (si == 31) { /* SXTW */
- tcg_gen_ext32s_i64(tcg_rd, tcg_tmp);
- goto done;
- }
- }
- if (si == 63 || (si == 31 && ri <= si)) { /* ASR */
- if (si == 31) {
- tcg_gen_ext32s_i64(tcg_tmp, tcg_tmp);
- }
- tcg_gen_sari_i64(tcg_rd, tcg_tmp, ri);
+ /* Recognize simple(r) extractions. */
+ if (ri <= si) {
+ int len = (si - ri) + 1;
+ if (opc == 0) { /* SBFM: ASR, SBFX, SXTB, SXTH, SXTW */
+ tcg_gen_sextract_i64(tcg_rd, tcg_tmp, ri, len);
goto done;
- }
- } else if (opc == 2) { /* UBFM */
- if (ri == 0) { /* UXTB, UXTH, plus non-canonical AND */
- tcg_gen_andi_i64(tcg_rd, tcg_tmp, bitmask64(si + 1));
- return;
- }
- if (si == 63 || (si == 31 && ri <= si)) { /* LSR */
- if (si == 31) {
- tcg_gen_ext32u_i64(tcg_tmp, tcg_tmp);
- }
- tcg_gen_shri_i64(tcg_rd, tcg_tmp, ri);
+ } else if (opc == 2) { /* UBFM: UBFX, LSR, UXTB, UXTH */
+ tcg_gen_extract_i64(tcg_rd, tcg_tmp, ri, len);
return;
}
- if (si + 1 == ri && si != bitsize - 1) { /* LSL */
- int shift = bitsize - 1 - si;
- tcg_gen_shli_i64(tcg_rd, tcg_tmp, shift);
- goto done;
- }
}
- if (opc != 1) { /* SBFM or UBFM */
- tcg_gen_movi_i64(tcg_rd, 0);
- }
+ /* Do the bit move operation. Note that above we handled ri <= si,
+ Wd<s-r:0> = Wn<s:r>, via tcg_gen_*extract_i64. Now we handle
+ the ri > si case, Wd<32+s-r,32-r> = Wn<s:0>, via deposit. */
+ pos = (bitsize - ri) & (bitsize - 1);
+ len = si + 1;
- /* do the bit move operation */
- if (si >= ri) {
- /* Wd<s-r:0> = Wn<s:r> */
- tcg_gen_shri_i64(tcg_tmp, tcg_tmp, ri);
- pos = 0;
- len = (si - ri) + 1;
- } else {
- /* Wd<32+s-r,32-r> = Wn<s:0> */
- pos = bitsize - ri;
- len = si + 1;
+ if (opc == 0 && len < ri) {
+ /* SBFM: sign extend the destination field from len to fill
+ the balance of the word. Let the deposit below insert all
+ of those sign bits. */
+ tcg_gen_sextract_i64(tcg_tmp, tcg_tmp, 0, len);
+ len = ri;
}
- tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_tmp, pos, len);
-
- if (opc == 0) { /* SBFM - sign extend the destination field */
- tcg_gen_shli_i64(tcg_rd, tcg_rd, 64 - (pos + len));
- tcg_gen_sari_i64(tcg_rd, tcg_rd, 64 - (pos + len));
+ if (opc == 1) { /* BFM */
+ tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_tmp, pos, len);
+ } else {
+ /* SBFM or UBFM: We start with zero, and we haven't modified
+ any bits outside bitsize, therefore the zero-extension
+ below is unneeded. */
+ tcg_gen_deposit_z_i64(tcg_rd, tcg_tmp, pos, len);
+ return;
}
done:
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 0ad9070..08da9ac 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -288,29 +288,6 @@ static void gen_revsh(TCGv_i32 var)
tcg_gen_ext16s_i32(var, var);
}
-/* Unsigned bitfield extract. */
-static void gen_ubfx(TCGv_i32 var, int shift, uint32_t mask)
-{
- if (shift)
- tcg_gen_shri_i32(var, var, shift);
- tcg_gen_andi_i32(var, var, mask);
-}
-
-/* Signed bitfield extract. */
-static void gen_sbfx(TCGv_i32 var, int shift, int width)
-{
- uint32_t signbit;
-
- if (shift)
- tcg_gen_sari_i32(var, var, shift);
- if (shift + width < 32) {
- signbit = 1u << (width - 1);
- tcg_gen_andi_i32(var, var, (1u << width) - 1);
- tcg_gen_xori_i32(var, var, signbit);
- tcg_gen_subi_i32(var, var, signbit);
- }
-}
-
/* Return (b << 32) + a. Mark inputs as dead */
static TCGv_i64 gen_addq_msw(TCGv_i64 a, TCGv_i32 b)
{
@@ -9178,9 +9155,9 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
goto illegal_op;
if (i < 32) {
if (op1 & 0x20) {
- gen_ubfx(tmp, shift, (1u << i) - 1);
