[ARM] Fix PR48808, PR48792: More work on CANNOT_CHANGE_MODE_CLASS

Index: gcc/reload.c
===================================================================
--- gcc/reload.c	2011-05-30 17:26:36.000000000 +0100
+++ gcc/reload.c	2011-06-01 18:45:48.000000000 +0100
@@ -1019,6 +1019,7 @@  push_reload (rtx in, rtx out, rtx *inloc
 #ifdef CANNOT_CHANGE_MODE_CLASS
       && !CANNOT_CHANGE_MODE_CLASS (GET_MODE (SUBREG_REG (in)), inmode, rclass)
 #endif
+      && contains_reg_of_mode[(int) rclass][(int) GET_MODE (SUBREG_REG (in))]
       && (CONSTANT_P (SUBREG_REG (in))
 	  || GET_CODE (SUBREG_REG (in)) == PLUS
 	  || strict_low
@@ -1125,6 +1126,7 @@  push_reload (rtx in, rtx out, rtx *inloc
 #ifdef CANNOT_CHANGE_MODE_CLASS
       && !CANNOT_CHANGE_MODE_CLASS (GET_MODE (SUBREG_REG (out)), outmode, rclass)
 #endif
+      && contains_reg_of_mode[(int) rclass][(int) GET_MODE (SUBREG_REG (out))]
       && (CONSTANT_P (SUBREG_REG (out))
 	  || strict_low
 	  || (((REG_P (SUBREG_REG (out))
Index: gcc/reload1.c
===================================================================
--- gcc/reload1.c	2011-05-30 17:26:36.000000000 +0100
+++ gcc/reload1.c	2011-06-01 18:50:01.000000000 +0100
@@ -4471,6 +4471,43 @@  scan_paradoxical_subregs (rtx x)
 	}
     }
 }
+
+/* *OP_PTR and *OTHER_PTR are two operands to a conceptual reload.
+   If *OP_PTR is a paradoxical subreg, try to remove that subreg
+   and apply the corresponding narrowing subreg to *OTHER_PTR.
+   Return true if the operands were changed, false otherwise.  */
+
+static bool
+strip_paradoxical_subreg (rtx *op_ptr, rtx *other_ptr)
+{
+  rtx op, inner, other, tem;
+
+  op = *op_ptr;
+  if (GET_CODE (op) != SUBREG)
+    return false;
+
+  inner = SUBREG_REG (op);
+  if (GET_MODE_SIZE (GET_MODE (op)) <= GET_MODE_SIZE (GET_MODE (inner)))
+    return false;
+
+  other = *other_ptr;
+  tem = gen_lowpart_common (GET_MODE (inner), other);
+  if (!tem)
+    return false;
+
+  /* If the lowpart operation turned a hard register into a subreg,
+     rather than simplifying it to another hard register, then the
+     mode change cannot be properly represented.  For example, OTHER
+     might be valid in its current mode, but not in the new one.  */
+  if (GET_CODE (tem) == SUBREG
+      && REG_P (other)
+      && HARD_REGISTER_P (other))
+    return false;
+
+  *op_ptr = inner;
+  *other_ptr = tem;
+  return true;
+}
 
 /* A subroutine of reload_as_needed.  If INSN has a REG_EH_REGION note,
    examine all of the reload insns between PREV and NEXT exclusive, and
@@ -5538,7 +5575,7 @@  gen_reload_chain_without_interm_reg_p (i
      chain reloads or do need an intermediate hard registers.  */
   bool result = true;
   int regno, n, code;
-  rtx out, in, tem, insn;
+  rtx out, in, insn;
   rtx last = get_last_insn ();
 
   /* Make r2 a component of r1.  */
@@ -5557,11 +5594,7 @@  gen_reload_chain_without_interm_reg_p (i
 
   /* If IN is a paradoxical SUBREG, remove it and try to put the
      opposite SUBREG on OUT.  Likewise for a paradoxical SUBREG on OUT.  */
-  if (GET_CODE (in) == SUBREG
-      && (GET_MODE_SIZE (GET_MODE (in))
-	  > GET_MODE_SIZE (GET_MODE (SUBREG_REG (in))))
-      && (tem = gen_lowpart_common (GET_MODE (SUBREG_REG (in)), out)) != 0)
-    in = SUBREG_REG (in), out = tem;
+  strip_paradoxical_subreg (&in, &out);
 
   if (GET_CODE (in) == PLUS
       && (REG_P (XEXP (in, 0))
@@ -7557,7 +7590,6 @@  emit_output_reload_insns (struct insn_ch
 	      if (tertiary_icode != CODE_FOR_nothing)
 		{
 		  rtx third_reloadreg = rld[tertiary_reload].reg_rtx;
-		  rtx tem;
 
 		  /* Copy primary reload reg to secondary reload reg.
 		     (Note that these have been swapped above, then
@@ -7566,13 +7598,7 @@  emit_output_reload_insns (struct insn_ch
 		  /* If REAL_OLD is a paradoxical SUBREG, remove it
 		     and try to put the opposite SUBREG on
 		     RELOADREG.  */
-		  if (GET_CODE (real_old) == SUBREG
-		      && (GET_MODE_SIZE (GET_MODE (real_old))
-			  > GET_MODE_SIZE (GET_MODE (SUBREG_REG (real_old))))
-		      && 0 != (tem = gen_lowpart_common
-			       (GET_MODE (SUBREG_REG (real_old)),
-				reloadreg)))
-		    real_old = SUBREG_REG (real_old), reloadreg = tem;
+		  strip_paradoxical_subreg (&real_old, &reloadreg);
 
 		  gen_reload (reloadreg, second_reloadreg,
 			      rl->opnum, rl->when_needed);
@@ -8388,16 +8414,8 @@  gen_reload (rtx out, rtx in, int opnum,
 
   /* If IN is a paradoxical SUBREG, remove it and try to put the
      opposite SUBREG on OUT.  Likewise for a paradoxical SUBREG on OUT.  */
-  if (GET_CODE (in) == SUBREG
-      && (GET_MODE_SIZE (GET_MODE (in))
-	  > GET_MODE_SIZE (GET_MODE (SUBREG_REG (in))))
-      && (tem = gen_lowpart_common (GET_MODE (SUBREG_REG (in)), out)) != 0)
-    in = SUBREG_REG (in), out = tem;
-  else if (GET_CODE (out) == SUBREG
-	   && (GET_MODE_SIZE (GET_MODE (out))
-	       > GET_MODE_SIZE (GET_MODE (SUBREG_REG (out))))
-	   && (tem = gen_lowpart_common (GET_MODE (SUBREG_REG (out)), in)) != 0)
-    out = SUBREG_REG (out), in = tem;
+  if (!strip_paradoxical_subreg (&in, &out))
+    strip_paradoxical_subreg (&out, &in);
 
   /* How to do this reload can get quite tricky.  Normally, we are being
      asked to reload a simple operand, such as a MEM, a constant, or a pseudo
Index: gcc/testsuite/gcc.target/sparc/ultrasp12.c
===================================================================
--- /dev/null	2011-06-01 19:41:05.354325326 +0100
+++ gcc/testsuite/gcc.target/sparc/ultrasp12.c	2011-06-01 18:52:09.000000000 +0100
@@ -0,0 +1,64 @@ 
+/* PR rtl-optimization/48830 */
+/* Testcase by Hans-Peter Nilsson <hp@gcc.gnu.org> */
+
+/* { dg-do compile } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O2 -mcpu=ultrasparc -mvis" } */
+
+typedef unsigned char uint8_t;
+typedef unsigned int uint32_t;
+typedef unsigned long int uint64_t;
+typedef unsigned long int uintmax_t;
+typedef unsigned char rc_vec_t __attribute__((__vector_size__(8)));
+typedef short rc_svec_type_ __attribute__((__vector_size__(8)));
+typedef unsigned char rc_vec4_type_ __attribute__((__vector_size__(4)));
+
+void
+rc_stat_xsum_acc(const uint8_t *__restrict src1, int src1_dim,
+                 const uint8_t *__restrict src2, int src2_dim,
+                 int len, int height, uintmax_t sum[5])
+{
+    uint32_t s1 = 0;
+    uint32_t s2 = 0;
+    uintmax_t s11 = 0;
+    uintmax_t s22 = 0;
+    uintmax_t s12 = 0;
+    int full = len / ((1024) < (1024) ? (1024) : (1024));
+    int rem = len % ((1024) < (1024) ? (1024) : (1024));
+    int rem1 = rem / 1;
+    int y;
+    unsigned int rc_gsr_scale_ __attribute__ ((__unused__)) = 7; unsigned int rc_gsr_align_ __attribute__ ((__unused__)) = 4; unsigned int rc_gsr_set_ __attribute__ ((__unused__)) = 0; register unsigned int rc_gsr_fakedep_ __attribute__ ((__unused__)) = 0; unsigned int rc_gsr_ldinit_ __attribute__ ((__unused__)) = 0;
+    for (y = 0; y < height; y++) {
+        rc_vec_t a1, a2, a11, a22, a12;
+        int i1 = (y)*(src1_dim);
+        int i2 = (y)*(src2_dim);
+        int x;
+        ((a1) = ((rc_vec_t) {0}));
+        ((a2) = ((rc_vec_t) {0}));
+        ((a11) = ((rc_vec_t) {0}));
+        ((a22) = ((rc_vec_t) {0}));
+        ((a12) = ((rc_vec_t) {0}));
+        for (x = 0; x < full; x++) {
+            int k;
+            for (k = 0; k < ((1024) < (1024) ? (1024) : (1024)) /
+                            1; k++)
+            {
+                do { rc_vec_t v1, v2; ((v1) = *(const rc_vec_t*)(&(src1)[i1])); ((v2) = *(const rc_vec_t*)(&(src2)[i2])); ((a1) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(__builtin_vis_pdist (v1, ((rc_vec_t) {0}), (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a1)).i)))).v)); ((a2) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(__builtin_vis_pdist (v2, ((rc_vec_t) {0}), (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a2)).i)))).v)); do { rc_vec_t s1_ = (v1); rc_vec_t s2_ = (v1); rc_vec_t accvin_ = (a11); rc_vec_t s1lo7_, s1msb_, accvout_; uint32_t maclo_, machi_; rc_svec_type_ masklow_ = (rc_svec_type_){(255), (255), (255), (255)}; rc_svec_type_ s1msbhi_, s1msblo_, s1lo7hi_, s1lo7lo_; rc_svec_type_ s1msbdiv2hi_, s1msbdiv2lo_; rc_vec4_type_ s1lo7hi4_, s1lo7lo4_, s1msbhi4_, s1msblo4_; rc_vec4_type_ s1msbdiv2hi4_, s1msbdiv2lo4_, s2hi4_, s2lo4_; rc_vec4_type_ accvhi4_, accvlo4_; rc_svec_type_ mulhilo7_, mullolo7_, mulhimsbdiv2_, mullomsbdiv2_; rc_svec_type_ mulhi_, mullo_, mulhihi_, mullohi_; rc_svec_type_ mulhilo_, mullolo_; rc_vec4_type_ zero4_ = (((union { rc_vec4_type_ v; uint64_t i; })(uint64_t)(0)).v); rc_vec_t msb_ = (rc_vec_t){(0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80)}; ((s1msb_) = (s1_) & (msb_)); ((s1lo7_) = (s1_) & (~msb_)); do { if (rc_gsr_ldinit_) { extern void rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(void); rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(); } if (!