+ tcg_gen_extract_i32(tmp, tmp, shift, i);
} else {
- gen_sbfx(tmp, shift, i);
+ tcg_gen_sextract_i32(tmp, tmp, shift, i);
}
}
store_reg(s, rd, tmp);
@@ -10497,15 +10474,17 @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
imm++;
if (shift + imm > 32)
goto illegal_op;
- if (imm < 32)
- gen_sbfx(tmp, shift, imm);
+ if (imm < 32) {
+ tcg_gen_sextract_i32(tmp, tmp, shift, imm);
+ }
break;
case 6: /* Unsigned bitfield extract. */
imm++;
if (shift + imm > 32)
goto illegal_op;
- if (imm < 32)
- gen_ubfx(tmp, shift, (1u << imm) - 1);
+ if (imm < 32) {
+ tcg_gen_extract_i32(tmp, tmp, shift, imm);
+ }
break;
case 3: /* Bitfield insert/clear. */
if (imm < shift)
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 15/18] target-i386: Use new deposit and extract ops
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (13 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 14/18] target-arm: Use new " Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 16/18] target-mips: Use the new extract op Richard Henderson
` (3 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
A couple of places where it was easy to identify a right-shift
followed by an extract or and-with-immediate, and the obvious
sign-extract from a high byte register.
Acked-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-i386/translate.c | 45 +++++++++++++++++++++++----------------------
1 file changed, 23 insertions(+), 22 deletions(-)
diff --git a/target-i386/translate.c b/target-i386/translate.c
index 324103c..4d6d36f 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -383,8 +383,7 @@ static void gen_op_mov_reg_v(TCGMemOp ot, int reg, TCGv t0)
static inline void gen_op_mov_v_reg(TCGMemOp ot, TCGv t0, int reg)
{
if (ot == MO_8 && byte_reg_is_xH(reg)) {
- tcg_gen_shri_tl(t0, cpu_regs[reg - 4], 8);
- tcg_gen_ext8u_tl(t0, t0);
+ tcg_gen_extract_tl(t0, cpu_regs[reg - 4], 8, 8);
} else {
tcg_gen_mov_tl(t0, cpu_regs[reg]);
}
@@ -3756,8 +3755,7 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
/* Extract the LEN into a mask. Lengths larger than
operand size get all ones. */
- tcg_gen_shri_tl(cpu_A0, cpu_regs[s->vex_v], 8);
- tcg_gen_ext8u_tl(cpu_A0, cpu_A0);
+ tcg_gen_extract_tl(cpu_A0, cpu_regs[s->vex_v], 8, 8);
tcg_gen_movcond_tl(TCG_COND_LEU, cpu_A0, cpu_A0, bound,
cpu_A0, bound);
tcg_temp_free(bound);
@@ -3908,9 +3906,8 @@ static void gen_sse(CPUX86State *env, DisasContext *s, int b,
gen_compute_eflags(s);
}
carry_in = cpu_tmp0;
- tcg_gen_shri_tl(carry_in, cpu_cc_src,
- ctz32(b == 0x1f6 ? CC_C : CC_O));
- tcg_gen_andi_tl(carry_in, carry_in, 1);
+ tcg_gen_extract_tl(carry_in, cpu_cc_src,
+ ctz32(b == 0x1f6 ? CC_C : CC_O), 1);
}
switch (ot) {
@@ -5435,21 +5432,25 @@ static target_ulong disas_insn(CPUX86State *env, DisasContext *s,
rm = (modrm & 7) | REX_B(s);
if (mod == 3) {
- gen_op_mov_v_reg(ot, cpu_T0, rm);
- switch (s_ot) {
- case MO_UB:
- tcg_gen_ext8u_tl(cpu_T0, cpu_T0);
- break;
- case MO_SB:
- tcg_gen_ext8s_tl(cpu_T0, cpu_T0);
- break;
- case MO_UW:
- tcg_gen_ext16u_tl(cpu_T0, cpu_T0);
- break;
- default:
- case MO_SW:
- tcg_gen_ext16s_tl(cpu_T0, cpu_T0);
- break;
+ if (s_ot == MO_SB && byte_reg_is_xH(rm)) {
+ tcg_gen_sextract_tl(cpu_T0, cpu_regs[rm - 4], 8, 8);
+ } else {
+ gen_op_mov_v_reg(ot, cpu_T0, rm);
+ switch (s_ot) {
+ case MO_UB:
+ tcg_gen_ext8u_tl(cpu_T0, cpu_T0);
+ break;
+ case MO_SB:
+ tcg_gen_ext8s_tl(cpu_T0, cpu_T0);
+ break;
+ case MO_UW:
+ tcg_gen_ext16u_tl(cpu_T0, cpu_T0);
+ break;
+ default:
+ case MO_SW:
+ tcg_gen_ext16s_tl(cpu_T0, cpu_T0);
+ break;
+ }
}
gen_op_mov_reg_v(d_ot, reg, cpu_T0);
} else {
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 16/18] target-mips: Use the new extract op
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (14 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 15/18] target-i386: " Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 17/18] target-ppc: Use the new deposit and extract ops Richard Henderson
` (2 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Use extract for EXT and DEXT.
Reviewed-by: Yongbok Kim <yongbok.kim@imgtec.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-mips/translate.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/target-mips/translate.c b/target-mips/translate.c
index d8dde7a..cf79aa4 100644
--- a/target-mips/translate.c
+++ b/target-mips/translate.c
@@ -4484,11 +4484,12 @@ static void gen_bitops (DisasContext *ctx, uint32_t opc, int rt,
if (lsb + msb > 31) {
goto fail;
}
- tcg_gen_shri_tl(t0, t1, lsb);
if (msb != 31) {
- tcg_gen_andi_tl(t0, t0, (1U << (msb + 1)) - 1);
+ tcg_gen_extract_tl(t0, t1, lsb, msb + 1);
} else {
- tcg_gen_ext32s_tl(t0, t0);
+ /* The two checks together imply that lsb == 0,
+ so this is a simple sign-extension. */
+ tcg_gen_ext32s_tl(t0, t1);
}
break;
#if defined(TARGET_MIPS64)
@@ -4503,10 +4504,7 @@ static void gen_bitops (DisasContext *ctx, uint32_t opc, int rt,
if (lsb + msb > 63) {
goto fail;
}
- tcg_gen_shri_tl(t0, t1, lsb);
- if (msb != 63) {
- tcg_gen_andi_tl(t0, t0, (1ULL << (msb + 1)) - 1);
- }
+ tcg_gen_extract_tl(t0, t1, lsb, msb + 1);
break;
#endif
case OPC_INS:
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 17/18] target-ppc: Use the new deposit and extract ops
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (15 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 16/18] target-mips: Use the new extract op Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:03 ` [Qemu-devel] [patch v3 18/18] target-s390x: " Richard Henderson
2016-11-16 20:59 ` [Qemu-devel] [patch v3 00/18] tcg field extract primitives no-reply
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Use the new primitives for RDWINM and RLDICL.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-ppc/translate.c | 35 +++++++++++++++++++----------------
1 file changed, 19 insertions(+), 16 deletions(-)
diff --git a/target-ppc/translate.c b/target-ppc/translate.c
index 59e9552..435c6f0 100644
--- a/target-ppc/translate.c
+++ b/target-ppc/translate.c
@@ -1975,16 +1975,16 @@ static void gen_rlwinm(DisasContext *ctx)
{
TCGv t_ra = cpu_gpr[rA(ctx->opcode)];
TCGv t_rs = cpu_gpr[rS(ctx->opcode)];
- uint32_t sh = SH(ctx->opcode);
- uint32_t mb = MB(ctx->opcode);
- uint32_t me = ME(ctx->opcode);
-
- if (mb == 0 && me == (31 - sh)) {
- tcg_gen_shli_tl(t_ra, t_rs, sh);
- tcg_gen_ext32u_tl(t_ra, t_ra);
- } else if (sh != 0 && me == 31 && sh == (32 - mb)) {
- tcg_gen_ext32u_tl(t_ra, t_rs);
- tcg_gen_shri_tl(t_ra, t_ra, mb);
+ int sh = SH(ctx->opcode);
+ int mb = MB(ctx->opcode);
+ int me = ME(ctx->opcode);
+ int len = me - mb + 1;
+ int rsh = (32 - sh) & 31;
+
+ if (sh != 0 && len > 0 && me == (31 - sh)) {
+ tcg_gen_deposit_z_tl(t_ra, t_rs, sh, len);
+ } else if (me == 31 && rsh + len <= 32) {
+ tcg_gen_extract_tl(t_ra, t_rs, rsh, len);
} else {
target_ulong mask;
#if defined(TARGET_PPC64)
@@ -1992,8 +1992,9 @@ static void gen_rlwinm(DisasContext *ctx)
me += 32;
#endif
mask = MASK(mb, me);
-