__builtin_constant_p(rc_gsr_align_) || !__builtin_constant_p(2) || !rc_gsr_set_ || (unsigned) (rc_gsr_align_) != rc_gsr_align_ || (unsigned) (2) != rc_gsr_scale_) { rc_gsr_set_ = 1; rc_gsr_align_ = (rc_gsr_align_); rc_gsr_scale_ = (2); unsigned int val_ = (rc_gsr_scale_ << 3) | rc_gsr_align_; if (__builtin_constant_p (val_)) { __asm__("wr %%g0,%[gsrval],%%gsr\n" ";# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "i" (val_), "1" (rc_gsr_fakedep_)); } else { __asm__("wr %[gsrval],0,%%gsr" "\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "r" (val_), "1" (rc_gsr_fakedep_)); } } else { __asm__("\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_) : "0" (s1msb_), [fakegsr] "g" (rc_gsr_fakedep_)); } } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1msb_); (s1msbhi4_) = hl_.hilo_.hi_; (s1msblo4_) = hl_.hilo_.lo_; } while (0); s1msbhi_ = __builtin_vis_fexpand(s1msbhi4_); s1msblo_ = __builtin_vis_fexpand(s1msblo4_); s1msbdiv2hi4_ = __builtin_vis_fpack16(s1msbhi_); s1msbdiv2lo4_ = __builtin_vis_fpack16(s1msblo_); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s2_); (s2hi4_) = hl_.hilo_.hi_; (s2lo4_) = hl_.hilo_.lo_; } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1lo7_); (s1lo7hi4_) = hl_.hilo_.hi_; (s1lo7lo4_) = hl_.hilo_.lo_; } while (0); s1msbdiv2hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2hi4_, zero4_); s1msbdiv2lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2lo4_, zero4_); s1lo7hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7hi4_, zero4_); s1lo7lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7lo4_, zero4_); mulhilo7_ = __builtin_vis_fmul8x16(s2hi4_, s1lo7hi_); mullolo7_ = __builtin_vis_fmul8x16(s2lo4_, s1lo7lo_); mulhimsbdiv2_ = __builtin_vis_fmul8x16(s2hi4_, s1msbdiv2hi_); mullomsbdiv2_ = __builtin_vis_fmul8x16(s2lo4_, s1msbdiv2lo_); mulhi_ = mulhilo7_ + mulhimsbdiv2_ + mulhimsbdiv2_; mullo_ = mullolo7_ + mullomsbdiv2_ + mullomsbdiv2_; mulhihi_ = mulhi_ & ~masklow_; mulhilo_ = mulhi_ & masklow_; mullohi_ = mullo_ & ~masklow_; mullolo_ = mullo_ & masklow_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (accvin_); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); maclo_ = __builtin_vis_pdist ((rc_vec_t)mullolo_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i)); maclo_ = __builtin_vis_pdist ((rc_vec_t)mulhilo_, ((rc_vec_t) {0}), maclo_); machi_ = __builtin_vis_pdist ((rc_vec_t)mullohi_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i)); machi_ = __builtin_vis_pdist ((rc_vec_t)mulhihi_, ((rc_vec_t) {0}), machi_); do { typedef union { struct { rc_vec4_type_ hi_, lo_; } hilo_; rc_vec_t v_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) {{((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)machi_)).v)), ((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)maclo_)).v))}}; (accvout_) = hl_.v_; } while (0); __asm__("\n;# dep fake GSR %[fakegsr] on %[xdep]" : [fakegsr] "=brm" (rc_gsr_fakedep_) : [xdep] "brm" (accvout_), "0" (rc_gsr_fakedep_)); (a11) = accvout_; } while (0); do { rc_vec_t s1_ = (v2); rc_vec_t s2_ = (v2); rc_vec_t accvin_ = (a22); rc_vec_t s1lo7_, s1msb_, accvout_; uint32_t maclo_, machi_; rc_svec_type_ masklow_ = (rc_svec_type_){(255), (255), (255), (255)}; rc_svec_type_ s1msbhi_, s1msblo_, s1lo7hi_, s1lo7lo_; rc_svec_type_ s1msbdiv2hi_, s1msbdiv2lo_; rc_vec4_type_ s1lo7hi4_, s1lo7lo4_, s1msbhi4_, s1msblo4_; rc_vec4_type_ s1msbdiv2hi4_, s1msbdiv2lo4_, s2hi4_, s2lo4_; rc_vec4_type_ accvhi4_, accvlo4_; rc_svec_type_ mulhilo7_, mullolo7_, mulhimsbdiv2_, mullomsbdiv2_; rc_svec_type_ mulhi_, mullo_, mulhihi_, mullohi_; rc_svec_type_ mulhilo_, mullolo_; rc_vec4_type_ zero4_ = (((union { rc_vec4_type_ v; uint64_t i; })(uint64_t)(0)).v); rc_vec_t msb_ = (rc_vec_t){(0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80)}; ((s1msb_) = (s1_) & (msb_)); ((s1lo7_) = (s1_) & (~msb_)); do { if (rc_gsr_ldinit_) { extern void rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(void); rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(); } if (!__builtin_constant_p(rc_gsr_align_) || !__builtin_constant_p(2) || !rc_gsr_set_ || (unsigned) (rc_gsr_align_) != rc_gsr_align_ || (unsigned) (2) != rc_gsr_scale_) { rc_gsr_set_ = 1; rc_gsr_align_ = (rc_gsr_align_); rc_gsr_scale_ = (2); unsigned int val_ = (rc_gsr_scale_ << 3) | rc_gsr_align_; if (__builtin_constant_p (val_)) { __asm__("wr %%g0,%[gsrval],%%gsr\n" ";# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "i" (val_), "1" (rc_gsr_fakedep_)); } else { __asm__("wr %[gsrval],0,%%gsr" "\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "r" (val_), "1" (rc_gsr_fakedep_)); } } else { __asm__("\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_) : "0" (s1msb_), [fakegsr] "g" (rc_gsr_fakedep_)); } } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1msb_); (s1msbhi4_) = hl_.hilo_.hi_; (s1msblo4_) = hl_.hilo_.lo_; } while (0); s1msbhi_ = __builtin_vis_fexpand(s1msbhi4_); s1msblo_ = __builtin_vis_fexpand(s1msblo4_); s1msbdiv2hi4_ = __builtin_vis_fpack16(s1msbhi_); s1msbdiv2lo4_ = __builtin_vis_fpack16(s1msblo_); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s2_); (s2hi4_) = hl_.hilo_.hi_; (s2lo4_) = hl_.hilo_.lo_; } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1lo7_); (s1lo7hi4_) = hl_.hilo_.hi_; (s1lo7lo4_) = hl_.hilo_.lo_; } while (0); s1msbdiv2hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2hi4_, zero4_); s1msbdiv2lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2lo4_, zero4_); s1lo7hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7hi4_, zero4_); s1lo7lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7lo4_, zero4_); mulhilo7_ = __builtin_vis_fmul8x16(s2hi4_, s1lo7hi_); mullolo7_ = __builtin_vis_fmul8x16(s2lo4_, s1lo7lo_); mulhimsbdiv2_ = __builtin_vis_fmul8x16(s2hi4_, s1msbdiv2hi_); mullomsbdiv2_ = __builtin_vis_fmul8x16(s2lo4_, s1msbdiv2lo_); mulhi_ = mulhilo7_ + mulhimsbdiv2_ + mulhimsbdiv2_; mullo_ = mullolo7_ + mullomsbdiv2_ + mullomsbdiv2_; mulhihi_ = mulhi_ & ~masklow_; mulhilo_ = mulhi_ & masklow_; mullohi_ = mullo_ & ~masklow_; mullolo_ = mullo_ & masklow_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (accvin_); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); maclo_ = __builtin_vis_pdist ((rc_vec_t)mullolo_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i)); maclo_ = __builtin_vis_pdist ((rc_vec_t)mulhilo_, ((rc_vec_t) {0}), maclo_); machi_ = __builtin_vis_pdist ((rc_vec_t)mullohi_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i)); machi_ = __builtin_vis_pdist ((rc_vec_t)mulhihi_, ((rc_vec_t) {0}), machi_); do { typedef union { struct { rc_vec4_type_ hi_, lo_; } hilo_; rc_vec_t v_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) {{((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)machi_)).v)), ((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)maclo_)).v))}}; (accvout_) = hl_.v_; } while (0); __asm__("\n;# dep fake GSR %[fakegsr] on %[xdep]" : [fakegsr] "=brm" (rc_gsr_fakedep_) : [xdep] "brm" (accvout_), "0" (rc_gsr_fakedep_)); (a22) = accvout_; } while (0); do { rc_vec_t s1_ = (v1); rc_vec_t s2_ = (v2); rc_vec_t accvin_ = (a12); rc_vec_t s1lo7_, s1msb_, accvout_; uint32_t maclo_, machi_; rc_svec_type_ masklow_ = (rc_svec_type_){(255), (255), (255), (255)}; rc_svec_type_ s1msbhi_, s1msblo_, s1lo7hi_, s1lo7lo_; rc_svec_type_ s1msbdiv2hi_, s1msbdiv2lo_; rc_vec4_type_ s1lo7hi4_, s1lo7lo4_, s1msbhi4_, s1msblo4_; rc_vec4_type_ s1msbdiv2hi4_, s1msbdiv2lo4_, s2hi4_, s2lo4_; rc_vec4_type_ accvhi4_, accvlo4_; rc_svec_type_ mulhilo7_, mullolo7_, mulhimsbdiv2_, mullomsbdiv2_; rc_svec_type_ mulhi_, mullo_, mulhihi_, mullohi_; rc_svec_type_ mulhilo_, mullolo_; rc_vec4_type_ zero4_ = (((union { rc_vec4_type_ v; uint64_t i; })(uint64_t)(0)).v); rc_vec_t msb_ = (rc_vec_t){(0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80)}; ((s1msb_) = (s1_) & (msb_)); ((s1lo7_) = (s1_) & (~msb_)); do { if (rc_gsr_ldinit_) { extern void rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(void); rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(); } if (!__builtin_constant_p(rc_gsr_align_) || !