- if (mask <= 0xffffffffu) {
+ if (sh == 0) {
+ tcg_gen_andi_tl(t_ra, t_rs, mask);
+ } else if (mask <= 0xffffffffu) {
TCGv_i32 t0 = tcg_temp_new_i32();
tcg_gen_trunc_tl_i32(t0, t_rs);
tcg_gen_rotli_i32(t0, t0, sh);
@@ -2096,11 +2097,13 @@ static void gen_rldinm(DisasContext *ctx, int mb, int me, int sh)
{
TCGv t_ra = cpu_gpr[rA(ctx->opcode)];
TCGv t_rs = cpu_gpr[rS(ctx->opcode)];
+ int len = me - mb + 1;
+ int rsh = (64 - sh) & 63;
- if (sh != 0 && mb == 0 && me == (63 - sh)) {
- tcg_gen_shli_tl(t_ra, t_rs, sh);
- } else if (sh != 0 && me == 63 && sh == (64 - mb)) {
- tcg_gen_shri_tl(t_ra, t_rs, mb);
+ if (sh != 0 && len > 0 && me == (63 - sh)) {
+ tcg_gen_deposit_z_tl(t_ra, t_rs, sh, len);
+ } else if (me == 63 && rsh + len <= 64) {
+ tcg_gen_extract_tl(t_ra, t_rs, rsh, len);
} else {
tcg_gen_rotli_tl(t_ra, t_rs, sh);
tcg_gen_andi_tl(t_ra, t_ra, MASK(mb, me));
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* [Qemu-devel] [patch v3 18/18] target-s390x: Use the new deposit and extract ops
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (16 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 17/18] target-ppc: Use the new deposit and extract ops Richard Henderson
@ 2016-11-16 20:03 ` Richard Henderson
2016-11-16 20:59 ` [Qemu-devel] [patch v3 00/18] tcg field extract primitives no-reply
18 siblings, 0 replies; 20+ messages in thread
From: Richard Henderson @ 2016-11-16 20:03 UTC (permalink / raw)
To: qemu-devel
Use the new primitives for RISBG.
Signed-off-by: Richard Henderson <rth@twiddle.net>
---
target-s390x/translate.c | 34 ++++++++++++++++++++++------------
1 file changed, 22 insertions(+), 12 deletions(-)
diff --git a/target-s390x/translate.c b/target-s390x/translate.c
index 02bc705..6cebb7e 100644
--- a/target-s390x/translate.c
+++ b/target-s390x/translate.c
@@ -3134,20 +3134,26 @@ static ExitStatus op_risbg(DisasContext *s, DisasOps *o)
}
}
- /* In some cases we can implement this with deposit, which can be more
- efficient on some hosts. */
- if (~mask == imask && i3 <= i4) {
- if (s->fields->op2 == 0x5d) {
- i3 += 32, i4 += 32;
- }
+ len = i4 - i3 + 1;
+ pos = 63 - i4;
+ rot = i5 & 63;
+ if (s->fields->op2 == 0x5d) {
+ pos += 32;
+ }
+
+ /* In some cases we can implement this with extract. */
+ if (imask == 0 && pos == 0 && len > 0 && rot + len <= 64) {
+ tcg_gen_extract_i64(o->out, o->in2, rot, len);
+ return NO_EXIT;
+ }
+
+ /* In some cases we can implement this with deposit. */
+ if (len > 0 && (imask == 0 || ~mask == imask)) {
/* Note that we rotate the bits to be inserted to the lsb, not to
the position as described in the PoO. */
- len = i4 - i3 + 1;
- pos = 63 - i4;
- rot = (i5 - pos) & 63;
+ rot = (rot - pos) & 63;
} else {
- pos = len = -1;
- rot = i5 & 63;
+ pos = -1;
}
/* Rotate the input as necessary. */
@@ -3155,7 +3161,11 @@ static ExitStatus op_risbg(DisasContext *s, DisasOps *o)
/* Insert the selected bits into the output. */
if (pos >= 0) {
- tcg_gen_deposit_i64(o->out, o->out, o->in2, pos, len);
+ if (imask == 0) {
+ tcg_gen_deposit_z_i64(o->out, o->in2, pos, len);
+ } else {
+ tcg_gen_deposit_i64(o->out, o->out, o->in2, pos, len);
+ }
} else if (imask == 0) {
tcg_gen_andi_i64(o->out, o->in2, mask);
} else {
--
2.7.4
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [Qemu-devel] [patch v3 00/18] tcg field extract primitives
2016-11-16 20:03 [Qemu-devel] [patch v3 00/18] tcg field extract primitives Richard Henderson
` (17 preceding siblings ...)