__builtin_constant_p(2) || !rc_gsr_set_ || (unsigned) (rc_gsr_align_) != rc_gsr_align_ || (unsigned) (2) != rc_gsr_scale_) { rc_gsr_set_ = 1; rc_gsr_align_ = (rc_gsr_align_); rc_gsr_scale_ = (2); unsigned int val_ = (rc_gsr_scale_ << 3) | rc_gsr_align_; if (__builtin_constant_p (val_)) { __asm__("wr %%g0,%[gsrval],%%gsr\n" ";# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "i" (val_), "1" (rc_gsr_fakedep_)); } else { __asm__("wr %[gsrval],0,%%gsr" "\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "r" (val_), "1" (rc_gsr_fakedep_)); } } else { __asm__("\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_) : "0" (s1msb_), [fakegsr] "g" (rc_gsr_fakedep_)); } } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1msb_); (s1msbhi4_) = hl_.hilo_.hi_; (s1msblo4_) = hl_.hilo_.lo_; } while (0); s1msbhi_ = __builtin_vis_fexpand(s1msbhi4_); s1msblo_ = __builtin_vis_fexpand(s1msblo4_); s1msbdiv2hi4_ = __builtin_vis_fpack16(s1msbhi_); s1msbdiv2lo4_ = __builtin_vis_fpack16(s1msblo_); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s2_); (s2hi4_) = hl_.hilo_.hi_; (s2lo4_) = hl_.hilo_.lo_; } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1lo7_); (s1lo7hi4_) = hl_.hilo_.hi_; (s1lo7lo4_) = hl_.hilo_.lo_; } while (0); s1msbdiv2hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2hi4_, zero4_); s1msbdiv2lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2lo4_, zero4_); s1lo7hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7hi4_, zero4_); s1lo7lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7lo4_, zero4_); mulhilo7_ = __builtin_vis_fmul8x16(s2hi4_, s1lo7hi_); mullolo7_ = __builtin_vis_fmul8x16(s2lo4_, s1lo7lo_); mulhimsbdiv2_ = __builtin_vis_fmul8x16(s2hi4_, s1msbdiv2hi_); mullomsbdiv2_ = __builtin_vis_fmul8x16(s2lo4_, s1msbdiv2lo_); mulhi_ = mulhilo7_ + mulhimsbdiv2_ + mulhimsbdiv2_; mullo_ = mullolo7_ + mullomsbdiv2_ + mullomsbdiv2_; mulhihi_ = mulhi_ & ~masklow_; mulhilo_ = mulhi_ & masklow_; mullohi_ = mullo_ & ~masklow_; mullolo_ = mullo_ & masklow_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (accvin_); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); maclo_ = __builtin_vis_pdist ((rc_vec_t)mullolo_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i)); maclo_ = __builtin_vis_pdist ((rc_vec_t)mulhilo_, ((rc_vec_t) {0}), maclo_); machi_ = __builtin_vis_pdist ((rc_vec_t)mullohi_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i)); machi_ = __builtin_vis_pdist ((rc_vec_t)mulhihi_, ((rc_vec_t) {0}), machi_); do { typedef union { struct { rc_vec4_type_ hi_, lo_; } hilo_; rc_vec_t v_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) {{((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)machi_)).v)), ((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)maclo_)).v))}}; (accvout_) = hl_.v_; } while (0); __asm__("\n;# dep fake GSR %[fakegsr] on %[xdep]" : [fakegsr] "=brm" (rc_gsr_fakedep_) : [xdep] "brm" (accvout_), "0" (rc_gsr_fakedep_)); (a12) = accvout_; } while (0); (i1) += 8; (i2) += 8; } while (0);
+
+            }
+            do { uint32_t t1, t2, t11, t22, t12; ((t1) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a1)).i)); ((t2) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a2)).i)); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a11); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t11) = maclo_ + machi_ * 256; } while (0); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a22); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t22) = maclo_ + machi_ * 256; } while (0); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a12); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t12) = maclo_ + machi_ * 256; } while (0); ((a1) = ((rc_vec_t) {0})); ((a2) = ((rc_vec_t) {0})); ((a11) = ((rc_vec_t) {0})); ((a22) = ((rc_vec_t) {0})); ((a12) = ((rc_vec_t) {0})); (s1) += t1; (s2) += t2; (s11) += t11; (s22) += t22; (s12) += t12; } while (0);
+        }
+        for (x = 0; x < rem1; x++) {
+            do { rc_vec_t v1, v2; ((v1) = *(const rc_vec_t*)(&(src1)[i1])); ((v2) = *(const rc_vec_t*)(&(src2)[i2])); ((a1) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(__builtin_vis_pdist (v1, ((rc_vec_t) {0}), (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a1)).i)))).v)); ((a2) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(__builtin_vis_pdist (v2, ((rc_vec_t) {0}), (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a2)).i)))).v)); do { rc_vec_t s1_ = (v1); rc_vec_t s2_ = (v1); rc_vec_t accvin_ = (a11); rc_vec_t s1lo7_, s1msb_, accvout_; uint32_t maclo_, machi_; rc_svec_type_ masklow_ = (rc_svec_type_){(255), (255), (255), (255)}; rc_svec_type_ s1msbhi_, s1msblo_, s1lo7hi_, s1lo7lo_; rc_svec_type_ s1msbdiv2hi_, s1msbdiv2lo_; rc_vec4_type_ s1lo7hi4_, s1lo7lo4_, s1msbhi4_, s1msblo4_; rc_vec4_type_ s1msbdiv2hi4_, s1msbdiv2lo4_, s2hi4_, s2lo4_; rc_vec4_type_ accvhi4_, accvlo4_; rc_svec_type_ mulhilo7_, mullolo7_, mulhimsbdiv2_, mullomsbdiv2_; rc_svec_type_ mulhi_, mullo_, mulhihi_, mullohi_; rc_svec_type_ mulhilo_, mullolo_; rc_vec4_type_ zero4_ = (((union { rc_vec4_type_ v; uint64_t i; })(uint64_t)(0)).v); rc_vec_t msb_ = (rc_vec_t){(0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80)}; ((s1msb_) = (s1_) & (msb_)); ((s1lo7_) = (s1_) & (~msb_)); do { if (rc_gsr_ldinit_) { extern void rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(void); rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(); } if (!__builtin_constant_p(rc_gsr_align_) || !__builtin_constant_p(2) || !rc_gsr_set_ || (unsigned) (rc_gsr_align_) != rc_gsr_align_ || (unsigned) (2) != rc_gsr_scale_) { rc_gsr_set_ = 1; rc_gsr_align_ = (rc_gsr_align_); rc_gsr_scale_ = (2); unsigned int val_ = (rc_gsr_scale_ << 3) | rc_gsr_align_; if (__builtin_constant_p (val_)) { __asm__("wr %%g0,%[gsrval],%%gsr\n" ";# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "i" (val_), "1" (rc_gsr_fakedep_)); } else { __asm__("wr %[gsrval],0,%%gsr" "\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "r" (val_), "1" (rc_gsr_fakedep_)); } } else { __asm__("\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_) : "0" (s1msb_), [fakegsr] "g" (rc_gsr_fakedep_)); } } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1msb_); (s1msbhi4_) = hl_.hilo_.hi_; (s1msblo4_) = hl_.hilo_.lo_; } while (0); s1msbhi_ = __builtin_vis_fexpand(s1msbhi4_); s1msblo_ = __builtin_vis_fexpand(s1msblo4_); s1msbdiv2hi4_ = __builtin_vis_fpack16(s1msbhi_); s1msbdiv2lo4_ = __builtin_vis_fpack16(s1msblo_); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s2_); (s2hi4_) = hl_.hilo_.hi_; (s2lo4_) = hl_.hilo_.lo_; } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1lo7_); (s1lo7hi4_) = hl_.hilo_.hi_; (s1lo7lo4_) = hl_.hilo_.lo_; } while (0); s1msbdiv2hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2hi4_, zero4_); s1msbdiv2lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2lo4_, zero4_); s1lo7hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7hi4_, zero4_); s1lo7lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7lo4_, zero4_); mulhilo7_ = __builtin_vis_fmul8x16(s2hi4_, s1lo7hi_); mullolo7_ = __builtin_vis_fmul8x16(s2lo4_, s1lo7lo_); mulhimsbdiv2_ = __builtin_vis_fmul8x16(s2hi4_, s1msbdiv2hi_); mullomsbdiv2_ = __builtin_vis_fmul8x16(s2lo4_, s1msbdiv2lo_); mulhi_ = mulhilo7_ + mulhimsbdiv2_ + mulhimsbdiv2_; mullo_ = mullolo7_ + mullomsbdiv2_ + mullomsbdiv2_; mulhihi_ = mulhi_ & ~masklow_; mulhilo_ = mulhi_ & masklow_; mullohi_ = mullo_ & ~masklow_; mullolo_ = mullo_ & masklow_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (accvin_); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); maclo_ = __builtin_vis_pdist ((rc_vec_t)mullolo_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i)); maclo_ = __builtin_vis_pdist ((rc_vec_t)mulhilo_, ((rc_vec_t) {0}), maclo_); machi_ = __builtin_vis_pdist ((rc_vec_t)mullohi_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i)); machi_ = __builtin_vis_pdist ((rc_vec_t)mulhihi_, ((rc_vec_t) {0}), machi_); do { typedef union { struct { rc_vec4_type_ hi_, lo_; } hilo_; rc_vec_t v_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) {{((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)machi_)).v)), ((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)maclo_)).v))}}; (accvout_) = hl_.v_; } while (0); __asm__("\n;# dep fake GSR %[fakegsr] on %[xdep]" : [fakegsr] "=brm" (rc_gsr_fakedep_) : [xdep] "brm" (accvout_), "0" (rc_gsr_fakedep_)); (a11) = accvout_; } while (0); do { rc_vec_t s1_ = (v2); rc_vec_t s2_ = (v2); rc_vec_t accvin_ = (a22); rc_vec_t s1lo7_, s1msb_, accvout_; uint32_t maclo_, machi_; rc_svec_type_ masklow_ = (rc_svec_type_){(255), (255), (255), (255)}; rc_svec_type_ s1msbhi_, s1msblo_, s1lo7hi_, s1lo7lo_; rc_svec_type_ s1msbdiv2hi_, s1msbdiv2lo_; rc_vec4_type_ s1lo7hi4_, s1lo7lo4_, s1msbhi4_, s1msblo4_; rc_vec4_type_ s1msbdiv2hi4_, s1msbdiv2lo4_, s2hi4_, s2lo4_; rc_vec4_type_ accvhi4_, accvlo4_; rc_svec_type_ mulhilo7_, mullolo7_, mulhimsbdiv2_, mullomsbdiv2_; rc_svec_type_ mulhi_, mullo_, mulhihi_, mullohi_; rc_svec_type_ mulhilo_, mullolo_; rc_vec4_type_ zero4_ = (((union { rc_vec4_type_ v; uint64_t i; })(uint64_t)(0)).v); rc_vec_t msb_ = (rc_vec_t){(0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80)}; ((s1msb_) = (s1_) & (msb_)); ((s1lo7_) = (s1_) & (~msb_)); do { if (rc_gsr_ldinit_) { extern void rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(void); rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(); } if (!__builtin_constant_p(rc_gsr_align_) || !