2016-11-16 20:03 ` [Qemu-devel] [patch v3 18/18] target-s390x: " Richard Henderson
@ 2016-11-16 20:59 ` no-reply
18 siblings, 0 replies; 20+ messages in thread
From: no-reply @ 2016-11-16 20:59 UTC (permalink / raw)
To: rth; +Cc: famz, qemu-devel
Hi,
Your series seems to have some coding style problems. See output below for
more information:
Type: series
Subject: [Qemu-devel] [patch v3 00/18] tcg field extract primitives
Message-id: 1479326625-10682-1-git-send-email-rth@twiddle.net
=== TEST SCRIPT BEGIN ===
#!/bin/bash
BASE=base
n=1
total=$(git log --oneline $BASE.. | wc -l)
failed=0
# Useful git options
git config --local diff.renamelimit 0
git config --local diff.renames True
commits="$(git log --format=%H --reverse $BASE..)"
for c in $commits; do
echo "Checking PATCH $n/$total: $(git log -n 1 --format=%s $c)..."
if ! git show $c --format=email | ./scripts/checkpatch.pl --mailback -; then
failed=1
echo
fi
n=$((n+1))
done
exit $failed
=== TEST SCRIPT END ===
Updating 3c8cf5a9c21ff8782164d1def7f44bd888713384
From https://github.com/patchew-project/qemu
* [new tag] patchew/1479326625-10682-1-git-send-email-rth@twiddle.net -> patchew/1479326625-10682-1-git-send-email-rth@twiddle.net
* [new tag] patchew/1479326850-8369-1-git-send-email-joserz@linux.vnet.ibm.com -> patchew/1479326850-8369-1-git-send-email-joserz@linux.vnet.ibm.com
* [new tag] patchew/1479327452-16096-1-git-send-email-stefanha@redhat.com -> patchew/1479327452-16096-1-git-send-email-stefanha@redhat.com
Switched to a new branch 'test'
5f8de8d target-s390x: Use the new deposit and extract ops
5d887cd target-ppc: Use the new deposit and extract ops
823629a target-mips: Use the new extract op
b1df231 target-i386: Use new deposit and extract ops
4fcc1ad target-arm: Use new deposit and extract ops
38aa933 target-alpha: Use deposit and extract ops
935116b tcg/s390: Support deposit into zero
bc2ecb0 tcg/s390: Implement field extraction opcodes
34f18c5 tcg/s390: Expose host facilities to tcg-target.h
830033c tcg/ppc: Implement field extraction opcodes
7b20c32 tcg/mips: Implement field extraction opcodes
8e69031 tcg/i386: Implement field extraction opcodes
a10576c tcg/arm: Implement field extraction opcodes
ce7e87e tcg/arm: Move isa detection to tcg-target.h
ae30586 tcg/aarch64: Implement field extraction opcodes
fbb4fe9 tcg: Add deposit_z expander
4745d42 tcg: Minor adjustments to deposit expanders
e29bca5 tcg: Add field extraction primitives
=== OUTPUT BEGIN ===
Checking PATCH 1/18: tcg: Add field extraction primitives...
ERROR: spaces required around that ':' (ctx:VxE)
#139: FILE: tcg/optimize.c:881:
+ CASE_OP_32_64(extract):
^
ERROR: spaces required around that ':' (ctx:VxE)
#145: FILE: tcg/optimize.c:887:
+ CASE_OP_32_64(sextract):
^
ERROR: spaces required around that ':' (ctx:VxE)
#159: FILE: tcg/optimize.c:1064:
+ CASE_OP_32_64(extract):
^
ERROR: spaces required around that ':' (ctx:VxE)
#167: FILE: tcg/optimize.c:1072:
+ CASE_OP_32_64(sextract):
^
ERROR: space prohibited after that '&&' (ctx:ExW)
#271: FILE: tcg/tcg-op.c:582:
+ && TCG_TARGET_extract_i32_valid(ofs, len)) {
^
ERROR: space prohibited after that '&&' (ctx:ExW)
#334: FILE: tcg/tcg-op.c:645:
+ && TCG_TARGET_extract_i32_valid(ofs, len)) {
^
ERROR: space prohibited after that '&&' (ctx:ExW)
#420: FILE: tcg/tcg-op.c:1799:
+ && TCG_TARGET_extract_i64_valid(ofs, len)) {
^
ERROR: space prohibited after that '&&' (ctx:ExW)
#526: FILE: tcg/tcg-op.c:1905:
+ && TCG_TARGET_extract_i64_valid(ofs, len)) {
^
total: 8 errors, 0 warnings, 599 lines checked
Your patch has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
Checking PATCH 2/18: tcg: Minor adjustments to deposit expanders...
Checking PATCH 3/18: tcg: Add deposit_z expander...
ERROR: space prohibited after that '&&' (ctx:ExW)
#33: FILE: tcg/tcg-op.c:577:
+ && TCG_TARGET_deposit_i32_valid(ofs, len)) {
^
ERROR: space prohibited after that '&&' (ctx:ExW)
#98: FILE: tcg/tcg-op.c:1836:
+ && TCG_TARGET_deposit_i64_valid(ofs, len)) {
^
total: 2 errors, 0 warnings, 185 lines checked
Your patch has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
Checking PATCH 4/18: tcg/aarch64: Implement field extraction opcodes...
Checking PATCH 5/18: tcg/arm: Move isa detection to tcg-target.h...
WARNING: architecture specific defines should be avoided
#19: FILE: tcg/arm/tcg-target.h:30:
+#ifndef __ARM_ARCH
WARNING: architecture specific defines should be avoided
#20: FILE: tcg/arm/tcg-target.h:31:
+# if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \
WARNING: architecture specific defines should be avoided
#39: FILE: tcg/arm/tcg-target.h:50:
+#if defined(__ARM_ARCH_5T__) \
total: 0 errors, 3 warnings, 107 lines checked
Your patch has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
Checking PATCH 6/18: tcg/arm: Implement field extraction opcodes...
Checking PATCH 7/18: tcg/i386: Implement field extraction opcodes...
Checking PATCH 8/18: tcg/mips: Implement field extraction opcodes...
Checking PATCH 9/18: tcg/ppc: Implement field extraction opcodes...
Checking PATCH 10/18: tcg/s390: Expose host facilities to tcg-target.h...
Checking PATCH 11/18: tcg/s390: Implement field extraction opcodes...
ERROR: spaces required around that ':' (ctx:VxE)
#52: FILE: tcg/s390/tcg-target.inc.c:2162:
+ OP_32_64(extract):
^
total: 1 errors, 0 warnings, 51 lines checked
Your patch has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
Checking PATCH 12/18: tcg/s390: Support deposit into zero...
Checking PATCH 13/18: target-alpha: Use deposit and extract ops...
Checking PATCH 14/18: target-arm: Use new deposit and extract ops...
Checking PATCH 15/18: target-i386: Use new deposit and extract ops...
Checking PATCH 16/18: target-mips: Use the new extract op...
Checking PATCH 17/18: target-ppc: Use the new deposit and extract ops...
Checking PATCH 18/18: target-s390x: Use the new deposit and extract ops...
=== OUTPUT END ===
Test command exited with code: 1
---
Email generated automatically by Patchew [http://patchew.org/].
Please send your feedback to patchew-devel@freelists.org
^ permalink raw reply [flat|nested] 20+ messages in thread