__builtin_constant_p(2) || !rc_gsr_set_ || (unsigned) (rc_gsr_align_) != rc_gsr_align_ || (unsigned) (2) != rc_gsr_scale_) { rc_gsr_set_ = 1; rc_gsr_align_ = (rc_gsr_align_); rc_gsr_scale_ = (2); unsigned int val_ = (rc_gsr_scale_ << 3) | rc_gsr_align_; if (__builtin_constant_p (val_)) { __asm__("wr %%g0,%[gsrval],%%gsr\n" ";# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "i" (val_), "1" (rc_gsr_fakedep_)); } else { __asm__("wr %[gsrval],0,%%gsr" "\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "r" (val_), "1" (rc_gsr_fakedep_)); } } else { __asm__("\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_) : "0" (s1msb_), [fakegsr] "g" (rc_gsr_fakedep_)); } } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1msb_); (s1msbhi4_) = hl_.hilo_.hi_; (s1msblo4_) = hl_.hilo_.lo_; } while (0); s1msbhi_ = __builtin_vis_fexpand(s1msbhi4_); s1msblo_ = __builtin_vis_fexpand(s1msblo4_); s1msbdiv2hi4_ = __builtin_vis_fpack16(s1msbhi_); s1msbdiv2lo4_ = __builtin_vis_fpack16(s1msblo_); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s2_); (s2hi4_) = hl_.hilo_.hi_; (s2lo4_) = hl_.hilo_.lo_; } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1lo7_); (s1lo7hi4_) = hl_.hilo_.hi_; (s1lo7lo4_) = hl_.hilo_.lo_; } while (0); s1msbdiv2hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2hi4_, zero4_); s1msbdiv2lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2lo4_, zero4_); s1lo7hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7hi4_, zero4_); s1lo7lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7lo4_, zero4_); mulhilo7_ = __builtin_vis_fmul8x16(s2hi4_, s1lo7hi_); mullolo7_ = __builtin_vis_fmul8x16(s2lo4_, s1lo7lo_); mulhimsbdiv2_ = __builtin_vis_fmul8x16(s2hi4_, s1msbdiv2hi_); mullomsbdiv2_ = __builtin_vis_fmul8x16(s2lo4_, s1msbdiv2lo_); mulhi_ = mulhilo7_ + mulhimsbdiv2_ + mulhimsbdiv2_; mullo_ = mullolo7_ + mullomsbdiv2_ + mullomsbdiv2_; mulhihi_ = mulhi_ & ~masklow_; mulhilo_ = mulhi_ & masklow_; mullohi_ = mullo_ & ~masklow_; mullolo_ = mullo_ & masklow_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (accvin_); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); maclo_ = __builtin_vis_pdist ((rc_vec_t)mullolo_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i)); maclo_ = __builtin_vis_pdist ((rc_vec_t)mulhilo_, ((rc_vec_t) {0}), maclo_); machi_ = __builtin_vis_pdist ((rc_vec_t)mullohi_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i)); machi_ = __builtin_vis_pdist ((rc_vec_t)mulhihi_, ((rc_vec_t) {0}), machi_); do { typedef union { struct { rc_vec4_type_ hi_, lo_; } hilo_; rc_vec_t v_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) {{((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)machi_)).v)), ((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)maclo_)).v))}}; (accvout_) = hl_.v_; } while (0); __asm__("\n;# dep fake GSR %[fakegsr] on %[xdep]" : [fakegsr] "=brm" (rc_gsr_fakedep_) : [xdep] "brm" (accvout_), "0" (rc_gsr_fakedep_)); (a22) = accvout_; } while (0); do { rc_vec_t s1_ = (v1); rc_vec_t s2_ = (v2); rc_vec_t accvin_ = (a12); rc_vec_t s1lo7_, s1msb_, accvout_; uint32_t maclo_, machi_; rc_svec_type_ masklow_ = (rc_svec_type_){(255), (255), (255), (255)}; rc_svec_type_ s1msbhi_, s1msblo_, s1lo7hi_, s1lo7lo_; rc_svec_type_ s1msbdiv2hi_, s1msbdiv2lo_; rc_vec4_type_ s1lo7hi4_, s1lo7lo4_, s1msbhi4_, s1msblo4_; rc_vec4_type_ s1msbdiv2hi4_, s1msbdiv2lo4_, s2hi4_, s2lo4_; rc_vec4_type_ accvhi4_, accvlo4_; rc_svec_type_ mulhilo7_, mullolo7_, mulhimsbdiv2_, mullomsbdiv2_; rc_svec_type_ mulhi_, mullo_, mulhihi_, mullohi_; rc_svec_type_ mulhilo_, mullolo_; rc_vec4_type_ zero4_ = (((union { rc_vec4_type_ v; uint64_t i; })(uint64_t)(0)).v); rc_vec_t msb_ = (rc_vec_t){(0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80), (0x80)}; ((s1msb_) = (s1_) & (msb_)); ((s1lo7_) = (s1_) & (~msb_)); do { if (rc_gsr_ldinit_) { extern void rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(void); rc_mixing_GSR_setting_with_RC_VEC_LDINIT_(); } if (!__builtin_constant_p(rc_gsr_align_) || !__builtin_constant_p(2) || !rc_gsr_set_ || (unsigned) (rc_gsr_align_) != rc_gsr_align_ || (unsigned) (2) != rc_gsr_scale_) { rc_gsr_set_ = 1; rc_gsr_align_ = (rc_gsr_align_); rc_gsr_scale_ = (2); unsigned int val_ = (rc_gsr_scale_ << 3) | rc_gsr_align_; if (__builtin_constant_p (val_)) { __asm__("wr %%g0,%[gsrval],%%gsr\n" ";# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "i" (val_), "1" (rc_gsr_fakedep_)); } else { __asm__("wr %[gsrval],0,%%gsr" "\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_), [fakegsr] "=rm" (rc_gsr_fakedep_) : "0" (s1msb_), [gsrval] "r" (val_), "1" (rc_gsr_fakedep_)); } } else { __asm__("\n;# dep %[depvec] on fake GSR %[fakegsr]" : [depvec] "=brm" (s1msb_) : "0" (s1msb_), [fakegsr] "g" (rc_gsr_fakedep_)); } } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1msb_); (s1msbhi4_) = hl_.hilo_.hi_; (s1msblo4_) = hl_.hilo_.lo_; } while (0); s1msbhi_ = __builtin_vis_fexpand(s1msbhi4_); s1msblo_ = __builtin_vis_fexpand(s1msblo4_); s1msbdiv2hi4_ = __builtin_vis_fpack16(s1msbhi_); s1msbdiv2lo4_ = __builtin_vis_fpack16(s1msblo_); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s2_); (s2hi4_) = hl_.hilo_.hi_; (s2lo4_) = hl_.hilo_.lo_; } while (0); do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (s1lo7_); (s1lo7hi4_) = hl_.hilo_.hi_; (s1lo7lo4_) = hl_.hilo_.lo_; } while (0); s1msbdiv2hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2hi4_, zero4_); s1msbdiv2lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1msbdiv2lo4_, zero4_); s1lo7hi_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7hi4_, zero4_); s1lo7lo_ = (rc_svec_type_)__builtin_vis_fpmerge(s1lo7lo4_, zero4_); mulhilo7_ = __builtin_vis_fmul8x16(s2hi4_, s1lo7hi_); mullolo7_ = __builtin_vis_fmul8x16(s2lo4_, s1lo7lo_); mulhimsbdiv2_ = __builtin_vis_fmul8x16(s2hi4_, s1msbdiv2hi_); mullomsbdiv2_ = __builtin_vis_fmul8x16(s2lo4_, s1msbdiv2lo_); mulhi_ = mulhilo7_ + mulhimsbdiv2_ + mulhimsbdiv2_; mullo_ = mullolo7_ + mullomsbdiv2_ + mullomsbdiv2_; mulhihi_ = mulhi_ & ~masklow_; mulhilo_ = mulhi_ & masklow_; mullohi_ = mullo_ & ~masklow_; mullolo_ = mullo_ & masklow_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (accvin_); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); maclo_ = __builtin_vis_pdist ((rc_vec_t)mullolo_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i)); maclo_ = __builtin_vis_pdist ((rc_vec_t)mulhilo_, ((rc_vec_t) {0}), maclo_); machi_ = __builtin_vis_pdist ((rc_vec_t)mullohi_, ((rc_vec_t) {0}), (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i)); machi_ = __builtin_vis_pdist ((rc_vec_t)mulhihi_, ((rc_vec_t) {0}), machi_); do { typedef union { struct { rc_vec4_type_ hi_, lo_; } hilo_; rc_vec_t v_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) {{((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)machi_)).v)), ((((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)((uint32_t)maclo_)).v))}}; (accvout_) = hl_.v_; } while (0); __asm__("\n;# dep fake GSR %[fakegsr] on %[xdep]" : [fakegsr] "=brm" (rc_gsr_fakedep_) : [xdep] "brm" (accvout_), "0" (rc_gsr_fakedep_)); (a12) = accvout_; } while (0); (i1) += 8; (i2) += 8; } while (0);
+        }
+        do { uint32_t t1, t2, t11, t22, t12; ((t1) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a1)).i)); ((t2) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a2)).i)); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a11); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t11) = maclo_ + machi_ * 256; } while (0); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a22); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t22) = maclo_ + machi_ * 256; } while (0); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a12); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t12) = maclo_ + machi_ * 256; } while (0); ((a1) = ((rc_vec_t) {0})); ((a2) = ((rc_vec_t) {0})); ((a11) = ((rc_vec_t) {0})); ((a22) = ((rc_vec_t) {0})); ((a12) = ((rc_vec_t) {0})); (s1) += t1; (s2) += t2; (s11) += t11; (s22) += t22; (s12) += t12; } while (0);
+
+        do { uint32_t t1, t2, t11, t22, t12; ((t1) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a1)).i)); ((t2) = (((union { rc_vec_t v; uint64_t i; })(uint64_t)(a2)).i)); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a11); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t11) = maclo_ + machi_ * 256; } while (0); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a22); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t22) = maclo_ + machi_ * 256; } while (0); do { rc_vec4_type_ accvhi4_, accvlo4_; uint64_t machi_, maclo_; do { typedef union { rc_vec_t v_; struct { rc_vec4_type_ hi_, lo_; } hilo_; } RC_hl_type_; RC_hl_type_ hl_ = (RC_hl_type_) (a12); (accvhi4_) = hl_.hilo_.hi_; (accvlo4_) = hl_.hilo_.lo_; } while (0); machi_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvhi4_)).i); maclo_ = (((union { rc_vec4_type_ v; uint32_t i; })(uint32_t)(accvlo4_)).i); (t12) = maclo_ + machi_ * 256; } while (0); ((a1) = ((rc_vec_t) {0})); ((a2) = ((rc_vec_t) {0})); ((a11) = ((rc_vec_t) {0})); ((a22) = ((rc_vec_t) {0})); ((a12) = ((rc_vec_t) {0})); (s1) += t1; (s2) += t2; (s11) += t11; (s22) += t22; (s12) += t12; } while (0);
+    }
+    sum[0] = s1;
+    sum[1] = s2;
+    sum[2] = s11;
+    sum[3] = s22;
+    sum[4] = s12;
+    ;
+}